agentleFS
HeyEddi-comHeyEddi-com/heyeddi-skills/skills/heyeddi-ci-fails/SKILL.md

heyeddi-ci-fails

Skill0 starsChanged 3 months agoMITView on GitHub

Diagnose and fix failing GitHub Checks on PR work by default: fetch evidence, write ephemeral ci-fails report, apply fixes, verify locally. Run automatically — do not wait for user to ask. Never merge without authorize merge. Companion to /heyeddi fails.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Run this skill automatically on any PR work — open PR, PR branch, review request, or before @heyeddi-pr-respond.

    line 16
  2. Distinctive:

    Always: commit + push fixes as part of the PR workflow

    line 20
  3. Distinctive:

    Only merge still requires authorize merge in the current turn

    line 21
  4. Distinctive:

    Never commit these. GitHub Checks remain SSOT.

    line 30
  5. Distinctive:

    Never invent failure causes without citing check evidence

    line 48
  6. Distinctive:

    Never merge without authorize merge

    line 49
  7. Distinctive:

    Never claim Spot/GHA jobs ran without Check or Spot evidence

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

HeyEddi CI Fails

Local agent counterpart to App /heyeddi fails: fetch failing Checks, write a diagnosis report, fix actionable failures, verify with evidenced commands. Stack-agnostic (log-driven).

Default behavior (no confirmation)

Run this skill automatically on any PR work — open PR, PR branch, review request, or before @heyeddi-pr-respond. Do not wait for the user to mention CI or ask you to fix failures.

  • Always fetch and diagnose failing Checks
  • Always apply fixes when the diagnosis identifies actionable failures
  • Always commit + push fixes as part of the PR workflow
  • Only merge still requires authorize merge in the current turn

Ephemeral artifacts (do not commit)

FileRole
pr-<N>-ci-fails-raw.jsonRaw gh evidence
pr-<N>-ci-fails.mdDiagnosis report

Never commit these. GitHub Checks remain SSOT.

Pipeline

fetch_failing_checks --pr <N>
write_ci_fails_report --pr <N> --force
→ fill likely cause / proposed fix from logs
apply fixes when diagnosis identifies actionable failures (default — do not ask)
discover_and_verify [--run]
assert_no_merge --check
→ commit + push to PR branch when fixes applied

Also tell the user they can comment /heyeddi fails on the PR for hosted App analysis (billable when that path applies).

Hard rules

  • Never invent failure causes without citing check evidence
  • Never merge without authorize merge
  • Never claim Spot/GHA jobs ran without Check or Spot evidence

Tools

ToolPurpose
fetch_failing_checksRead-only failing Checks rollup
write_ci_fails_reportWrite pr-<N>-ci-fails.md
discover_and_verifyEvidenced verify after fixes
assert_no_mergeMerge hard gate

When complete

python .agents/skills/heyeddi/scripts/suggest_next_skill.py \
  --current-skill heyeddi-ci-fails --project-root .

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.