Agent skill

Project Maintainer

by Pratiyush in Pratiyush/llm-wiki

Maintain an llmwiki-style open-source project across the full framework pipeline.

MITAuto-check passedKnowledge Management

Install Project Maintainer

skills CLI
$ npx skills add Pratiyush/llm-wiki --skill project-maintainer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Pratiyush/llm-wiki project-maintainer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Pratiyush/llm-wiki.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/project-maintainer .claude/skills/project-maintainer && rm -rf skills-src

Use ~/.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/

Facts

Skill name
project-maintainer
GitHub stars
396
Token cost
~1.4k tokens
SKILL.md length
689 words
Files
1
Skills in repo
6
Repo updated
First seen
Licence
MIT

At a glance

Maintain an llmwiki-style open-source project across the full framework pipeline.

  • Works in 5 steps: Audits phase gates — are we in the right… → Reconciles task tracking — keeps… → Runs stale checks — flags content,… → …
  • The user says maintain the project
  • SKILL.md covers What this skill does, When to invoke, Framework phase awareness and Workflow, plus 2 more sections
  • Calls python3

What it does

Project Maintainer is an agent skill from Pratiyush/llm-wiki. 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.

Its SKILL.md is about 1.4k 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 Knowledge Management, covering LLM wikis and Linting and formatting. It works with GitHub. The repository describes itself as: LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped. The licence is MIT.

When your agent uses it

  • The user says maintain the project
  • Update progress
  • Do a monthly verify
  • Check stale entries

Example prompts

  • “maintain the project”
  • “check my tasks”
  • “update progress”
  • “/project-maintainer”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Audits phase gates — are we in the right phase? Are the deliverables for the current phase complete?
  2. Reconciles task tracking — keeps tasks.md, _progress.md, and GitHub issues in sync (the framework's "dual-tracking" rule).
  3. Runs stale checks — flags content, links, and claims older than the stale threshold.
  4. Triggers CI — re-runs the privacy grep, performance budget check, and link checker.
  5. Reports next action — tells the user exactly what to do next and why.

What it can do on your machine

Read from SKILL.md and the folder at commit b108889. 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:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Project Maintainer loads about 1.4k tokens when it runs. Until then it costs about 108 tokens; SKILL.md has 689 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~108
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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 Pratiyush/llm-wiki at commit b108889, republished under its MIT licence (© Pratiyush). 689 words, ~1,439 tokens.

Download SKILL.mdSave it as .claude/skills/project-maintainer/SKILL.md (or your agent's skills folder).
name
project-maintainer
description
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.

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:

  1. Audits phase gates — are we in the right phase? Are the deliverables for the current phase complete?
  2. Reconciles task tracking — keeps tasks.md, _progress.md, and GitHub issues in sync (the framework's "dual-tracking" rule).
  3. Runs stale checks — flags content, links, and claims older than the stale threshold.
  4. Triggers CI — re-runs the privacy grep, performance budget check, and link checker.
  5. 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

PhaseThe Maintainer's job in this phase
0 CaptureVerify idea-brief.md exists and names target users + the 10x mechanism
1 ValidateVerify scorecard /25 is in _progress.md and ≥20
1.25 ResearchVerify .temp/ has at least 10 cloned reference repos and docs/research.md exists with a gap matrix
1.5 SteeringVerify _progress.md has "Key Decisions" table filled in
1.75 Agent SurveyFor agent-native tools — verify adapter compatibility matrix exists
2 BrandVerify README.md, LICENSE, and badges are in place
3 StructureVerify folder layout matches docs/architecture.md
4 ContentTrack which M items in docs/roadmap.md are ✅ vs [ ]
5 ContributionVerify CONTRIBUTING.md, PR template, issue templates, CI workflow
5.25 Adapter FlowFor agent-native tools — verify adapter contract doc + at least one community contribution example
5.5 Pre-Launch QARun the full QA checklist from docs/framework.md
6 LaunchVerify git tag + GitHub Release + social posts drafted
6.5 Self-DemoVerify GitHub Pages workflow triggered and live URL returns 200
7 GrowTrack stars / forks / downloads week-over-week
7.5 Living KnowledgeVerify public wiki is updating on release
8 MaintainRun monthly verification, merge PRs, update stale entries
Show full SKILL.md (387 more words)Show less

Workflow

  1. Locate the project root. Look for _progress.md in the current dir or its parents. If missing, tell the user this skill needs a project that follows the framework.

  2. Read the state files:

    • _progress.md — current phase + phase status table
    • tasks.md — Kiro-style tasks with [ ]/[/]/[x]/[-] markers
    • docs/roadmap.md — if present, the master MoSCoW table
    • CHANGELOG.md — latest release
  3. 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.

  4. Reconcile task tracking:

    • Are there items in tasks.md marked [x] but not in CHANGELOG.md?
    • Are there open GitHub issues with no matching task in tasks.md?
    • Are there tasks in tasks.md with no corresponding GitHub issue?
    • If any drift — propose fixes before making any changes.
  5. Run stale checks:

    • Any last_updated in wiki frontmatter older than 30 days? Flag.
    • Any source_file reference in wiki pointing to a file that no longer exists? Flag.
    • Any entity page mentioned in 3+ sources but with its own last_updated older than the newest source? Flag.
    • Any [[wikilink]] pointing to a non-existent page? Flag.
  6. 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
  7. 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>
  8. Offer to fix green issues automatically. For yellow/red, ask before touching anything.

Hard rules

  1. Never silently update _progress.md. Always explain what changed and why.
  2. Never close a GitHub issue without the user saying so.
  3. Never overwrite tasks.md without showing the diff first.
  4. Respect the framework's "one PR per concern" rule — if a fix spans multiple files, surface it as multiple suggestions, not one big patch.
  5. Never auto-bump versions. Version bumps are a launch activity, not maintenance.
  • self-learn — when a new pattern emerges during maintenance, pipe it to self-learn to 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).

© Pratiyush, MIT. 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 .claude/skills/project-maintainer of Pratiyush/llm-wiki.

Open the folder on GitHubat commit b108889

Compare with similar skills

Project Maintainer 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.

Project Maintainer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Project Maintainer this skillPratiyush/llm-wiki396—~1.4kAutomated safety check: PassMIT
Mc Wiki Deep Lintreceptron/mulmoclaude367—~1.4kAutomated safety check: WarnMIT
Speckit Wiki Statusharu/redmine_ai_helper106—~647Automated safety check: PassMIT
Swarmvaultswarmclawai/swarmvault708—~6.1kAutomated safety check: PassMIT
Quartz Wikiliangdabiao/llm-wiki156—~861Automated safety check: PassNone
Mindbasefrankchu91/mindbase-llm-wiki128—~1.1kAutomated safety check: PassMIT

Similar skills

  • Mc Wiki Deep Lint

    receptron/mulmoclaude

    On-demand LLM-driven wiki review — find contradictions between pages, stale claims, and missing concepts (topics mentioned in index.md / log.md / sources but not yet captured as their own page).

    367 GitHub stars~1.4k tokensUpdated yesterday
    Knowledge ManagementAuto-check: warnings
  • Speckit Wiki Status

    haru/redmine_ai_helper

    Compact wiki snapshot: counts, freshness, open lint issues, and one recommended next action

    106 GitHub stars~647 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Swarmvault

    swarmclawai/swarmvault

    Use SwarmVault when the user needs a local-first knowledge vault that writes durable markdown, graph, search, dashboard, review, chat-session, context-pack, task-ledger, static AI export, retrieval…

    708 GitHub stars~6.1k tokensUpdated 3 mo ago
    Knowledge ManagementAuto-check passed
  • Quartz Wiki

    liangdabiao/llm-wiki

    Set up and deploy Quartz v4 static site for markdown wikis. An agent skill from liangdabiao/llm-wiki.

    156 GitHub stars~861 tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed
  • Mindbase

    frankchu91/mindbase-llm-wiki

    Maintain a persistent AI-tended research wiki. An agent skill from frankchu91/mindbase-llm-wiki.

    128 GitHub stars~1.1k tokensUpdated 24 days ago
    Knowledge ManagementAuto-check passed
  • Export Template

    HurricaHjz/second-yourself

    Sync THIS LLM-Wiki framework with its public GitHub repo, ONE direction per run: --push (vault → repo) publishes your framework; --pull (repo → vault) updates your framework from a newer repo version.

    114 GitHub stars~4.8k tokensUpdated 7 days ago
    Knowledge ManagementAuto-check: warnings

More from Pratiyush/llm-wiki

  • Llmwiki Query

    Pratiyush/llm-wiki

    Answer a question by querying the user's llmwiki. An agent skill from Pratiyush/llm-wiki.

    396 GitHub stars~684 tokensUpdated 3 mo ago
    Auto-check passed
  • Llmwiki Sync

    Pratiyush/llm-wiki

    Sync Claude Code session transcripts into the user's llmwiki and ingest them into the wiki.

    396 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Self Learn

    Pratiyush/llm-wiki

    Extract reusable patterns from recent sessions, propose framework improvements, and (with approval) update the framework docs.

    396 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Wiki All

    Pratiyush/llm-wiki

    Run the complete llmwiki pipeline from scratch — init, sync, graph, build, lint, and serve.

    396 GitHub stars~587 tokensUpdated 3 mo ago
    Auto-check passed
  • Llmwiki Ingest

    Pratiyush/llm-wiki

    Ingest one source document (or a folder of them) into the llmwiki.

    396 GitHub stars~691 tokensUpdated 3 mo ago
    Auto-check passed

Works with

Questions about Project Maintainer

What does Project Maintainer do?

Maintain an llmwiki-style open-source project across the full framework pipeline. Project Maintainer is an agent skill from Pratiyush/llm-wiki. Maintain an llmwiki-style open-source project across the full framework pipeline.

When should I use Project Maintainer?

Project Maintainer fits situations like: the user says maintain the project; update progress; do a monthly verify; check stale entries.

How do I install Project Maintainer in Claude Code?

Run `npx skills add Pratiyush/llm-wiki --skill project-maintainer -a claude-code`. Or copy the skill folder (.claude/skills/project-maintainer in Pratiyush/llm-wiki) into .claude/skills/project-maintainer in your project. Claude Code loads it when a task matches its description.

How do I install Project Maintainer in Codex?

Run `npx skills add Pratiyush/llm-wiki --skill project-maintainer -a codex`. Or copy the skill folder (.claude/skills/project-maintainer in Pratiyush/llm-wiki) into .agents/skills/project-maintainer in your project. Codex loads it when a task matches its description.

Can I use Project Maintainer 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 Pratiyush/llm-wiki --skill project-maintainer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/project-maintainer, .gemini/skills/project-maintainer, .github/skills/project-maintainer and .opencode/skills/project-maintainer in your project.

What does Project Maintainer need to run?

Going by SKILL.md and its folder, Project Maintainer needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Project Maintainer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Project Maintainer 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 Project Maintainer use?

Project Maintainer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Project Maintainer use?

About 1.4k tokens (SKILL.md is roughly 5.8k 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 Project Maintainer?

Skills that share tags, products or a category with Project Maintainer: Mc Wiki Deep Lint (receptron/mulmoclaude, 367 stars), Speckit Wiki Status (haru/redmine_ai_helper, 106 stars), Swarmvault (swarmclawai/swarmvault, 708 stars) and Quartz Wiki (liangdabiao/llm-wiki, 156 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Project Maintainer?

Pratiyush (a GitHub user) maintains it in Pratiyush/llm-wiki, which has 396 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 18, 2026.

Source: Pratiyush/llm-wiki on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.