project-maintainer
Skill383 starsChanged 5 months agoMITView on GitHub
Maintain an llmwiki-style open-source project across the full framework pipeline. Use when the user says "maintain the project", "check my tasks", "update progress", "run phase gate", "do a monthly verify", "lint my wiki", "check stale entries", or invokes any form of ongoing project-keeping chore. Reads _progress.md, tasks.md, docs/roadmap.md, and .github issues to figure out what's next and what's drifted.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- pygent-ai/project-maintainertheir own version, first seen Aug 5, 2026
- Hi-Jiajun/openclaw-skills-publictheir own version, first seen Mar 9, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- pygent-ai/project-maintainer★ 1same name
- Hi-Jiajun/openclaw-skills-public★ 0same name
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.
In this repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llmwiki-ingestSkill
- llmwiki-querySkill
- llmwiki-syncSkill
- self-learnSkill
- wiki-allSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 52
Locate the project root: Look for _progress.md in the current dir or its parents.
- Distinctive: line 66
If any drift — propose fixes before making any changes.
- Very specific: line 103
Never silently update
_progress.md: Always explain what changed and why.
≈ “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.
Files
project-maintainer
What this skill does
The Maintainer owns the full Open Source Framework v4.1 pipeline on a project. Given the current repo state, it:
- Audits phase gates — are we in the right phase? Are the deliverables for the current phase complete?
- Reconciles task tracking — keeps
tasks.md,_progress.md, and GitHub issues in sync (the framework's "dual-tracking" rule). - Runs stale checks — flags content, links, and claims older than the stale threshold.
- Triggers CI — re-runs the privacy grep, performance budget check, and link checker.
- Reports next action — tells the user exactly what to do next and why.
It works for any project that follows the framework — not just llmwiki.
When to invoke
- "Maintain the project" / "maintenance check" / "do a health check"
- "Update progress" / "reconcile tasks" / "sync tasks"
- "Check phase gate" / "can I move to the next phase"
- "Lint the wiki" / "check for stale entries"
- "Monthly verify" / "quarterly review"
- Any time the user is unsure what to work on next
Framework phase awareness
| Phase | The Maintainer's job in this phase |
| 0 Capture | Verify idea-brief.md exists and names target users + the 10x mechanism |
| 1 Validate | Verify scorecard /25 is in _progress.md and ≥20 |
| 1.25 Research | Verify .temp/ has at least 10 cloned reference repos and docs/research.md exists with a gap matrix |
| 1.5 Steering | Verify _progress.md has "Key Decisions" table filled in |
| 1.75 Agent Survey | For agent-native tools — verify adapter compatibility matrix exists |
| 2 Brand | Verify README.md, LICENSE, and badges are in place |
| 3 Structure | Verify folder layout matches docs/architecture.md |
| 4 Content | Track which M items in docs/roadmap.md are ✅ vs [ ] |
| 5 Contribution | Verify CONTRIBUTING.md, PR template, issue templates, CI workflow |
| 5.25 Adapter Flow | For agent-native tools — verify adapter contract doc + at least one community contribution example |
| 5.5 Pre-Launch QA | Run the full QA checklist from docs/framework.md |
| 6 Launch | Verify git tag + GitHub Release + social posts drafted |
| 6.5 Self-Demo | Verify GitHub Pages workflow triggered and live URL returns 200 |
| 7 Grow | Track stars / forks / downloads week-over-week |
| 7.5 Living Knowledge | Verify public wiki is updating on release |
| 8 Maintain | Run monthly verification, merge PRs, update stale entries |
Workflow
- Locate the project root. Look for
_progress.mdin the current dir or its parents. If missing, tell the user this skill needs a project that follows the framework. - Read the state files:
_progress.md— current phase + phase status tabletasks.md— Kiro-style tasks with[ ]/[/]/[x]/[-]markersdocs/roadmap.md— if present, the master MoSCoW tableCHANGELOG.md— latest release
- Audit each phase gate up to the current phase. For each phase marked done, verify the deliverable file exists and is non-empty. Report any gaps.
- Reconcile task tracking:
- Are there items in
tasks.mdmarked[x]but not inCHANGELOG.md? - Are there open GitHub issues with no matching task in
tasks.md? - Are there tasks in
tasks.mdwith no corresponding GitHub issue? - If any drift — propose fixes before making any changes.
- Are there items in
- Run stale checks:
- Any
last_updatedin wiki frontmatter older than 30 days? Flag. - Any
source_filereference in wiki pointing to a file that no longer exists? Flag. - Any entity page mentioned in 3+ sources but with its own
last_updatedolder than the newest source? Flag. - Any
[[wikilink]]pointing to a non-existent page? Flag.
- Any
- Run CI gates locally (if configured):
- Privacy grep:
grep -r "<real_username>" site/ wiki/must be empty - Link check:
python3 -m llmwiki lint-docs(when implemented) - Performance budget: build time
<15s, HTML<50MB
- Privacy grep:
- Write the report. Structure:
## Health report: <project> — <date> **Phase:** <current phase> (<status>) ### ✅ Green - <things that are fine> ### ⚠️ Yellow - <minor drift that should be fixed soon> ### ❌ Red - <broken gates that block progress> ### Next action 1. <specific thing the user should do next> 2. <second thing if any> - Offer to fix green issues automatically. For yellow/red, ask before touching anything.
Hard rules
- Never silently update
_progress.md. Always explain what changed and why. - Never close a GitHub issue without the user saying so.
- Never overwrite
tasks.mdwithout showing the diff first. - Respect the framework's "one PR per concern" rule — if a fix spans multiple files, surface it as multiple suggestions, not one big patch.
- Never auto-bump versions. Version bumps are a launch activity, not maintenance.
Related skills
self-learn— when a new pattern emerges during maintenance, pipe it toself-learnto potentially add it to the framework.llmwiki-query— when you need context from past sessions on why a decision was made.llmwiki-lint— for wiki-specific lint work (overlaps with step 5).
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.

