agentleFS
Sign inStart free
HeyEddi-comHeyEddi-com/heyeddi-skills/skills/heyeddi-ci-guide/SKILL.md

heyeddi-ci-guide

Skill0 starsChanged 3 months agoMITView on GitHub

Reference for HeyEddi CI commands, authorize-merge auth, feedback via debate + support@, and Spot runners (GHA overflow + sealed pipeline). Use when asking how to work with HeyEddi CI.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Always: run @heyeddi-ci-fails first — fetch failing Checks, diagnose, fix actionable failures, commit + push

    line 29
  2. Very specific:

    Always: run @heyeddi-pr-respond — fix all review items, commit + push, post every reply in-thread

    line 30
  3. Distinctive:

    Never: ask "do you want me to fix?" or "should I comment on threads?" — that is always the default

    line 31
  4. Distinctive:

    Only merge requires authorize merge in the current turn

    line 33
  5. Very specific:

    Prefer GHA + workspace Runners mode (overflow / always) with runs-on: ${{ vars.HEYEDDI_RUNS_ON || 'ubuntu-latest' }}

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 Guide

Short reference for agents and humans working with HeyEddi CI. Depth lives in reference/commands.md.

Skills in this pack

SkillJob
@heyeddi-ci-configAuthor eddi-ci.yaml from the live policy contract
@heyeddi-pr-respondAddress all PR review feedback (human + HeyEddi CI)
@heyeddi-ci-failsDiagnose and fix failing Checks (default on PR work; /heyeddi fails for App path)
@heyeddi-ci-runnersSpot: GHA overflow/always + sealed pipeline: (evidence before claims)
@heyeddi-ci-guideThis skill

Human PR review stays on @heyeddi-pr-review / @heyeddi-pr-respond.

Default PR workflow

On any PR work (open PR, PR branch, review request):

  1. Always run @heyeddi-ci-fails first — fetch failing Checks, diagnose, fix actionable failures, commit + push
  2. Always run @heyeddi-pr-respond — fix all review items, commit + push, post every reply in-thread
  3. Never ask "do you want me to fix?" or "should I comment on threads?" — that is always the default
  4. Never skip CI because the user did not mention it
  5. Only merge requires authorize merge in the current turn

Commands (PR comments)

See reference/commands.md. Common:

  • /heyeddi review / again / check / deep — review passes
  • /heyeddi ci / /heyeddi fails — failed Checks analysis (billable path)
  • /heyeddi ask … / /heyeddi debate … — Q&A on findings
  • Reply on an inline HeyEddi finding — debate when parent looks like HeyEddi

Auth matrix

ActionAllowed when
Commit + push (PR workflow)Automatic during @heyeddi-ci-fails / @heyeddi-pr-respond — do not ask
Merge (gh pr merge)User says authorize merge in the current turn
auto_merge in YAMLNever (schema rejects / forbidden)
Billable knobs (on_ci_failure, sealed runners)Explicit opt-in

Feedback (real paths only)

There is no structured FP/telemetry API yet.

  1. Disagree on a finding: /heyeddi ask / debate on that thread
  2. Product or skill feedback: support@heyeddi.com (skills may draft a mail body)

Runners status

Spot is shipped:

  • Prefer GHA + workspace Runners mode (overflow / always) with runs-on: ${{ vars.HEYEDDI_RUNS_ON || 'ubuntu-latest' }}
  • Sealed pipeline: jobs post HeyEddi Runner: {job_id} Checks for entitled workspaces
  • Claim a job ran only with Check/Spot evidence — see @heyeddi-ci-runners

Install

npx skills add HeyEddi-com/heyeddi-skills -a cursor -y --skill '*'
# or CI skills by name / Marketplace plugin heyeddi-ci-skills
# or Team Marketplace plugin heyeddi-ci-skills

Tools

None (tools: []). This skill is documentation only.

Notes

  • Living knobs: always @heyeddi-ci-config → load_policy_contract
  • Ephemeral .heyeddi/docs/pr-* scratch: never commit

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.

Check your setup, free