CI
aiblueprinthq/ai-blueprint
Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook.
Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment.
Install Michel Monitor Pull Request GitHub Actions
$ npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install PackmindHub/packmind michel-monitor-pull-request-github-actions --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/PackmindHub/packmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/scripts/michel/michel-monitor-pull-request-github-actions .claude/skills/michel-monitor-pull-request-github-actions && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "michel-monitor-pull-request-github-actions" agent skill from https://github.com/PackmindHub/packmind/tree/main/scripts/michel/michel-monitor-pull-request-github-actions into .claude/skills/michel-monitor-pull-request-github-actions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "michel-monitor-pull-request-github-actions", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/PackmindHub/packmind/tree/main/scripts/michel/michel-monitor-pull-request-github-actionsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install PackmindHub/packmind michel-monitor-pull-request-github-actions --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PackmindHub/packmind.git skills-src && mkdir -p .agents/skills && cp -r skills-src/scripts/michel/michel-monitor-pull-request-github-actions .agents/skills/michel-monitor-pull-request-github-actions && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "michel-monitor-pull-request-github-actions" agent skill from https://github.com/PackmindHub/packmind/tree/main/scripts/michel/michel-monitor-pull-request-github-actions into .agents/skills/michel-monitor-pull-request-github-actions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "michel-monitor-pull-request-github-actions", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install PackmindHub/packmind michel-monitor-pull-request-github-actions --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PackmindHub/packmind.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/scripts/michel/michel-monitor-pull-request-github-actions .cursor/skills/michel-monitor-pull-request-github-actions && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "michel-monitor-pull-request-github-actions" agent skill from https://github.com/PackmindHub/packmind/tree/main/scripts/michel/michel-monitor-pull-request-github-actions into .cursor/skills/michel-monitor-pull-request-github-actions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "michel-monitor-pull-request-github-actions", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/PackmindHub/packmind.git --path scripts/michel/michel-monitor-pull-request-github-actions--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install PackmindHub/packmind michel-monitor-pull-request-github-actions --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PackmindHub/packmind.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/scripts/michel/michel-monitor-pull-request-github-actions .gemini/skills/michel-monitor-pull-request-github-actions && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "michel-monitor-pull-request-github-actions" agent skill from https://github.com/PackmindHub/packmind/tree/main/scripts/michel/michel-monitor-pull-request-github-actions into .gemini/skills/michel-monitor-pull-request-github-actions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "michel-monitor-pull-request-github-actions", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install PackmindHub/packmind michel-monitor-pull-request-github-actionsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/PackmindHub/packmind.git skills-src && mkdir -p .github/skills && cp -r skills-src/scripts/michel/michel-monitor-pull-request-github-actions .github/skills/michel-monitor-pull-request-github-actions && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "michel-monitor-pull-request-github-actions" agent skill from https://github.com/PackmindHub/packmind/tree/main/scripts/michel/michel-monitor-pull-request-github-actions into .github/skills/michel-monitor-pull-request-github-actions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "michel-monitor-pull-request-github-actions", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install PackmindHub/packmind michel-monitor-pull-request-github-actions --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/PackmindHub/packmind.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/scripts/michel/michel-monitor-pull-request-github-actions .opencode/skills/michel-monitor-pull-request-github-actions && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "michel-monitor-pull-request-github-actions" agent skill from https://github.com/PackmindHub/packmind/tree/main/scripts/michel/michel-monitor-pull-request-github-actions into .opencode/skills/michel-monitor-pull-request-github-actions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "michel-monitor-pull-request-github-actions", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
michel-monitor-pull-request-github-actions- GitHub stars
- 318
- Token cost
- ~2.6k tokens
- SKILL.md length
- 875 words
- Files
- 1
- Skills in repo
- 35
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment.
- Works in 5 steps: Classify — any_failure vs stuck → Diagnose a failure → Apply a fix and push → …
- With anyfailure
- SKILL.md covers Decision flow, 1. Classify — any_failure vs…, 2. Diagnose a failure and 3. Apply a fix and push, plus 2 more sections
- Calls gh, git and nx
What it does
Michel Monitor Pull Request GitHub Actions is an agent skill from PackmindHub/packmind. Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment. Invoke whenever Michel's CI monitor loop triggers with anyfailure, stuck, or nottriggered — the bash loop already handles pending and allgreen silently, so this skill never sees those states.
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering CI/CD and Pull requests. It works with GitHub Actions, Bash and GitHub. The repository describes itself as: Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance. The licence is Apache-2.0.
When your agent uses it
- With anyfailure
- Nottriggered — the bash loop already handles pending and allgreen silently
- So this skill never sees those states
Example prompts
- “/michel-monitor-pull-request-github-actions”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 67de8a2. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
ghgitnxjq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh and git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Michel Monitor Pull Request GitHub Actions loads about 2.6k tokens when it runs. Until then it costs about 103 tokens; SKILL.md has 875 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from PackmindHub/packmind at commit 67de8a2, republished under its Apache-2.0 licence (© PackmindHub). 875 words, ~2,620 tokens.
Download SKILL.mdSave it as
.claude/skills/michel-monitor-pull-request-github-actions/SKILL.md (or your agent's skills folder).- name
- michel-monitor-pull-request-github-actions
- description
- Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment. Invoke whenever Michel's CI monitor loop triggers with `any_failure`, `stuck`, or `not_triggered` — the bash loop already handles `pending` and `all_green` silently, so this skill never sees those states.
Monitor a pull request's GitHub Actions CI
Called during one iteration of the CI monitor loop. The harness prompt already contains everything needed to start:
{{CHECKS_JSON}}— snapshot of all check statuses at loop entry{{REASON}}—any_failure,stuck, ornot_triggered{{PR_NUMBER}},{{BRANCH}},{{WORKDIR}},{{ITER}},{{MAX_ITER}}
Decision flow
Read CHECKS_JSON in prompt
→ if REASON == "stuck": document timeout in running comment → done
→ if REASON == "not_triggered": investigate why CI never started, document → done
→ if REASON == "any_failure":
1. Identify failing run(s) via gh run list
2. Fetch failed logs with gh run view --log-failed
3. Match pattern → apply fix locally
4. Commit + push
5. Create or update running comment
(if unfixable: document reason → done, no push)1. Classify — any_failure vs stuck
The bash outer loop has already classified the state; you are invoked only in these two cases:
{{REASON}} | Meaning | Action |
|---|---|---|
any_failure | At least one completed check has conclusion ∈ {failure, timed_out, cancelled, action_required} | Diagnose and fix (sections 2–3) |
stuck | A workflow started but has been in-progress for >20 min | Document timeout in running comment (section 5) — no code changes |
not_triggered | Zero checks ever registered for the whole monitoring window — CI never started | Investigate why (section 5) and document — no code changes |
conclusion values to recognise: success / failure / timed_out / cancelled / action_required / neutral / skipped / stale / null.
A completed check with conclusion = null counts as failure.
gh CLI contract — re-fetch with gh run list, NOT gh pr checks
Do not use gh pr checks here. It resolves the commit's statusCheckRollup
over GraphQL, and the worker's fine-grained PAT has no permission that can read
the Checks API (check-runs). It always partial-fails with Resource not accessible by personal access token (…statusCheckRollup.contexts.nodes.N),
returns an empty body, and makes a healthy PR look like zero checks — the bug that
produced false not_triggered loops. There is no fine-grained permission that
fixes this; only a classic PAT (repo scope) or a GitHub App can read check-runs.
Re-fetch CI state with gh run list instead — it hits GET /actions/runs
(Actions:read, which the token has) and reports each workflow run's status and
conclusion directly, no GraphQL:
gh run list --branch <BRANCH> --repo <OWNER/REPO> \
--json databaseId,status,conclusion,workflowName,startedAt,headSha --limit 50Classify only the runs whose .headSha equals the PR head commit
(gh pr view <PR_NUMBER> --repo <OWNER/REPO> --json headRefOid --jq .headRefOid);
runs on the branch with a different SHA are stale from earlier pushes.
| run state | meaning |
|---|---|
status != "completed" | pending |
completed + conclusion ∈ {success, neutral, skipped} | pass |
completed + conclusion ∈ {failure, timed_out, cancelled, action_required, startup_failure, null} | fail |
2. Diagnose a failure
Step 1 — Start from the snapshot
Read {{CHECKS_JSON}} in the prompt first — it is the snapshot of the head commit's runs (name, status, conclusion, bucket) at loop entry. Only re-fetch if you need data fresher than the snapshot, and use gh run list to do it (see the gh CLI contract above) — never gh pr checks, which the fine-grained PAT cannot read.
Step 2 — Find the failing run
gh run list --branch <BRANCH> --repo <OWNER/REPO> \
--json databaseId,name,status,conclusion,workflowName,url \
--limit 10 | jq '.[] | select(.conclusion == "failure")'Step 3 — Read failed step logs
gh run view <RUN_ID> --repo <OWNER/REPO> --log-failed--log-failed returns only the failing steps' output — much smaller than full logs.
Step 4 — Get job/step names if needed
gh run view <RUN_ID> --repo <OWNER/REPO> --json jobsStep 5 — Match the root cause
| Log pattern | Likely cause | Fix |
|---|---|---|
| ESLint / Lint errors | Code violates ESLint rules | Fix the lint errors in the affected files |
| Jest / test failure | Assertion failed or file error | Fix the test or the production code it covers |
| TypeScript / tsc error | Type mismatch, bad import | Fix the type error in the source |
| Build error (nx build) | Missing dep, bad import path | Fix import or tsconfig |
| Missing secret / env var | Required CI env not set | Document as unfixable — you cannot add CI secrets |
| Repeated identical failure | Same error as prior iteration | Document as unfixable — cycling wastes iterations |
Detecting a repeated failure: fetch the running comment body, scan for the previous iteration's **Failure:** and **Cause:** lines, and compare their error signature to the current run's log output. If the signatures match, declare unfixable rather than pushing another identical attempt.
Show full SKILL.md (307 more words)Show less
3. Apply a fix and push
Edit and commit
git -C <WORKDIR> add <changed-files>
git -C <WORKDIR> commit -m "🐛 fix(ci): <short description>"Validate the projects you touched with targeted nx test <project> / nx lint <project> before pushing, then let CI confirm — CI re-runs the full nx affected gate on the PR as the authoritative check (that is what you are monitoring).
Push
git push -u origin <BRANCH> --force-with-lease --no-verify--force-with-lease only overwrites the remote tip if it matches the last-known ref, so it is safe for force-push. Push with --no-verify: the full gate already ran in the validation phase before the first push and CI re-runs it as the authoritative check, so re-running the local pre-push hook here only duplicates CI's work (and a non-zero exit risks losing the run).
4. Single running PR comment
There is exactly one running comment per PR, identified by <!-- michel-ci-monitor -->. Posting a second comment fragments the history and makes the PR timeline hard to follow — always find the existing one and patch it in place.
Look up the comment ID
gh api --paginate "repos/<OWNER>/<REPO>/issues/<PR_NUMBER>/comments" \
--jq '[.[] | select(.body | contains("<!-- michel-ci-monitor -->"))] | first | .id'--paginate ensures the comment is found even if the PR has more than 30 comments.
Create the comment (first failure, no comment exists yet)
gh pr comment <PR_NUMBER> --repo <OWNER>/<REPO> --body "$(cat <<'BODY'
<!-- michel-ci-monitor -->
## Michel — CI Monitor
### Iteration 1
**Failure:** <workflow / job / step>
**Cause:** <1-2 sentences>
**Fix applied:** <what was changed and why>
**Commit:** <git sha>
BODY
)"Update the comment (subsequent iterations)
Write the new body to a tempfile to avoid shell-quoting issues with $, backticks, or multi-line content:
COMMENT_ID=$(gh api --paginate "repos/<OWNER>/<REPO>/issues/<PR_NUMBER>/comments" \
--jq '[.[] | select(.body | contains("<!-- michel-ci-monitor -->"))] | first | .id')
EXISTING=$(gh api "repos/<OWNER>/<REPO>/issues/comments/${COMMENT_ID}" --jq '.body')
cat > /tmp/comment-body.md <<BODY
${EXISTING}
### Iteration <N>
**Failure:** <details>
**Cause:** <details>
**Fix applied:** <details or 'Unfixable — see below'>
BODY
gh api -X PATCH "repos/<OWNER>/<REPO>/issues/comments/${COMMENT_ID}" \
-F body=@/tmp/comment-body.mdComment body structure — cumulative, one ### Iteration N heading per invocation:
- What workflow / job / step failed
- Root cause (from the logs)
- Fix applied — or "Unfixable" with reason
- Git commit SHA if a fix was pushed
5. Terminal states — unfixable or timeout
When you cannot fix the problem or the workflow is stuck, update the running comment and return without committing anything.
Unfixable:
### Iteration <N> — Unfixable
**Failure:** <details>
**Reason not fixable:** <missing CI secret | repeated identical failure | infra issue | error outside codebase>
**Recommendation:** Manual intervention required.Timeout (stuck):
### Timeout reached
Workflow **<name>** has been running for >20 minutes — likely a CI infrastructure issue, not a code problem.
No fix was attempted. Manual re-run or intervention may be needed.CI did not trigger (not_triggered):
First confirm with gh run list --branch <BRANCH> --repo <OWNER/REPO> whether any
run exists. Zero runs ⇒ the workflow never started — most often no self-hosted
runner was available, a branch/path filter excluded the PR, or the run needs
approval.
### CI did not trigger
No checks registered for this PR within the monitoring window. CI did not start
— likely no self-hosted runner available, a branch/path filter, or a required run
approval. No fix was attempted. Verify runner availability / workflow triggers,
then re-run.© PackmindHub, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in scripts/michel/michel-monitor-pull-request-github-actions of PackmindHub/packmind.
Open the folder on GitHubat commit 67de8a2
Compare with similar skills
Michel Monitor Pull Request GitHub Actions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Michel Monitor Pull Request GitHub Actions this skillPackmindHub/packmind | 318 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| CIaiblueprinthq/ai-blueprint | 463 | — | ~2.2k | Automated safety check: Pass | MIT | |
| CIopenJiuwen-ai/sciencediscovery | 159 | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | |
| Diy Netlifyswyxio/skills | 176 | — | ~1.1k | Automated safety check: Pass | MIT | |
| ONNX Runtime CI Managementmicrosoft/onnxruntime | 22k | — | ~4.1k | Automated safety check: Pass | MIT | |
| Renovate Actions PR Reviewbacknotprop/plannotator | 9.3k | — | ~640 | Automated safety check: Pass | Apache-2.0 |
Similar skills
CI
openJiuwen-ai/sciencediscovery
Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag.
Diy Netlify
swyxio/skills
Build or audit an isolated Netlify/Vercel-style pull-request preview workflow using GitHub Actions and the project's existing hosting provider.
- Official
ONNX Runtime CI Management
microsoft/onnxruntime
Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change.
Renovate Actions PR Review
backnotprop/plannotator
Reviews Renovate pull requests that bump GitHub Actions by checking pinned SHAs against upstream tags, scanning changelogs and confirming workflows stay compatible.
GitHub Actions Workflow Automation
ruvnet/agentic-flow
Generates and optimizes GitHub Actions workflows with swarm coordination, using named modes for PR management, issue tracking, releases and repository structure.
More from PackmindHub/packmind
All 35 skills in this repoMichel CLI Demo Recorder
PackmindHub/packmind
Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR.
Michel UI Demo Recorder
PackmindHub/packmind
Record polished UI demo videos and screenshots of a running web app using Playwright MCP — for client deliverables, release notes, feature walkthroughs, or bug repros.
Packmind Create Skill
PackmindHub/packmind
Guide for creating effective skills. An agent skill from PackmindHub/packmind.
Doc Audit
PackmindHub/packmind
Audit Packmind end-user documentation (apps/doc/) for broken links, outdated CLI references, non-existent concepts, misleading information, and missing coverage.
Feature Sprint
PackmindHub/packmind
Execute the implementation plan produced by /feature-spec. An agent skill from PackmindHub/packmind.
Michel Packmind Engineer Review
PackmindHub/packmind
Review an implemented GitHub issue the way a senior Packmind engineer would — the human-judgment checks that ESLint, the TypeScript compiler, and e2e tests cannot catch (authorization scoping…
Related
Works with
Categories
Questions about Michel Monitor Pull Request GitHub Actions
What does Michel Monitor Pull Request GitHub Actions do?
Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment. Michel Monitor Pull Request GitHub Actions is an agent skill from PackmindHub/packmind. Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment.
When should I use Michel Monitor Pull Request GitHub Actions?
Michel Monitor Pull Request GitHub Actions fits situations like: with anyfailure; nottriggered — the bash loop already handles pending and allgreen silently; so this skill never sees those states.
How do I install Michel Monitor Pull Request GitHub Actions in Claude Code?
Run `npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a claude-code`. Or copy the skill folder (scripts/michel/michel-monitor-pull-request-github-actions in PackmindHub/packmind) into .claude/skills/michel-monitor-pull-request-github-actions in your project. Claude Code loads it when a task matches its description.
How do I install Michel Monitor Pull Request GitHub Actions in Codex?
Run `npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a codex`. Or copy the skill folder (scripts/michel/michel-monitor-pull-request-github-actions in PackmindHub/packmind) into .agents/skills/michel-monitor-pull-request-github-actions in your project. Codex loads it when a task matches its description.
Can I use Michel Monitor Pull Request GitHub Actions in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add PackmindHub/packmind --skill michel-monitor-pull-request-github-actions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/michel-monitor-pull-request-github-actions, .gemini/skills/michel-monitor-pull-request-github-actions, .github/skills/michel-monitor-pull-request-github-actions and .opencode/skills/michel-monitor-pull-request-github-actions in your project.
What does Michel Monitor Pull Request GitHub Actions need to run?
Going by SKILL.md and its folder, Michel Monitor Pull Request GitHub Actions needs the command-line tools its instructions call (gh, git, nx and jq).
Does Michel Monitor Pull Request GitHub Actions access the network?
SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Michel Monitor Pull Request GitHub Actions safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Michel Monitor Pull Request GitHub Actions use?
Michel Monitor Pull Request GitHub Actions is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Michel Monitor Pull Request GitHub Actions use?
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Michel Monitor Pull Request GitHub Actions?
Skills that share tags, products or a category with Michel Monitor Pull Request GitHub Actions: CI (aiblueprinthq/ai-blueprint, 463 stars), CI (openJiuwen-ai/sciencediscovery, 159 stars), Diy Netlify (swyxio/skills, 176 stars) and ONNX Runtime CI Management (microsoft/onnxruntime, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Michel Monitor Pull Request GitHub Actions?
PackmindHub (a GitHub organization) maintains it in PackmindHub/packmind, which has 318 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 9, 2026.
Source: PackmindHub/packmind on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.