New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Speckit Wiki Lint

by haru in haru/redmine_ai_helper

Health-check the wiki: contradictions, orphan pages, stale claims, broken links, index drift

MITAuto-check passedKnowledge Management

Install Speckit Wiki Lint

skills CLI
$ npx skills add haru/redmine_ai_helper --skill speckit-wiki-lint -a claude-code

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

GitHub CLI
$ gh skill install haru/redmine_ai_helper speckit-wiki-lint --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/haru/redmine_ai_helper.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/speckit-wiki-lint .claude/skills/speckit-wiki-lint && 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
speckit-wiki-lint
GitHub stars
106
Token cost
~935 tokens
SKILL.md length
428 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Health-check the wiki: contradictions, orphan pages, stale claims, broken links, index drift

  • Works in 5 steps: Resolve the wiki → Run the checks → Apply mechanical fixes (per config) → …
  • Tasks that involve LLM wikis
  • SKILL.md covers User Input, Steps and Guardrails
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Speckit Wiki Lint is an agent skill from haru/redmine_ai_helper. Health-check the wiki: contradictions, orphan pages, stale claims, broken links, index drift

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires spec-kit project structure with .specify/ directory

It sits in Knowledge Management, covering LLM wikis and Spec-driven development. The repository describes itself as: A Redmine plugin that adds AI agents, MCP Server, smart completion, and vector search. The licence is MIT.

When your agent uses it

  • Tasks that involve LLM wikis
  • Tasks that involve Spec-driven development

Example prompts

  • “/speckit-wiki-lint”

Requirements

  • Compatibility (from SKILL.md): Requires spec-kit project structure with .specify/ directory

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Resolve the wiki
  2. Run the checks
  3. Apply mechanical fixes (per config)
  4. Write the report
  5. Report

What it can do on your machine

Read from SKILL.md and the folder at commit 3cd87d6. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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.

  • Compatibility

    Requires spec-kit project structure with .specify/ directory

    From compatibility in the SKILL.md frontmatter.

Context cost

Speckit Wiki Lint loads about 935 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 428 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~28
When it runs · the whole SKILL.md, loaded when a task matches
~935

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 haru/redmine_ai_helper at commit 3cd87d6, republished under its MIT licence (© haru). 428 words, ~935 tokens.

Download SKILL.mdSave it as .claude/skills/speckit-wiki-lint/SKILL.md (or your agent's skills folder).
name
speckit-wiki-lint
description
Health-check the wiki: contradictions, orphan pages, stale claims, broken links, index drift
compatibility
Requires spec-kit project structure with .specify/ directory
metadata.author
formin
metadata.source
extension:wiki
user-invocable
true
disable-model-invocation
false

Wiki Lint Skill

Lint the Wiki

The maintenance pass that keeps a compounding wiki from rotting. Karpathy's LLM Wiki pattern calls for regular health checks — contradictions, orphaned pages, stale claims, coverage gaps — because an unmaintained knowledge base is abandoned, not merely imperfect.

Mechanical problems are fixed automatically (when configured); semantic problems are reported with suggested edits, never auto-rewritten.

User Input

text
$ARGUMENTS

Optional scope: a page filename (lint one page and its neighbors) or a check name from the list below (run only that check). Empty means the full pass.

Steps

1. Resolve the wiki

Load configuration exactly as /speckit.wiki.init does. If WIKI_DIR/SCHEMA.md does not exist, report that and stop. Read SCHEMA.md, INDEX.md, and sources.md; read pages as each check requires.

2. Run the checks
CheckFindsSeverity
index-driftpages missing from INDEX.md; index lines pointing at nonexistent filesmechanical
linksrelative links to missing pages; citations naming unknown S-idsmechanical
orphanspages no other page links to (INDEX itself does not count)structural
contradictions> ⚠ conflict: markers still unresolved; pairs of pages sharing a source or link that assert incompatible claimssemantic
stalepages whose updated is older than lint.stale_after_days; pages whose source was re-ingested after the page was last updatedsemantic
citationsclaims without a source ID, when ingest.require_citations is truesemantic

Bound the contradiction check: compare only pages that share a source ID or a link — never all pairs.

Show full SKILL.md (199 more words)Show less
3. Apply mechanical fixes (per config)

If lint.auto_fix is index-and-links:

  • regenerate INDEX.md from the actual pages/ contents (grouped by frontmatter type, one line each);
  • repair links whose target was renamed (when the target is unambiguous) and remove links to pages that no longer exist.

If lint.auto_fix is none, list these as suggested fixes instead. Never auto-fix a semantic finding — do not rewrite prose, resolve conflicts, or delete claims.

4. Write the report

Overwrite WIKI_DIR/lint-report.md:

markdown
# Wiki Lint Report — <today's date>

| # | Check | Severity | Page | Finding | Suggested fix |
|---|-------|----------|------|---------|---------------|
| 1 | contradictions | semantic | payments-retries.md | S002 vs S007 on retry cap | re-ingest source S002; keep the newer claim, drop the marker |

One row per finding; a clean pass writes the header plus "No findings."

5. Report
  • Counts per check, fixes applied vs. suggested.
  • The two or three highest-value findings, verbatim from the table.
  • Next step: the single action that clears the most severe finding (usually a re-ingest of a stale source, or a conflict for the user to resolve by editing the page).

Guardrails

  • Mechanical fixes only — INDEX.md and link targets. Page prose, claims, conflict markers, and sources.md history are never modified by lint.
  • lint-report.md is the only file lint may overwrite wholesale.
  • Findings must be verifiable: every row names the page and the exact claim or link it refers to.
  • Stay within the configured token budget: read pages check-by-check, not the whole wiki at once.

© haru, 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/speckit-wiki-lint of haru/redmine_ai_helper.

Open the folder on GitHubat commit 3cd87d6

Compare with similar skills

Speckit Wiki Lint 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.

Speckit Wiki Lint compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Speckit Wiki Lint this skillharu/redmine_ai_helper106—~935Automated safety check: PassMIT
Mc Wiki Deep Lintreceptron/mulmoclaude371—~1.4kAutomated safety check: WarnMIT
Braindbdimknaf/braindb111—~6.1kAutomated safety check: NotesApache-2.0
Export TemplateHurricaHjz/second-yourself123—~4.8kAutomated safety check: WarnMIT
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.5k—~3.6kAutomated safety check: PassMIT
Large Codebase Knowledge Base BuilderTencent/teamai-cli5.2k—~4.4kAutomated safety check: PassCustom licence

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).

    371 GitHub stars~1.4k tokensUpdated yesterday
    Knowledge ManagementAuto-check: warnings

  • Braindb

    dimknaf/braindb

    Memory recall and save. An agent skill from dimknaf/braindb.

    111 GitHub stars~6.1k tokensUpdated 29 days ago
    Knowledge ManagementAuto-check: notes

  • 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.

    123 GitHub stars~4.8k tokensUpdated 9 days ago
    Knowledge ManagementAuto-check: warnings

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.5k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

  • Large Codebase Knowledge Base Builder

    Tencent/teamai-cli

    Compresses a large multi-repository codebase into a structured knowledge base through architecture reverse-engineering, a Graph RAG graph and AST analysis.

    5.2k GitHub stars~4.4k tokensUpdated yesterday
    Knowledge ManagementAuto-check passed

  • LLM Wiki

    lewislulu/llm-wiki-skill

    Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers…

    655 GitHub stars~3.7k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check passed

More from haru/redmine_ai_helper

All 23 skills in this repo

  • Commit

    haru/redmine_ai_helper

    Stage the current changes and create a git commit with a properly formatted English message.

    106 GitHub stars~1.1k tokensUpdated today
    Auto-check: notes

  • Create Pull Request

    haru/redmine_ai_helper

    Create a pull request from the current branch. An agent skill from haru/redmine_ai_helper.

    106 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Create Release Branch

    haru/redmine_ai_helper

    Create a release branch for a given version. An agent skill from haru/redmine_ai_helper.

    106 GitHub stars~599 tokensUpdated today
    Auto-check passed

  • Record Code Review Feedback

    haru/redmine_ai_helper

    Record code review findings (GitHub Copilot PR review or a local AI review) that led to a code change in docs/code-review-feedback/ as append-only entries with root-cause analysis.

    106 GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • Record Spec Feedback

    haru/redmine_ai_helper

    Record a user's correction of an AI-written specification in docs/spec-feedback/ as an append-only entry with root-cause analysis.

    106 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Qlty Check

    haru/redmine_ai_helper

    Code quality checks, formatting, and metrics via qlty CLI. An agent skill from haru/redmine_ai_helper.

    106 GitHub starsUsed in 2 repos~628 tokens
    Auto-check passed

Categories

Questions about Speckit Wiki Lint

What does Speckit Wiki Lint do?

Health-check the wiki: contradictions, orphan pages, stale claims, broken links, index drift. Speckit Wiki Lint is an agent skill from haru/redmine_ai_helper.

When should I use Speckit Wiki Lint?

Speckit Wiki Lint fits situations like: tasks that involve LLM wikis; tasks that involve Spec-driven development.

How do I install Speckit Wiki Lint in Claude Code?

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

How do I install Speckit Wiki Lint in Codex?

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

Can I use Speckit Wiki Lint 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 haru/redmine_ai_helper --skill speckit-wiki-lint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/speckit-wiki-lint, .gemini/skills/speckit-wiki-lint, .github/skills/speckit-wiki-lint and .opencode/skills/speckit-wiki-lint in your project.

What does Speckit Wiki Lint need to run?

SKILL.md names no scripts, command-line tools or credentials: Speckit Wiki Lint is instructions for the agent only. Compatibility (from SKILL.md): Requires spec-kit project structure with .specify/ directory.

Does Speckit Wiki Lint 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 Speckit Wiki Lint 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 Speckit Wiki Lint use?

Speckit Wiki Lint 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 Speckit Wiki Lint use?

About 935 tokens (SKILL.md is roughly 3.7k 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 Speckit Wiki Lint?

Skills that share tags, products or a category with Speckit Wiki Lint: Mc Wiki Deep Lint (receptron/mulmoclaude, 371 stars), Braindb (dimknaf/braindb, 111 stars), Export Template (HurricaHjz/second-yourself, 123 stars) and Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Speckit Wiki Lint?

haru (a GitHub user) maintains it in haru/redmine_ai_helper, which has 106 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 10, 2026.

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