github
Skill340 starsChanged 7 months agoMITView on GitHub
GitHub CLI operations via `gh` for issues, PRs, Actions, releases, and REST/GraphQL API with `--json`/`--jq` parsing. Triggers on: "create an issue", "submit a PR", "check CI status", "why did CI fail", "merge a PR", or pasted GitHub URLs.
- Installs packages
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 143 edited versions we read keep these.
1
Distinctive
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
- Very specific: line 13
All GitHub operations use the gh CLI.
- Distinctive: line 46
Add missing scopes without re-authenticating from scratch:
- Very specific: line 106
Prefer higher-level commands over raw API: Use gh issue create instead of gh api repos/.../issues -X POST.
- Very specific: line 107
Use
--repoconsistently when outside a git directory: Never rely on implicit repo detection in scripts or CI environments.
“Common” is measured: kept by at least 6 in 10 of the 143 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
GitHub
All GitHub operations use the gh CLI. Prefer --json with --jq for structured,
parseable output. Use --repo owner/repo when not inside a git repository with a
configured remote. Use --web to open any resource in the browser.
Prerequisites and Auth
Installation
| Platform | Command |
| macOS | brew install gh |
| Debian/Ubuntu | sudo apt install gh |
| Windows | winget install GitHub.cli |
Authentication
gh auth login # interactive OAuth login
gh auth status # check current auth and active accountRequired OAuth Scopes
| Scope | Grants Access To |
repo | Private repos, issues, PRs, commits, status |
read:org | Org membership, team listing |
workflow | Trigger and manage GitHub Actions workflows |
gist | Create and manage gists |
delete_repo | Delete repositories (not granted by default) |
admin:org | Manage org settings, teams, members |
project | Read/write access to ProjectV2 boards |
Add missing scopes without re-authenticating from scratch:
gh auth refresh --scopes repo,read:org,workflowReference Routing
| User intent | Load |
| Create/list/view/edit/close issues, add comments | references/issues.md |
| Create/list/view/review/merge/edit/close pull requests | references/pull-requests.md |
| List runs, view logs, trigger/rerun/watch workflows, artifacts | references/ci-actions.md |
| Create/fork/clone/view/edit/archive/delete repositories | references/repos.md |
| Create/list/view/edit/upload/delete releases | references/releases.md |
| Search repos, issues, PRs, code, commits | references/search.md |
Raw REST/GraphQL via gh api, pagination, rate limit | references/api.md |
| GraphQL cost model, bulk queries, mutations, rate limits | references/graphql-queries.md |
| Multi-step workflow recipes (PR lifecycle, CI triage, releases) | references/automation-workflows.md |
| Create/list/view/edit/delete gists | references/gists.md |
| List orgs, teams, members | references/orgs.md |
Workflow Pattern
- Identify user intent from the routing table above.
- Load the matching
references/<file>.mdfor command syntax and examples. - Execute the
ghcommand with--repo owner/repoand--json/--jqas needed. - On error, consult the Error Handling table below.
Error Handling
| Error | Cause | Resolution |
| HTTP 401 Unauthorized | Token expired or revoked | Run gh auth login to re-authenticate |
| HTTP 403 Forbidden | Insufficient permissions or rate limited | Check gh auth status for scopes; check gh api rate_limit |
| HTTP 404 Not Found | Repo does not exist, is private without repo scope, or resource deleted | Verify repo name; run gh auth refresh --scopes repo |
| HTTP 422 Unprocessable Entity | Invalid payload — missing required field, validation error | Check request body fields match API schema |
| HTTP 429 Too Many Requests | REST rate limit exceeded (5000 req/hr authenticated) | Wait for X-RateLimit-Reset timestamp; reduce request frequency |
| GraphQL rate limit exceeded | Used more than 5000 points/hr | Reduce query complexity or wait; see references/graphql-queries.md |
| "no git remotes found" | Running gh outside a git repo without --repo | Add --repo owner/repo to the command |
| Insufficient OAuth scopes | Token lacks required scope for the operation | Run gh auth refresh --scopes scope1,scope2 |
| Duplicate issue/PR title | Not a real error — GitHub allows duplicates, but check before creating | Search with gh issue list or gh pr list first |
| Archived repo blocks writes | Repo is archived; all write operations fail | Unarchive with gh repo edit owner/repo --archived=false or use a different repo |
Enable debug logging to see raw HTTP requests and responses:
GH_DEBUG=api gh pr list --repo owner/repoCalibration Rules
- Prefer
--jsonover parsing text output. Text output formats are unstable acrossghversions. Always use--json field1,field2to get machine-readable output. - Use
--jqto minimize output before processing. Filter at the source rather than piping large JSON blobs to external tools.--jqruns server-side and reduces data transferred. - Prefer higher-level commands over raw API. Use
gh issue createinstead ofgh api repos/.../issues -X POST. High-level commands handle auth, pagination, and error formatting automatically. - Use
--repoconsistently when outside a git directory. Never rely on implicit repo detection in scripts or CI environments. Always pass--repo owner/repoexplicitly. - Use GraphQL only for nested or bulk data. For single-resource fetches and mutations with simple payloads, REST is faster to write, easier to debug, and predictable under rate limits.
Limitations
- Network required — all
ghcommands require internet access; no offline mode. - GraphQL point budget — 5000 points/hr for authenticated users. Complex queries with
high
first/lastvalues consume points faster. Seereferences/graphql-queries.md. - Secrets are write-only —
gh secret setworks, but there is nogh secret get. Secret values cannot be retrieved after creation. - Org admin operations — managing org settings, teams, and SAML requires the
admin:orgscope, which is not granted by default. - Artifact retention — workflow artifacts are retained for 90 days by default. Expired artifacts cannot be downloaded.
Other versions157 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 157
- steipete/warelay★ 394ksame name
- moltbot/clawdbot★ 394ksame name
- moltbot/moltbot★ 394ksame name
- clawdbot/clawdbot★ 394ksame name
- steipete/clawdis★ 394ksame name
- openclaw/openclaw★ 394ksame name
- molt-bot/clawdbot★ 391ksame name
- NousResearch/hermes-agent★ 259ksame name
- spinabot/brigade★ 11ksame name
- casibase/casibase★ 5.7ksame name
147 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use BlueBubbles, plugin-sdk-impact and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
jiulingyunSkillBlueBubbles
为Clawdbot构建或更新BlueBubbles外部通道插件(扩展包,REST发送/探测,webhook入站)。
Also in 20 projects that use this
bighamxSkillplugin-sdk-impact
Query how many public plugins use a Plugin SDK method, optionally by recent release date, and assess SDK deprecation or behavior changes using live ClawHub evidence.
Also in 7 projects that use this
hkyutongSkillnode-connect
Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale, or plugins.entries.device-pair.config.publicUrl.
Also in 18 projects that use this
molt-botSkilldiscord-e2e
Test Discord with Convex-leased QA bots: check credentials without a Gateway, exercise owned messages, or prove OpenClaw replies, files, threads, reactions, streaming, and typing. Distinguish API and Gateway evidence from manual user interactions.
Also in 10 projects that use this
molt-botSkillopenclaw-repair-sweep
Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.
Also in 10 projects that use this
clawdbotSkillopenclaw-performance
Performance work in OpenClaw: a slow or heavy flow (latency, CPU, memory, SQL, RPC, renders), writing or reviewing a perf PR, or adding a cache. Count the work, delete waste first, cache last.
Also in 6 projects that use this
- +2 more from molt-bot
In this repository94 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adr-writerSkill
- agent-builderSkill
- animateSkill
- api-docs-generatorSkill
- appraiseSkill
- architecture-diagramSkill
- architecture-reviewerSkill
- arxiv-figuresSkill
- arxiv-packageSkill
- arxiv-preflightSkill
- benchmark-runnerSkill
- changelog-composerSkill
- chart-claritySkill
- citation-auditSkill
- codebase-advisorSkill
- code-refinerSkill
- competitive-analyzerSkill
- concept-to-imageSkill
- debug-investigatorSkill
- decision-mapSkill
- dependency-auditSkill
- devils-advocateSkill
- domain-modelingSkill
- engineering-retroSkill
- env-validatorSkill
- estimate-calibratorSkill
- feasibility-assessorSkill
- figure-rhetoricSkill
- figure-table-qualitySkill
- filesystemSkill
- gpu-optimizerSkill
- handoffSkill
- html-presentationSkill
- html-videoSkill
- humanizeSkill
- idea-validatorSkill
- immuneSkill
- intakeSkill
- kg-builderSkill
- launch-videoSkill
- learning-workspaceSkill
- lightpanda-browserSkill
- linkedin-post-styleSkill
- literature-reviewSkill
- manuscript-provenanceSkill
- manuscript-reviewSkill
- manuscript-typographySkill
- market-analyzerSkill
- marp-slidesSkill
- mcp-to-skillSkill
- md-to-pdfSkill
- migration-risk-analyzerSkill
- milestone-runnerSkill
- module-deepeningSkill
- notebooklmSkill
- package-evaluatorSkill
- package-optimizerSkill
- paper-to-skillSkill
- plan-promptsSkill
- The first 60 shown.
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
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.

