Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .github/skills/agentic-workflows/SKILL.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,6 +12,7 @@ This skill is a dispatcher: identify the task type, load the matching `.github/a
Read only the files you need:
Load these files from `github/gh-aw` (they are not available locally).
- `.github/aw/agentic-chat.md`
- `.github/aw/agentic-workflows-mcp.md`
- `.github/aw/asciicharts.md`
Comment on lines 14 to 16
- `.github/aw/campaign.md`
- `.github/aw/charts-trending.md`
Expand Down

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

16 changes: 10 additions & 6 deletions .github/workflows/daily-agent-of-the-day-blog-writer.md
Original file line number Diff line number Diff line change
Expand Up @@ -98,19 +98,21 @@ Use UTC date and set target file:

### 2) Collect live workflow evidence

Use `agentic-workflows` MCP tools:
Use `agenticworkflows` CLI commands (run each as a **simple shell command with no pipes or redirects**):

1. `list` to identify active workflows.
2. `logs` for recent runs (last 3 days, up to 5 runs) of top candidates.
3. `audit` for structured evidence when available.
1. `agenticworkflows status` to identify active workflows.
2. `agenticworkflows logs <workflow-name> --start-date -3d --limit 5` for recent runs of top candidates.
3. `agenticworkflows audit <run-id>` for structured evidence when available.
Comment on lines +103 to +105

**Important**: If any command is not working, run `agenticworkflows --help` as a standalone command (no pipes) to check available subcommands and flags. Do not combine commands with `|`, `&&`, `2>&1`, or other shell operators.

From evidence, extract:

- Workflow behavior observed in real runs.
- Real links to created/updated issues and PRs.
- Any chart/image links or artifact links.

If no useful data appears for the selected workflow, pick another active workflow.
If no useful data appears for the selected workflow, pick another active workflow. If evidence collection commands keep failing (e.g., tool not found or permission error), call `noop` immediately with a brief explanation — **do not delegate evidence collection to a general-purpose sub-agent**.

### 3) Gather optional chart image

Expand Down Expand Up @@ -163,6 +165,8 @@ Body requirements:

### 6) Open PR

**You (the main agent) must call `create_pull_request` directly** — sub-agents cannot call safe-output tools. Do not delegate this step to a general-purpose sub-agent.

Create a PR with title:

- `Agent of the Day – YYYY-MM-DD`
Expand All @@ -175,7 +179,7 @@ PR body must include:

### 7) No-action rule

If no trustworthy live evidence can be gathered after checking multiple workflows, call `noop` with a short explanation.
If no trustworthy live evidence can be gathered after checking multiple workflows, or if the `agenticworkflows` CLI commands fail, call `noop` with a short explanation. **Do not end the session without calling at least one safe-output tool** (`create_pull_request` or `noop`).

## Quality Bar

Expand Down
2 changes: 1 addition & 1 deletion actions/setup/md/mcp_cli_tools_prompt.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
<mcp-clis>
CLI servers are available on `PATH`:
__GH_AW_MCP_CLI_SERVERS_LIST__
Use `<server> --help` for tool names, parameters, and examples before calling any command.
Invoke as a simple shell command: `<server> <tool> [--flag value ...]`. Do **NOT** add pipes, redirects, or shell operators (`|`, `&&`, `2>&1`, etc.) — run `<server> --help` or `<server> <tool> --help` as a standalone command (no pipes) to discover available tools and parameters.
</mcp-clis>