Sync new Anthropic skills: academy-guide, discernment-nudge

[davila7]

Summary

Automated sync from anthropics/skills via the scheduled skills-migration routine.

• Compared every skill in the upstream repo against cli-tool/components/skills/ (including duplicate-named local copies) before making any changes.
• Added the two skills that don't exist locally yet, copied verbatim (Apache 2.0):
  • productivity/academy-guide — recommends matching Claude Academy courses/tutorials/use cases
  • productivity/discernment-nudge — prompts users to verify facts/reasoning/assumptions after substantive answers
• Left everything else untouched. Several skills that share a name with upstream (docx, pptx, xlsx, claude-api, frontend-design, skill-creator, artifacts-builder, mcp-builder, etc.) already have local content that is newer than or diverged from upstream — overwriting those would have discarded local customizations, so they were skipped per the "never overwrite locally customized skills" rule.
• Updated cli-tool/components/skills/ANTHROPIC_ATTRIBUTION.md with the two new entries.
• Regenerated the component catalog (python scripts/generate_components_json.py), which updated docs/components.json and the split dashboard/public/ artifacts.

Validation

Both new skills were reviewed with the component-reviewer agent: no critical issues or warnings — valid frontmatter, kebab-case naming, no hardcoded secrets/absolute paths, correct productivity/ category placement (consistent with other meta/behavioral skills already there).

Test plan

• component-reviewer validation on both new skills (passed, no issues)
• python scripts/generate_components_json.py runs clean and includes both new skills in docs/components.json
• Manual smoke test of --skill academy-guide / --skill discernment-nudge installation (not run in this automated session)

---

Generated by Claude Code

---

Summary by cubic

Adds upstream skills academy-guide and discernment-nudge to expand onboarding and post-answer verification guidance. Previously these skills were unavailable; they are now installable via the CLI and visible on the website after regenerating the component catalog.

• Areas affected: components (cli-tool/components/skills/) and website (docs/, dashboard/public/).
• New components: skills/productivity/academy-guide, skills/productivity/discernment-nudge; updated ANTHROPIC_ATTRIBUTION.md.
• Catalog regenerated (docs/components.json and dashboard indexes); counts updated; includes a new MCP catalog entry web-data/dimhour.
• No changes to existing customized skills; no new environment variables or secrets; no migration required.

^{Written for commit c9b996a. Summary will update on new commits.}

[github-actions]

👋 Thanks for contributing, @davila7!

This PR touches cli-tool/components/** and has been marked review-pending.

What happens next

1. 🤖 Automated security audit runs and posts results on this PR.
2. 👀 Maintainer review — a human reviewer validates the component with the component-reviewer agent (format, naming, security, clarity).
3. ✅ Merge — once approved, your PR is merged to main.
4. 📦 Catalog regeneration — the component catalog is rebuilt automatically.
5. 🚀 Live on aitmpl.com — your component appears on the website after deploy.

While you wait

• Check the Security Audit comment below for any issues to fix.
• Make sure your component follows the contribution guide.

This is an automated message. No action is required from you right now — a maintainer will review soon.

[github-actions]

🎉 SkillSpector Security Scan

Static analysis (--no-llm) by SkillSpector (NVIDIA, Apache-2.0).

Status: ✅ PASSED

Metric	Count
Skills scanned	2
🔴 HIGH/CRITICAL (score > 50)	0
🟡 MEDIUM	0
🟢 LOW / clean	2

No HIGH/CRITICAL findings. ✅

---

Generated by SkillSpector. Score bands: 0-20 LOW, 21-50 MEDIUM, 51-80 HIGH, 81-100 CRITICAL.

[github-actions]

⚠️ Security Audit Report

Status: ❌ FAILED

Metric	Count
Total Components	770
✅ Passed	359
❌ Failed	411
⚠️ Warnings	978

❌ Failed Components (Top 5)

Component	Errors	Warnings	Score
vercel-edge-function	3	4	81/100
prompt-engineer	2	0	90/100
neon-expert	2	2	88/100
agent-overview	2	1	89/100
unused-code-cleaner	2	1	89/100

...and 406 more failed component(s)

---

📊 View Full Report for detailed error messages and all components

[greptile-apps]

Greptile Summary

The PR adds the upstream academy-guide and discernment-nudge productivity skills, including their Apache 2.0 licenses and attribution. It also regenerates the documentation and dashboard catalogs so the skills are discoverable and installable.

• Adds two directory-shaped skills with valid metadata and companion license files.
• Adds corresponding dashboard content records and catalog/search metadata.
• Refreshes component counts and incorporates the previously committed Dimhour MCP source into generated artifacts.

Confidence Score: 5/5

The PR appears safe to merge, with the new skills and their generated catalog representations aligned.

The installer supports directory-shaped skills and recursively includes companion license files, while the regenerated catalog provides matching source, metadata, search, count, and content representations; no concrete blocking or non-blocking defect remains.

Important Files Changed

Filename	Overview
cli-tool/components/skills/productivity/academy-guide/SKILL.md	Adds a self-contained skill for matching Claude-learning questions to verified Academy resources.
cli-tool/components/skills/productivity/discernment-nudge/SKILL.md	Adds bounded guidance for appending targeted verification questions after substantive answers.
docs/components.json	Regenerates the canonical component catalog with both skills and the previously committed Dimhour MCP.
dashboard/public/components/skills.json	Regenerates the dashboard skill listing to expose the two new productivity skills.
dashboard/public/search-index.json	Refreshes searchable component metadata for the regenerated catalog.

_{Reviews (1): Last reviewed commit: "feat(skills): sync academy-guide and dis..." | Re-trigger Greptile}

[cubic-dev-ai]

No issues found across 18 files

Not reviewed (too large): docs/components.json (~3,632 lines), dashboard/public/components.json (~2 lines), dashboard/public/components/agents.json (~2 lines), dashboard/public/components/commands.json (~2 lines), dashboard/public/components/skills.json (~2 lines), dashboard/public/search-index.json (~2 lines) - if these are generated or fixture files, add them to ignored paths to exclude them from future reviews.

_{Re-trigger cubic}

[github-actions]

⚠️ Security Audit Report

Status: ❌ FAILED

Metric	Count
Total Components	770
✅ Passed	359
❌ Failed	411
⚠️ Warnings	979

❌ Failed Components (Top 5)

Component	Errors	Warnings	Score
vercel-edge-function	3	4	81/100
prompt-engineer	2	0	90/100
neon-expert	2	2	88/100
agent-overview	2	1	89/100
unused-code-cleaner	2	1	89/100

...and 406 more failed component(s)

---

📊 View Full Report for detailed error messages and all components