diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json index 389793bc6..607057e6b 100644 --- a/.claude-plugin/marketplace.json +++ b/.claude-plugin/marketplace.json @@ -129,7 +129,7 @@ { "name": "product-skills", "source": "./product-team", - "description": "12 product skills with 13 Python tools: product manager toolkit (RICE, PRDs), agile product owner, product strategist, UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, product analytics, experiment designer, product discovery, roadmap communicator.", + "description": "14 product skills with 15 Python tools: product manager toolkit (RICE, PRDs), agile product owner, product strategist, UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, product analytics, experiment designer, product discovery, roadmap communicator, code-to-prd, research summarizer.", "version": "2.1.2", "author": { "name": "Alireza Rezvani" diff --git a/.claude/commands/plugin-audit.md b/.claude/commands/plugin-audit.md new file mode 100644 index 000000000..51f680e1f --- /dev/null +++ b/.claude/commands/plugin-audit.md @@ -0,0 +1,153 @@ +--- +description: Run the full 8-phase plugin audit pipeline on a skill directory. +--- + +Run the comprehensive plugin audit pipeline on the skill at `$ARGUMENTS`. If no argument provided, ask the user for the skill path. + +Execute all 8 phases sequentially. Auto-fix non-critical issues. Only prompt the user for critical decisions (external dependencies, security findings, breaking changes). + +## Phase 1: Discovery + +1. Verify `$ARGUMENTS` exists and contains `SKILL.md`. If not, error and stop. +2. Read `SKILL.md` frontmatter — extract `name`, `description`, `Category`, `Tier`. +3. Detect components: + - `scripts/*.py` → Python tools (count them) + - `references/*.md` → reference docs (count them) + - `assets/` → templates/samples + - `expected_outputs/` → test fixtures + - `agents/*.md` → embedded agents + - `skills/*/SKILL.md` → sub-skills (compound skill) + - `.claude-plugin/plugin.json` → standalone plugin + - `settings.json` → command registrations +4. Detect domain from path (`engineering/`, `product-team/`, `marketing-skill/`, etc.) +5. Search `commands/` for a `.md` file matching the skill name. +6. Display discovery summary. + +## Phase 2: Structure Validation + +Run: +```bash +python3 engineering/skill-tester/scripts/skill_validator.py $ARGUMENTS --json +``` + +Parse JSON. If score < 75: +- Auto-fix missing frontmatter fields, missing section headings, missing directories. +- Re-run. If still < 75, mark as FAIL but continue collecting results. + +## Phase 3: Quality Scoring + +Run: +```bash +python3 engineering/skill-tester/scripts/quality_scorer.py $ARGUMENTS --detailed --json +``` + +Parse JSON. If score < 60, report improvement roadmap items. + +## Phase 4: Script Testing + +If `$ARGUMENTS/scripts/` contains `.py` files, run: +```bash +python3 engineering/skill-tester/scripts/script_tester.py $ARGUMENTS --json --verbose +``` + +All scripts must PASS. If any script uses external imports, **ask the user** whether the dependency is acceptable. + +## Phase 5: Security Audit + +Run: +```bash +python3 engineering/skill-security-auditor/scripts/skill_security_auditor.py $ARGUMENTS --strict --json +``` + +Zero CRITICAL or HIGH findings required. **Do NOT auto-fix security issues** — report them to the user with file, line, pattern, and recommended fix. + +## Phase 6: Marketplace & Plugin Compliance + +### 6a. plugin.json +If `$ARGUMENTS/.claude-plugin/plugin.json` exists: +- Must be valid JSON +- Only allowed fields: `name`, `description`, `version`, `author`, `homepage`, `repository`, `license`, `skills` +- Version must be `2.1.2` +- Auto-fix version mismatches and remove extra fields. + +### 6b. settings.json +If `$ARGUMENTS/settings.json` exists: +- Must be valid JSON +- Version must match repo version +- Each command in `commands` field must have a matching `commands/*.md` file + +### 6c. Marketplace entry +Check `.claude-plugin/marketplace.json` for an entry with `source` matching `./$ARGUMENTS`. Verify version and name match. + +### 6d. Domain plugin.json +Check the parent domain's `.claude-plugin/plugin.json` — verify skill count in description matches actual count. Auto-fix stale counts. + +## Phase 7: Ecosystem Integration + +### 7a. Cross-platform sync +Verify skill appears in `.codex/skills-index.json` and `.gemini/skills-index.json`. If missing: +```bash +python3 scripts/sync-codex-skills.py --verbose +python3 scripts/sync-gemini-skills.py --verbose +``` + +### 7b. Command integration +If the skill has associated commands, verify: +- Command `.md` has valid frontmatter +- Command references the correct skill +- Command is in `mkdocs.yml` nav +Auto-fix missing nav entries. + +### 7c. Agent integration +Check for embedded agents in `$ARGUMENTS/agents/`. Search `agents/` for cs-* agents that reference this skill. Verify references resolve. + +### 7d. Cross-skill dependencies +Read SKILL.md for references to other skills (`../` paths, "Related Skills" sections). Verify each referenced skill exists. + +## Phase 8: Domain Code Review + +Based on the domain, apply the appropriate agent's review criteria: + +| Domain | Agent | Focus | +|--------|-------|-------| +| `engineering/` or `engineering-team/` | cs-senior-engineer | Architecture, code quality, CI/CD | +| `product-team/` | cs-product-manager | PRD quality, user stories, RICE | +| `marketing-skill/` | cs-content-creator | Content quality, SEO, brand voice | +| `ra-qm-team/` | cs-quality-regulatory | Compliance, audit trail, regulatory | +| `business-growth/` | cs-growth-strategist | Growth metrics, revenue impact | +| `finance/` | cs-financial-analyst | Model accuracy, metric definitions | +| Other | cs-senior-engineer | General code review | + +Read the agent's `.md` file for review criteria. Apply those criteria to the skill's SKILL.md, scripts, and references. Check: +- Workflows are actionable and complete +- Scripts solve the stated problem +- References contain accurate domain knowledge +- No broken internal links +- Attribution present where required + +## Final Report + +Present all results in a structured summary: + +``` +╔══════════════════════════════════════════════════════════════╗ +║ PLUGIN AUDIT REPORT: {skill_name} ║ +╠══════════════════════════════════════════════════════════════╣ +║ Phase 1 — Discovery ✅ {type}, {domain} ║ +║ Phase 2 — Structure ✅ {score}/100 ({level}) ║ +║ Phase 3 — Quality ✅ {score}/100 ({grade}) ║ +║ Phase 4 — Scripts ✅ {n}/{n} PASS ║ +║ Phase 5 — Security ✅ PASS (0 critical, 0 high) ║ +║ Phase 6 — Marketplace ✅ plugin.json valid ║ +║ Phase 7 — Ecosystem ✅ synced ║ +║ Phase 8 — Code Review ✅ passed ║ +║ ║ +║ VERDICT: ✅ PASS ║ +║ Auto-fixes: {n} | Warnings: {n} | Action items: {n} ║ +╚══════════════════════════════════════════════════════════════╝ +``` + +**Verdict rules:** +- All phases pass → **PASS** +- Only warnings → **PASS WITH WARNINGS** +- Any blocker (structure <75, quality <60, script FAIL, security CRITICAL/HIGH, invalid plugin.json) → **FAIL** diff --git a/.codex/skills-index.json b/.codex/skills-index.json index 314436457..0ff5e140b 100644 --- a/.codex/skills-index.json +++ b/.codex/skills-index.json @@ -3,7 +3,7 @@ "name": "claude-code-skills", "description": "Production-ready skill packages for AI agents - Marketing, Engineering, Product, C-Level, PM, and RA/QM", "repository": "https://github.com/alirezarezvani/claude-skills", - "total_skills": 162, + "total_skills": 163, "skills": [ { "name": "contract-and-proposal-writer", @@ -797,6 +797,12 @@ "category": "product", "description": "Agile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use for writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing backlog." }, + { + "name": "code-to-prd", + "source": "../../product-team/code-to-prd", + "category": "product", + "description": "|" + }, { "name": "competitive-teardown", "source": "../../product-team/competitive-teardown", @@ -1010,7 +1016,7 @@ "description": "Marketing, content, and demand generation skills" }, "product": { - "count": 13, + "count": 14, "source": "../../product-team", "description": "Product management and design skills" }, diff --git a/.codex/skills/code-to-prd b/.codex/skills/code-to-prd new file mode 120000 index 000000000..9c44227ee --- /dev/null +++ b/.codex/skills/code-to-prd @@ -0,0 +1 @@ +../../product-team/code-to-prd \ No newline at end of file diff --git a/.gemini/skills-index.json b/.gemini/skills-index.json index e0ed693e2..aafa43fd2 100644 --- a/.gemini/skills-index.json +++ b/.gemini/skills-index.json @@ -1,7 +1,7 @@ { "version": "1.0.0", "name": "gemini-cli-skills", - "total_skills": 229, + "total_skills": 240, "skills": [ { "name": "README", @@ -13,6 +13,11 @@ "category": "agent", "description": "One paragraph describing what this agent does, who it's for, and when to activate it." }, + { + "name": "content-strategist", + "category": "agent", + "description": "Builds content engines that rank, convert, and compound. Thinks in systems \u2014 topic clusters, not individual posts. Every piece earns its place or gets killed." + }, { "name": "cs-agile-product-owner", "category": "agent", @@ -93,11 +98,26 @@ "category": "agent", "description": "Google Workspace administration agent using the gws CLI. Orchestrates workspace setup, Gmail/Drive/Sheets/Calendar automation, security audits, and recipe execution. Spawn when users need Google Workspace automation, gws CLI help, or workspace administration." }, + { + "name": "devops-engineer", + "category": "agent", + "description": "Builds infrastructure that scales without babysitting. Automates everything worth automating. Monitors before it breaks. Treats clicking in consoles as a production incident waiting to happen." + }, + { + "name": "finance-lead", + "category": "agent", + "description": "Startup CFO who builds models that survive contact with reality. Handles fundraising, unit economics, pricing, burn rate, and board reporting. Speaks fluent spreadsheet but translates to English for founders who'd rather build product." + }, { "name": "growth-marketer", "category": "agent", "description": "Growth marketing specialist for bootstrapped startups and indie hackers. Builds content engines, optimizes funnels, runs launch sequences, and finds scalable acquisition channels \u2014 all on a budget that makes enterprise marketers cry." }, + { + "name": "product-manager", + "category": "agent", + "description": "Ships outcomes, not features. Writes specs engineers actually read. Prioritizes ruthlessly. Kills darlings when the data says so. Operates at the intersection of user needs, business goals, and engineering reality." + }, { "name": "solo-founder", "category": "agent", @@ -111,7 +131,7 @@ { "name": "business-growth-bundle", "category": "business-growth", - "description": "4 production-ready business and growth skills: customer success manager with health scoring and churn prediction, sales engineer with RFP analysis, revenue operations with pipeline and GTM metrics, and contract & proposal writer. Python tools included (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw." + "description": "4 business growth agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Customer success (health scoring, churn), sales engineer (RFP), revenue operations (pipeline, GTM), contract & proposal writer. Python tools (stdlib-only)." }, { "name": "contract-and-proposal-writer", @@ -156,7 +176,7 @@ { "name": "c-level-advisor-bundle", "category": "c-level", - "description": "Provides strategic business advice by channelling the perspectives of 10 executive roles \u2014 CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, and Executive Mentor \u2014 across decisions, trade-offs, and org challenges. Runs multi-role board meetings, routes questions to the right executive voice, and delivers structured recommendations (Bottom Line \u2192 What \u2192 Why \u2192 How to Act \u2192 Your Decision). Use when a founder or executive needs business strategy advice, leadership perspective, executive decision support, board-level input, fundraising guidance, product-market fit review, hiring or culture frameworks, risk assessment, or competitive analysis." + "description": "10 C-level advisory agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO, Executive Mentor. Multi-role board meetings, strategy routing, structured recommendations. For founders needing executive-level decision support." }, { "name": "ceo-advisor", @@ -308,6 +328,11 @@ "category": "command", "description": "Generate changelogs from git history and validate conventional commits. Usage: /changelog [options]" }, + { + "name": "cmd-code-to-prd", + "category": "command", + "description": "Reverse-engineer a frontend codebase into a PRD. Usage: /code-to-prd [path]" + }, { "name": "competitive-matrix", "category": "command", @@ -416,7 +441,12 @@ { "name": "engineering-team-bundle", "category": "engineering", - "description": "23 production-ready engineering skills covering architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, computer vision, and specialized tools like Playwright Pro, Stripe integration, AWS, and MS365. 30+ Python automation tools (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw." + "description": "23 engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365. 30+ Python tools (stdlib-only)." + }, + { + "name": "epic-design", + "category": "engineering", + "description": ">" }, { "name": "extract", @@ -638,10 +668,15 @@ "category": "engineering-advanced", "description": "Dependency Auditor" }, + { + "name": "docker-development", + "category": "engineering-advanced", + "description": "Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening. Use when: user wants to optimize a Dockerfile, create or improve docker-compose configurations, implement multi-stage builds, audit container security, reduce image size, or follow container best practices. Covers build performance, layer caching, secret management, and production-ready container patterns." + }, { "name": "engineering-bundle", "category": "engineering-advanced", - "description": "25 advanced POWERFUL-tier engineering skills covering agent design, RAG architecture, MCP servers, CI/CD pipelines, database design, observability, security auditing, release management, and platform operations. Works with Claude Code, Codex CLI, and OpenClaw." + "description": "25 advanced engineering agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Agent design, RAG, MCP servers, CI/CD, database design, observability, security auditing, release management, platform ops." }, { "name": "env-secrets-manager", @@ -653,6 +688,11 @@ "category": "engineering-advanced", "description": "Git Worktree Manager" }, + { + "name": "helm-chart-builder", + "category": "engineering-advanced", + "description": "Helm chart development agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw \u2014 chart scaffolding, values design, template patterns, dependency management, security hardening, and chart testing. Use when: user wants to create or improve Helm charts, design values.yaml files, implement template helpers, audit chart security (RBAC, network policies, pod security), manage subcharts, or run helm lint/test." + }, { "name": "interview-system-designer", "category": "engineering-advanced", @@ -748,10 +788,15 @@ "category": "engineering-advanced", "description": "Scan codebases for technical debt, score severity, track trends, and generate prioritized remediation plans. Use when users mention tech debt, code quality, refactoring priority, debt scoring, cleanup sprints, or code health assessment. Also use for legacy code modernization planning and maintenance cost estimation." }, + { + "name": "terraform-patterns", + "category": "engineering-advanced", + "description": "Terraform infrastructure-as-code agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Covers module design patterns, state management strategies, provider configuration, security hardening, policy-as-code with Sentinel/OPA, and CI/CD plan/apply workflows. Use when: user wants to design Terraform modules, manage state backends, review Terraform security, implement multi-region deployments, or follow IaC best practices." + }, { "name": "finance-bundle", "category": "finance", - "description": "Production-ready financial analyst skill with ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction. 4 Python tools (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw." + "description": "Financial analyst agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Ratio analysis, DCF valuation, budget variance, rolling forecasts. 4 Python tools (stdlib-only)." }, { "name": "financial-analyst", @@ -891,7 +936,7 @@ { "name": "marketing-skill-bundle", "category": "marketing", - "description": "42-skill marketing division for AI coding agents. 7 specialist pods covering content, SEO, CRO, channels, growth, intelligence, and sales. Foundation context system + orchestration router. 27 Python tools (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw." + "description": "42 marketing agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more coding agents. 7 pods: content, SEO, CRO, channels, growth, intelligence, sales. Foundation context + orchestration router. 27 Python tools (stdlib-only)." }, { "name": "marketing-strategy-pmm", @@ -988,6 +1033,11 @@ "category": "product", "description": "Agile product ownership for backlog management and sprint execution. Covers user story writing, acceptance criteria, sprint planning, and velocity tracking. Use for writing user stories, creating acceptance criteria, planning sprints, estimating story points, breaking down epics, or prioritizing backlog." }, + { + "name": "code-to-prd", + "category": "product", + "description": "|" + }, { "name": "competitive-teardown", "category": "product", @@ -1026,7 +1076,12 @@ { "name": "product-team-bundle", "category": "product", - "description": "8 production-ready product skills: product manager toolkit with RICE prioritization, agile product owner, product strategist with OKR cascades, UX researcher, UI design system, competitive teardown, landing page generator, and SaaS scaffolder. Python tools included (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw." + "description": "10 product agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. PM toolkit (RICE), agile PO, product strategist (OKR), UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, research summarizer. Python tools (stdlib-only)." + }, + { + "name": "research-summarizer", + "category": "product", + "description": "Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw." }, { "name": "roadmap-communicator", @@ -1071,7 +1126,7 @@ { "name": "project-management-bundle", "category": "project-management", - "description": "6 production-ready project management skills for Atlassian users: senior PM with portfolio management, scrum master with velocity forecasting, Jira expert with JQL mastery, Confluence expert, Atlassian admin, and template creator. MCP integration for live Jira/Confluence automation. Works with Claude Code, Codex CLI, and OpenClaw." + "description": "6 project management agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Senior PM, scrum master, Jira expert (JQL), Confluence expert, Atlassian admin, template creator. MCP integration for live Jira/Confluence automation." }, { "name": "scrum-master", @@ -1136,7 +1191,7 @@ { "name": "ra-qm-team-bundle", "category": "ra-qm", - "description": "12 production-ready regulatory affairs and quality management skills for HealthTech/MedTech: ISO 13485 QMS, MDR 2017/745, FDA 510(k)/PMA, ISO 27001 ISMS, GDPR/DSGVO compliance, risk management (ISO 14971), CAPA, document control, and internal auditing. Python tools included (all stdlib-only). Works with Claude Code, Codex CLI, and OpenClaw." + "description": "12 regulatory & QM agent skills and plugins for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. ISO 13485 QMS, MDR 2017/745, FDA 510(k)/PMA, ISO 27001 ISMS, GDPR/DSGVO, risk management (ISO 14971), CAPA, document control, auditing. Python tools (stdlib-only)." }, { "name": "regulatory-affairs-head", @@ -1151,7 +1206,7 @@ ], "categories": { "agent": { - "count": 21, + "count": 25, "description": "Agent resources" }, "business-growth": { @@ -1163,15 +1218,15 @@ "description": "C-level resources" }, "command": { - "count": 17, + "count": 18, "description": "Command resources" }, "engineering": { - "count": 39, + "count": 40, "description": "Engineering resources" }, "engineering-advanced": { - "count": 33, + "count": 36, "description": "Engineering-advanced resources" }, "finance": { @@ -1183,7 +1238,7 @@ "description": "Marketing resources" }, "product": { - "count": 13, + "count": 15, "description": "Product resources" }, "project-management": { diff --git a/.gemini/skills/README/SKILL.md b/.gemini/skills/README/SKILL.md new file mode 120000 index 000000000..0a694b7f2 --- /dev/null +++ b/.gemini/skills/README/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/README.md \ No newline at end of file diff --git a/.gemini/skills/TEMPLATE/SKILL.md b/.gemini/skills/TEMPLATE/SKILL.md new file mode 120000 index 000000000..2139c8895 --- /dev/null +++ b/.gemini/skills/TEMPLATE/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/TEMPLATE.md \ No newline at end of file diff --git a/.gemini/skills/cmd-code-to-prd/SKILL.md b/.gemini/skills/cmd-code-to-prd/SKILL.md new file mode 120000 index 000000000..fadc8a6c8 --- /dev/null +++ b/.gemini/skills/cmd-code-to-prd/SKILL.md @@ -0,0 +1 @@ +../../../commands/code-to-prd.md \ No newline at end of file diff --git a/.gemini/skills/code-to-prd/SKILL.md b/.gemini/skills/code-to-prd/SKILL.md new file mode 120000 index 000000000..63d387a7d --- /dev/null +++ b/.gemini/skills/code-to-prd/SKILL.md @@ -0,0 +1 @@ +../../../product-team/code-to-prd/SKILL.md \ No newline at end of file diff --git a/.gemini/skills/content-strategist/SKILL.md b/.gemini/skills/content-strategist/SKILL.md new file mode 120000 index 000000000..5af444a7f --- /dev/null +++ b/.gemini/skills/content-strategist/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/content-strategist.md \ No newline at end of file diff --git a/.gemini/skills/devops-engineer/SKILL.md b/.gemini/skills/devops-engineer/SKILL.md new file mode 120000 index 000000000..6093dd69a --- /dev/null +++ b/.gemini/skills/devops-engineer/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/devops-engineer.md \ No newline at end of file diff --git a/.gemini/skills/docker-development/SKILL.md b/.gemini/skills/docker-development/SKILL.md new file mode 120000 index 000000000..9820e68c5 --- /dev/null +++ b/.gemini/skills/docker-development/SKILL.md @@ -0,0 +1 @@ +../../../engineering/docker-development/SKILL.md \ No newline at end of file diff --git a/.gemini/skills/epic-design/SKILL.md b/.gemini/skills/epic-design/SKILL.md new file mode 120000 index 000000000..238c184f6 --- /dev/null +++ b/.gemini/skills/epic-design/SKILL.md @@ -0,0 +1 @@ +../../../engineering-team/epic-design/SKILL.md \ No newline at end of file diff --git a/.gemini/skills/finance-lead/SKILL.md b/.gemini/skills/finance-lead/SKILL.md new file mode 120000 index 000000000..ef9ff63ae --- /dev/null +++ b/.gemini/skills/finance-lead/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/finance-lead.md \ No newline at end of file diff --git a/.gemini/skills/growth-marketer/SKILL.md b/.gemini/skills/growth-marketer/SKILL.md new file mode 120000 index 000000000..1b8776d3d --- /dev/null +++ b/.gemini/skills/growth-marketer/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/growth-marketer.md \ No newline at end of file diff --git a/.gemini/skills/helm-chart-builder/SKILL.md b/.gemini/skills/helm-chart-builder/SKILL.md new file mode 120000 index 000000000..0ca240f2e --- /dev/null +++ b/.gemini/skills/helm-chart-builder/SKILL.md @@ -0,0 +1 @@ +../../../engineering/helm-chart-builder/SKILL.md \ No newline at end of file diff --git a/.gemini/skills/product-manager/SKILL.md b/.gemini/skills/product-manager/SKILL.md new file mode 120000 index 000000000..5f28924f1 --- /dev/null +++ b/.gemini/skills/product-manager/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/product-manager.md \ No newline at end of file diff --git a/.gemini/skills/research-summarizer/SKILL.md b/.gemini/skills/research-summarizer/SKILL.md new file mode 120000 index 000000000..09abd430d --- /dev/null +++ b/.gemini/skills/research-summarizer/SKILL.md @@ -0,0 +1 @@ +../../../product-team/research-summarizer/SKILL.md \ No newline at end of file diff --git a/.gemini/skills/solo-founder/SKILL.md b/.gemini/skills/solo-founder/SKILL.md new file mode 120000 index 000000000..148ad6055 --- /dev/null +++ b/.gemini/skills/solo-founder/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/solo-founder.md \ No newline at end of file diff --git a/.gemini/skills/startup-cto/SKILL.md b/.gemini/skills/startup-cto/SKILL.md new file mode 120000 index 000000000..e5414fd15 --- /dev/null +++ b/.gemini/skills/startup-cto/SKILL.md @@ -0,0 +1 @@ +../../../agents/personas/startup-cto.md \ No newline at end of file diff --git a/.gemini/skills/terraform-patterns/SKILL.md b/.gemini/skills/terraform-patterns/SKILL.md new file mode 120000 index 000000000..1f246731b --- /dev/null +++ b/.gemini/skills/terraform-patterns/SKILL.md @@ -0,0 +1 @@ +../../../engineering/terraform-patterns/SKILL.md \ No newline at end of file diff --git a/commands/plugin-audit.md b/commands/plugin-audit.md new file mode 100644 index 000000000..04c3573a4 --- /dev/null +++ b/commands/plugin-audit.md @@ -0,0 +1,312 @@ +--- +name: plugin-audit +description: | + Comprehensive audit pipeline for skills, plugins, agents, and commands. Validates structure, + quality, security, marketplace compliance, cross-platform compatibility, and ecosystem integration. + Runs all built-in validation tools, invokes domain-appropriate agents for code review, + and produces a pass/fail gate report. Usage: /plugin-audit +--- + +# /plugin-audit + +Full audit pipeline for any skill, plugin, agent, or command in this repository. Runs 8 validation phases, auto-fixes what it can, and only stops for user input on critical decisions (breaking changes, new dependencies). + +## Usage + +```bash +/plugin-audit product-team/code-to-prd +/plugin-audit engineering/agenthub +/plugin-audit engineering-team/playwright-pro +``` + +## What It Does + +Execute all 8 phases sequentially. Stop on critical failures. Auto-fix non-critical issues. Report results at the end. + +--- + +## Phase 1: Discovery + +Identify what the skill contains and classify it. + +1. Verify `{skill_path}` exists and contains `SKILL.md` +2. Read `SKILL.md` frontmatter — extract `name`, `description`, `Category`, `Tier` +3. Detect skill type: + - Has `scripts/` → has Python tools + - Has `references/` → has reference docs + - Has `assets/` → has templates/samples + - Has `expected_outputs/` → has test fixtures + - Has `agents/` → has embedded agents + - Has `skills/` → has sub-skills (compound skill) + - Has `.claude-plugin/plugin.json` → is a standalone plugin + - Has `settings.json` → has command registrations +4. Detect domain from path: `engineering/`, `product-team/`, `marketing-skill/`, etc. +5. Check for associated command: search `commands/` for a `.md` file matching the skill name + +Display discovery summary before proceeding: +``` +Auditing: code-to-prd + Domain: product-team + Type: STANDARD skill with standalone plugin + Scripts: 2 | References: 2 | Assets: 1 | Expected outputs: 3 + Command: /code-to-prd (found) + Plugin: .claude-plugin/plugin.json (found) +``` + +--- + +## Phase 2: Structure Validation + +Run the skill-tester validator. + +```bash +python3 engineering/skill-tester/scripts/skill_validator.py {skill_path} --tier {detected_tier} --json +``` + +Parse the JSON output. Extract: +- Overall score and compliance level +- Failed checks (list each) +- Errors and warnings + +**Gate rule:** Score must be ≥ 75 (GOOD). If below 75: +- Read the errors list +- Auto-fix what's possible: + - Missing frontmatter fields → add them from SKILL.md content + - Missing sections → add stub headings + - Missing directories → create empty ones with a note +- Re-run after fixes. If still below 75, report as FAIL and continue to collect remaining results. + +--- + +## Phase 3: Quality Scoring + +Run the quality scorer. + +```bash +python3 engineering/skill-tester/scripts/quality_scorer.py {skill_path} --detailed --json +``` + +Parse the JSON output. Extract: +- Overall score and letter grade +- Per-dimension scores (Documentation, Code Quality, Completeness, Usability) +- Improvement roadmap items + +**Gate rule:** Score must be ≥ 60 (C). If below 60, report the improvement roadmap items as action items. + +--- + +## Phase 4: Script Testing + +If the skill has `scripts/` with `.py` files, run the script tester. + +```bash +python3 engineering/skill-tester/scripts/script_tester.py {skill_path} --json --verbose +``` + +Parse the JSON output. For each script, extract: +- Pass/Partial/Fail status +- Individual test results + +**Gate rule:** All scripts must PASS. Any FAIL is a blocker. PARTIAL triggers a warning. + +**Auto-fix:** If a script fails the `--help` test, check if it has `argparse` — if not, this is a real issue. If it fails the stdlib-only test, flag the import and **ask the user** whether the dependency is acceptable (this is a critical decision). + +--- + +## Phase 5: Security Audit + +Run the skill security auditor. + +```bash +python3 engineering/skill-security-auditor/scripts/skill_security_auditor.py {skill_path} --strict --json +``` + +Parse the JSON output. Extract: +- Verdict (PASS/WARN/FAIL) +- Critical findings (must be zero) +- High findings (must be zero in strict mode) +- Info findings (advisory only) + +**Gate rule:** Zero CRITICAL findings. Zero HIGH findings. Any CRITICAL or HIGH is a blocker — report the exact file, line, pattern, and recommended fix. + +**Do NOT auto-fix security issues.** Report them and let the user decide. + +--- + +## Phase 6: Marketplace & Plugin Compliance + +### 6a. plugin.json Validation + +If `{skill_path}/.claude-plugin/plugin.json` exists: + +1. Parse as JSON — must be valid +2. Verify only allowed fields: `name`, `description`, `version`, `author`, `homepage`, `repository`, `license`, `skills` +3. Version must match repo version (`2.1.2`) +4. `skills` must be `"./"` +5. `name` must match the skill directory name + +**Auto-fix:** If version is wrong, update it. If extra fields exist, remove them. + +### 6b. settings.json Validation + +If `{skill_path}/settings.json` exists: + +1. Parse as JSON — must be valid +2. Version must match repo version +3. If `commands` field exists, verify each command has a matching file in `commands/` + +### 6c. Marketplace Entry + +Check if the skill has an entry in `.claude-plugin/marketplace.json`: + +1. Search the `plugins` array for an entry with `source` matching `./` + skill path +2. If found: verify `version`, `name`, and that `source` path exists +3. If not found: check if the skill's domain bundle (e.g., `product-skills`) would include it via its `source` path + +### 6d. Domain plugin.json + +Check the parent domain's `.claude-plugin/plugin.json`: +- Verify the skill count in the description matches reality +- Verify version matches repo version + +**Auto-fix:** Update stale counts. Fix version mismatches. + +--- + +## Phase 7: Ecosystem Integration + +### 7a. Cross-Platform Sync + +Verify the skill appears in platform indexes: + +```bash +grep -l "{skill_name}" .codex/skills-index.json .gemini/skills-index.json +``` + +If missing from either index: +```bash +python3 scripts/sync-codex-skills.py --verbose +python3 scripts/sync-gemini-skills.py --verbose +``` + +### 7b. Command Integration + +If the skill has associated commands (from settings.json `commands` field or matching name in `commands/`): +- Verify the command `.md` file has valid YAML frontmatter (`name`, `description`) +- Verify the command references the correct skill path +- Verify the command is in `mkdocs.yml` nav + +**Auto-fix:** Add missing mkdocs.yml nav entries. + +### 7c. Agent Integration + +If the skill has embedded agents (`{skill_path}/agents/*.md`): +- Verify each agent has valid YAML frontmatter +- Verify agent references resolve (relative paths to skills) + +Search `agents/` for any cs-* agent that references this skill: +```bash +grep -rl "{skill_name}\|{skill_path}" agents/ +``` + +If found, verify the agent's skill references are correct. + +### 7d. Cross-Skill Dependencies + +Read the SKILL.md for references to other skills (look for `../` paths, skill names in "Related Skills" sections): +- Verify each referenced skill exists +- Verify the referenced skill's SKILL.md exists + +--- + +## Phase 8: Domain-Appropriate Code Review + +Based on the skill's domain, invoke the appropriate agent's review perspective: + +| Domain | Agent | Review Focus | +|--------|-------|-------------| +| `engineering/` or `engineering-team/` | cs-senior-engineer | Architecture, code quality, CI/CD integration | +| `product-team/` | cs-product-manager | PRD quality, user story coverage, RICE alignment | +| `marketing-skill/` | cs-content-creator | Content quality, SEO optimization, brand voice | +| `ra-qm-team/` | cs-quality-regulatory | Compliance checklist, audit trail, regulatory alignment | +| `business-growth/` | cs-growth-strategist | Growth metrics, revenue impact, customer success | +| `finance/` | cs-financial-analyst | Financial model accuracy, metric definitions | +| Other | cs-senior-engineer | General code and architecture review | + +**How to invoke:** Read the agent's `.md` file to understand its review criteria. Apply those criteria to review the skill's SKILL.md, scripts, and references. This is NOT spawning a subagent — it's using the agent's documented perspective to structure your review. + +Review checklist (apply domain-appropriate lens): +- [ ] SKILL.md workflows are actionable and complete +- [ ] Scripts solve the stated problem correctly +- [ ] References contain accurate domain knowledge +- [ ] Templates/assets are production-ready +- [ ] No broken internal links +- [ ] Attribution present where required + +--- + +## Final Report + +Present results as a structured table: + +``` +╔══════════════════════════════════════════════════════════════╗ +║ PLUGIN AUDIT REPORT: {skill_name} ║ +╠══════════════════════════════════════════════════════════════╣ +║ ║ +║ Phase 1 — Discovery ✅ {type}, {domain} ║ +║ Phase 2 — Structure ✅ {score}/100 ({level}) ║ +║ Phase 3 — Quality ✅ {score}/100 ({grade}) ║ +║ Phase 4 — Scripts ✅ {n}/{n} PASS ║ +║ Phase 5 — Security ✅ PASS (0 critical, 0 high) ║ +║ Phase 6 — Marketplace ✅ plugin.json valid ║ +║ Phase 7 — Ecosystem ✅ Codex + Gemini synced ║ +║ Phase 8 — Code Review ✅ {domain} review passed ║ +║ ║ +║ VERDICT: ✅ PASS — Ready for merge/publish ║ +║ ║ +║ Auto-fixes applied: {n} ║ +║ Warnings: {n} ║ +║ Action items: {n} ║ +║ ║ +╚══════════════════════════════════════════════════════════════╝ +``` + +### Verdict Logic + +| Condition | Verdict | +|-----------|---------| +| All phases pass | **PASS** — Ready for merge/publish | +| Only warnings (no blockers) | **PASS WITH WARNINGS** — Review warnings before merge | +| Any phase has a blocker | **FAIL** — List blockers with fix instructions | + +### Blockers (any of these = FAIL) + +- Structure score < 75 +- Quality score < 60 (after noting roadmap) +- Any script FAIL +- Any CRITICAL or HIGH security finding +- plugin.json invalid or has disallowed fields +- Version mismatch with repo + +### Non-Blockers (warnings only) + +- Quality score between 60-75 +- Script PARTIAL results +- Missing from one platform index (auto-fixed) +- Missing mkdocs.yml nav entry (auto-fixed) +- Security INFO findings + +--- + +## Skill References + +| Tool | Path | +|------|------| +| Skill Validator | `engineering/skill-tester/scripts/skill_validator.py` | +| Quality Scorer | `engineering/skill-tester/scripts/quality_scorer.py` | +| Script Tester | `engineering/skill-tester/scripts/script_tester.py` | +| Security Auditor | `engineering/skill-security-auditor/scripts/skill_security_auditor.py` | +| Quality Standards | `standards/quality/quality-standards.md` | +| Security Standards | `standards/security/security-standards.md` | +| Git Standards | `standards/git/git-workflow-standards.md` | diff --git a/mkdocs.yml b/mkdocs.yml index ab3d82332..2fb58214f 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -200,6 +200,7 @@ nav: - "Experiment Designer": skills/product-team/experiment-designer.md - "Landing Page Generator": skills/product-team/landing-page-generator.md - "Product Analytics": skills/product-team/product-analytics.md + - "Code to PRD": skills/product-team/code-to-prd.md - "Product Discovery": skills/product-team/product-discovery.md - "Product Manager Toolkit": skills/product-team/product-manager-toolkit.md - "Product Strategist": skills/product-team/product-strategist.md @@ -352,11 +353,13 @@ nav: - Commands: - Overview: commands/index.md - "/changelog": commands/changelog.md + - "/code-to-prd": commands/code-to-prd.md - "/competitive-matrix": commands/competitive-matrix.md - "/financial-health": commands/financial-health.md - "/okr": commands/okr.md - "/persona": commands/persona.md - "/pipeline": commands/pipeline.md + - "/plugin-audit": commands/plugin-audit.md - "/prd": commands/prd.md - "/project-health": commands/project-health.md - "/retro": commands/retro.md diff --git a/product-team/.claude-plugin/plugin.json b/product-team/.claude-plugin/plugin.json index ead9362f2..b081be890 100644 --- a/product-team/.claude-plugin/plugin.json +++ b/product-team/.claude-plugin/plugin.json @@ -1,6 +1,6 @@ { "name": "product-skills", - "description": "12 production-ready product skills: product manager toolkit (RICE, PRDs), agile product owner, product strategist, UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, product analytics, experiment designer, product discovery, and roadmap communicator. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.", + "description": "14 production-ready product skills: product manager toolkit (RICE, PRDs), agile product owner, product strategist, UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, product analytics, experiment designer, product discovery, roadmap communicator, code-to-prd, and research summarizer. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.", "version": "2.1.2", "author": { "name": "Alireza Rezvani", diff --git a/product-team/CLAUDE.md b/product-team/CLAUDE.md index 472505ad5..ee085243b 100644 --- a/product-team/CLAUDE.md +++ b/product-team/CLAUDE.md @@ -1,6 +1,6 @@ # Product Team Skills - Claude Code Guidance -This guide covers the 12 production-ready product management skills and their Python automation tools. +This guide covers the 14 production-ready product management skills and their Python automation tools. ## Product Skills Overview @@ -17,12 +17,14 @@ This guide covers the 12 production-ready product management skills and their Py 10. **experiment-designer/** - Experiment design and sample size planning (1 tool) 11. **product-discovery/** - Discovery frameworks and assumption mapping (1 tool) 12. **roadmap-communicator/** - Roadmap communication and changelog generation (1 tool) +13. **code-to-prd/** - Reverse-engineer any codebase into PRD (2 tools: codebase_analyzer, prd_scaffolder) +14. **research-summarizer/** - Research synthesis and summarization (1 tool) -**Total Tools:** 13 Python automation tools +**Total Tools:** 16 Python automation tools **Agents:** 5 (cs-product-manager, cs-agile-product-owner, cs-product-strategist, cs-ux-researcher, cs-product-analyst) -**Slash Commands:** 7 (/rice, /okr, /persona, /user-story, /competitive-matrix, /prd, /sprint-plan) +**Slash Commands:** 8 (/rice, /okr, /persona, /user-story, /competitive-matrix, /prd, /sprint-plan, /code-to-prd) ## Python Automation Tools @@ -308,7 +310,7 @@ python roadmap-communicator/scripts/changelog_generator.py --from v1.0.0 --to HE --- -**Last Updated:** March 11, 2026 -**Skills Deployed:** 12/12 product skills production-ready -**Total Tools:** 13 Python automation tools -**Agents:** 5 | **Commands:** 7 +**Last Updated:** March 17, 2026 +**Skills Deployed:** 14/14 product skills production-ready +**Total Tools:** 16 Python automation tools +**Agents:** 5 | **Commands:** 8