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

Knowledge Wiki Lint

by CatChen in CatChen/knowledge-wiki-template

Audit and repair the knowledge wiki. An agent skill from CatChen/knowledge-wiki-template.

MITAuto-check passedKnowledge Management

Install Knowledge Wiki Lint

skills CLI
$ npx skills add CatChen/knowledge-wiki-template --skill knowledge-wiki-lint -a claude-code

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

GitHub CLI
$ gh skill install CatChen/knowledge-wiki-template knowledge-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/CatChen/knowledge-wiki-template.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/knowledge-wiki-lint .claude/skills/knowledge-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
knowledge-wiki-lint
GitHub stars
106
Token cost
~3.5k tokens
SKILL.md length
1,686 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Audit and repair the knowledge wiki. An agent skill from CatChen/knowledge-wiki-template.

  • Works in 12 steps: Establish the working directory → Find orphan summaries → Delete orphan summary files and remove… → …
  • Tasks that involve LLM wikis
  • SKILL.md covers Setup, Check 1 — Orphan Summaries, Check 2 — Broken Summary →… and Check 3 — Broken Concept → *…, plus 9 more sections
  • Calls node and git

What it does

Knowledge Wiki Lint is an agent skill from CatChen/knowledge-wiki-template. Audit and repair the knowledge wiki. Detects orphan summaries (source deleted), broken wikilinks, and orphan concept files. Run periodically after accumulating new content or reorganizing source files.

Its SKILL.md is about 3.5k 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. The licence is MIT.

When your agent uses it

  • Tasks that involve LLM wikis

Example prompts

  • “/knowledge-wiki-lint”

Workflow steps

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

  1. Establish the working directory
  2. Find orphan summaries
  3. Delete orphan summary files and remove their index entries
  4. Find and repair broken summary → concept links
  5. Find and remove dead bullet points
  6. Find and delete ungrounded concepts
  7. Find and delete orphan concepts
  8. Remove dead index links
  9. Find summaries missing from the index
  10. Generate and insert missing summary entries
  11. Find concepts missing from the index
  12. Generate and insert missing concept entries

What it can do on your machine

Read from SKILL.md and the folder at commit 77b9be8. 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:

    • node
    • git

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

  • Network

    No URLs in SKILL.md. Its commands use 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

Knowledge Wiki Lint loads about 3.5k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 1,686 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~3.5k

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 CatChen/knowledge-wiki-template at commit 77b9be8, republished under its MIT licence (© CatChen). 1,686 words, ~3,479 tokens.

Download SKILL.mdSave it as .claude/skills/knowledge-wiki-lint/SKILL.md (or your agent's skills folder).
name
knowledge-wiki-lint
description
Audit and repair the knowledge wiki. Detects orphan summaries (source deleted), broken wikilinks, and orphan concept files. Run periodically after accumulating new content or reorganizing source files.

Knowledge Wiki Lint

Health-check and repair the wiki. Runs twelve checks in sequence — each builds on a clean state left by the previous one. JavaScript handles all file-system detection; the LLM handles any repair that requires judgment.

Setup

1. Establish the working directory

The knowledge base root is the Git repository root. Run git rev-parse --show-toplevel and store the result as KNOWLEDGE_PATH.

Use KNOWLEDGE_PATH for all subsequent steps.

Check 1 — Orphan Summaries

Deletes summary files whose source document has been moved or deleted.

2. Find orphan summaries

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-lint.mjs find-orphan-summaries

Output is a JSON object keyed by orphan summary file path (relative to KNOWLEDGE_PATH). Each value has a source field with the path the summary expected to find, or null if the frontmatter had no source field.

If the object is empty ({}), skip to Check 2 and print Check 1: no orphan summaries.

3. Delete orphan summary files and remove their index entries

For each key in the output:

  1. Delete the file at {KNOWLEDGE_PATH}/{key}.
  2. Derive the summary's rel-path by stripping the Wiki/Summaries/ prefix and the .md extension from the key. Example: Wiki/Summaries/Posts/Foo.summary.md → Posts/Foo.summary. Then run:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs delete-summary "{rel-path}"

After processing all orphans, delete any now-empty directories under Wiki/Summaries/:

bash
find {KNOWLEDGE_PATH}/Wiki/Summaries -type d -empty -delete

Creates missing concept files referenced by summaries.

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-lint.mjs find-broken-summary-links

Output is a JSON object keyed by missing concept file path. Each value has a referencedBy array listing the summary files that link to that missing concept.

If the object is empty ({}), skip to Check 3 and print Check 2: no broken summary → concept links.

For each missing concept:

4a. Read referencing summaries

Read each file listed in the referencedBy array.

4b. Create the concept file

Create {KNOWLEDGE_PATH}/{key} following exactly the format and instructions in the knowledge-wiki-concept skill (step 3b — "If the concept file does NOT exist"). Draw on all referencing summary files to write the article.

4c. Update the index

Derive the slug from the concept file path (basename without .md), and the display name from the # Title line of the file just created. Then follow step 3c of the knowledge-wiki-concept skill.

Removes dead bullet points from concept files that link to missing targets.

5. Find and remove dead bullet points

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-lint.mjs find-broken-concept-links

Output is a JSON object keyed by concept file path. Each value has a brokenLinks array of raw wikilink target strings (the text between [[ and ]]) that resolve to missing files.

If the object is empty ({}), skip to Check 4 and print Check 3: no broken concept links.

For each concept file in the output:

  1. Derive the slug (basename of the concept file path without .md). Example: Wiki/Concepts/foo-bar.md → foo-bar.
  2. For each string in brokenLinks, inspect the target to determine which command to run:
    • If the target starts with Wiki/Summaries/ — it is a broken source link. Run:
      bash
      node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs delete-source "{slug}" "{broken-link-target}"
    • If the target starts with Wiki/Concepts/ — it is a broken connected-concept link. Extract the linked slug by stripping the Wiki/Concepts/ prefix from the target. Example: Wiki/Concepts/foo-bar → foo-bar. Run:
      bash
      node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs delete-connected-concept "{slug}" "{linked-slug}"

    Double-quote all arguments to protect special characters.

Check 4 — Ungrounded Concepts

Deletes source-grounded concept files that no longer have any valid source summaries.

6. Find and delete ungrounded concepts

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-lint.mjs find-ungrounded-concepts

Output is a JSON array of type: Concept file paths whose ## Sources section has no bullet linking to an existing Wiki/Summaries/... file. type: Synthesis files are not included.

If the array is empty ([]), skip to Check 5 and print Check 4: no ungrounded concepts.

For each path in the array:

  1. Delete the file at {KNOWLEDGE_PATH}/{path}.
  2. Derive the slug (basename of {path} without .md). Run:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs delete-concept "{slug}"

If any ungrounded concepts were deleted, rerun Check 3 once before continuing to Check 5. The rerun removes any newly broken Connected Concepts entries that pointed to the deleted files. Record removals from the rerun together with the original Check 3 result in the final summary.

Check 5 — Orphan Concepts

Deletes concept files that nothing links to.

7. Find and delete orphan concepts

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-lint.mjs find-orphan-concepts

Output is a JSON object keyed by orphan concept file path.

If the object is empty ({}), skip to Check 6 and print Check 5: no orphan concepts.

For each key in the output:

  1. Delete the file at {KNOWLEDGE_PATH}/{key}.
  2. Derive the slug (basename of {key} without .md). Run:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs delete-concept "{slug}"

Removes entries from Wiki/index.md that point to files that no longer exist on disk.

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs delete-dead-links

Output is a JSON object { "concepts": N, "summaries": N } with the count of deleted entries in each section. The script writes the updated index automatically.

If both counts are zero, print Check 6: no dead index links. and skip to Check 7.

Otherwise record the counts for the final summary — no further action required.

Check 7 — Missing Summary Index Entries

Adds index entries for summary files on disk that have no Wikilink in Wiki/index.md.

9. Find summaries missing from the index

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs find-missing-summaries

Output is a JSON array of rel-paths (e.g. ["AvocadoToast/foo.summary"]).

If the array is empty, print Check 7: no summary index entries missing. and skip to Check 8.

10. Generate and insert missing summary entries

For each rel-path in the array:

  1. Read the summary file at {KNOWLEDGE_PATH}/Wiki/Summaries/{rel-path}.md.
  2. Generate a one-line English description of the source document from the ## Summary section.
  3. Run:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs upsert-summary "{rel-path}" "{description}"
    If upsert-summary fails with summary file not found, use the exact rel-path string from the find-missing-summaries JSON output verbatim — do not retype it.

Check 8 — Missing Concept Index Entries

Adds index entries for concept files on disk that have no Wikilink in Wiki/index.md.

11. Find concepts missing from the index

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs find-missing-concepts

Output is a JSON array of slugs (e.g. ["autonomous-driving"]).

If the array is empty, print Check 8: no concept index entries missing. and skip to Check 9.

12. Generate and insert missing concept entries

For each slug in the array:

  1. Read the concept file at {KNOWLEDGE_PATH}/Wiki/Concepts/{slug}.md.
  2. Extract the display name from the # Title line of the file.
  3. Generate a one-line English description from the file's opening prose.
  4. Run:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-index.mjs upsert-concept "{slug}" "{display-name}" "{description}"
Show full SKILL.md (696 more words)Show less

Check 9 — Stale Dismissed Merge Pairs

Removes entries from the merge dismissal list in Wiki/.state.json whose concept files no longer exist.

13. Prune stale dismissed pairs

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-state.mjs prune-merge-pairs

Output is a single integer: the number of pairs pruned. If 0, print Check 9: no stale dismissed pairs.

Check 10 — Stale Dismissed Cluster Pairs

Removes entries from the cluster dismissal list in Wiki/.state.json where the child concept file no longer exists on disk. Parent absence is allowed — a pair may have been recorded before the parent was created.

14. Prune stale dismissed cluster pairs

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-state.mjs prune-cluster-pairs

Output is a single integer: the number of entries pruned. If 0, print Check 10: no stale dismissed cluster pairs.

Removes Connected Concepts entries where a concept links to itself.

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-lint.mjs find-self-links

Output is a JSON object keyed by concept file path. If empty ({}), print Check 11: no self-links. and skip to Check 12.

For each concept file in the output:

  1. Derive the slug (basename without .md). Example: Wiki/Concepts/foo-bar.md → foo-bar.
  2. Remove the self-referencing Connected Concepts entry:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-concept.mjs delete-connected-concept "{slug}" "{slug}"

Consolidates Key Concepts entries where the same concept wikilink appears more than once in the same summary, typically caused by merging or folding multiple concepts into a single parent.

Run:

bash
node {KNOWLEDGE_PATH}/scripts/wiki/wiki-lint.mjs find-duplicate-concept-links

Output is a JSON object keyed by summary file path. Each value is an array of { conceptPath, lines } objects — one per duplicated concept, listing all the lines that reference it. If empty ({}), print Check 12: no duplicate concept links. and skip to Final Steps.

17. Consolidate duplicate entries

For each summary file and each duplicated concept within it:

  1. Read all duplicate lines for that concept.
  2. Derive the concept slug from conceptPath (basename without .md). Example: Wiki/Concepts/hong-kong.md → hong-kong.
  3. Extract the display name from any duplicate line (the |Display Name part of the wikilink). If the links are bare (no | alias), read the concept file's # Title line and use that as the display name.
  4. Write a single combined description that merges the key facts from all duplicate entries. Write the description in the same language as the original entries. Example:
    • Line 1: - [[Wiki/Concepts/hong-kong|Hong Kong]] — Gray market goods helping both economies
    • Line 2: - [[Wiki/Concepts/hong-kong|Hong Kong]] — Disney used it as negotiating leverage
    • Combined description: Gray market goods trade channel and Disney's negotiating leverage for mainland market entry
  5. Delete all duplicate entries for that concept. Pass all fields via a single-quoted heredoc so that summary paths containing quotes or other shell-special characters are safe:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-summary.mjs delete-concept - <<'EOF'
{summary-rel-path}
{concept-slug}
EOF
  6. Insert the single combined entry the same way — all four fields via heredoc, one per line:
    bash
    node {KNOWLEDGE_PATH}/scripts/wiki/wiki-summary.mjs insert-concept - <<'EOF'
{summary-rel-path}
{concept-slug}
{display-name}
{combined-description}
EOF

Final Steps

18. Print summary

Print the header, then a markdown table (not in a code block) with one row per check. Output the table so it renders:

Knowledge Wiki Lint

CheckResultDetails
1 · Orphan SummariesDeleted {N} | None{comma-separated Display Names, or omit cell if none}
2 · Broken Summary → Concept LinksCreated {N} | None{comma-separated Display Names, or omit cell if none}
3 · Broken Concept → * LinksRemoved {N} | None{M} concept file(s) affected, or omit cell if none
4 · Ungrounded ConceptsDeleted {N} | None{comma-separated Display Names, or omit cell if none}
5 · Orphan ConceptsDeleted {N} | None{comma-separated Display Names, or omit cell if none}
6 · Dead Index LinksRemoved {N} | None{M} concept(s), {K} summary(s), or omit cell if none
7 · Missing Summary Index EntriesAdded {N} | None
8 · Missing Concept Index EntriesAdded {N} | None
9 · Stale Dismissed Merge PairsPruned {N} | None
10 · Stale Dismissed Cluster PairsPruned {N} | None
11 · Self-Links in Connected ConceptsRemoved {N} | None{M} concept file(s) affected, or omit cell if none
12 · Duplicate Concept Links in SummariesConsolidated {N} | Noneacross {M} summary file(s), or omit cell if none

Use None in the Result column when a check found nothing to fix. Omit the Details cell content (leave the cell empty) when there are no meaningful details beyond what the Result column already conveys.

© CatChen, 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/knowledge-wiki-lint of CatChen/knowledge-wiki-template.

Open the folder on GitHubat commit 77b9be8

Compare with similar skills

Knowledge 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.

Knowledge Wiki Lint compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Knowledge Wiki Lint this skillCatChen/knowledge-wiki-template106—~3.5kAutomated safety check: PassMIT
Karpathy LLM WikiAstro-Han/karpathy-llm-wiki2.4k—~3.6kAutomated safety check: PassMIT
LLM Wiki Knowledge GraphEgonex-AI/Understand-Anything86k1 repos~1.5kAutomated safety check: PassMIT
Hermes History IngestAr9av/obsidian-wiki3.5k1 repos~2.2kAutomated safety check: NotesMIT
LLM Wikilewislulu/llm-wiki-skill655—~3.7kAutomated safety check: PassNone
Wiki Builderrohitg00/pro-workflow2.9k—~1kAutomated safety check: PassNone

Similar skills

  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

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

    2.4k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

  • LLM Wiki Knowledge Graph

    Egonex-AI/Understand-Anything

    Detects a Karpathy-pattern LLM wiki and builds an interactive knowledge graph with entities, implicit relationships and topic clusters.

    86k GitHub starsUsed in 1 repo~1.5k tokens
    Knowledge ManagementAuto-check passed

  • Hermes History Ingest

    Ar9av/obsidian-wiki

    Ingest Hermes agent history into Obsidian as distilled knowledge.

    3.5k GitHub starsUsed in 1 repo~2.2k tokens
    Knowledge ManagementAuto-check: notes

  • 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

  • Wiki Builder

    rohitg00/pro-workflow

    Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.

    2.9k GitHub stars~1k tokensUpdated 8 days ago
    Knowledge ManagementAuto-check passed

  • Wiki Query

    rohitg00/pro-workflow

    Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub starsUsed in 1 repo~554 tokens
    Knowledge ManagementAuto-check passed

More from CatChen/knowledge-wiki-template

  • Knowledge Wiki Concept

    CatChen/knowledge-wiki-template

    Create or update wiki concept files from knowledge base summaries.

    106 GitHub stars~1.3k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Summary

    CatChen/knowledge-wiki-template

    Generate or refresh wiki summaries for knowledge base markdown files.

    106 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Synthesis

    CatChen/knowledge-wiki-template

    Scan the wiki for cross-cutting connections, implicit relationships, contradictions, and gaps across concepts and summaries, then write synthesis concept files.

    106 GitHub stars~1.9k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Cluster

    CatChen/knowledge-wiki-template

    Find groups of concepts that share an implied parent slug and handle them: if the parent does not exist, create it; if it already exists, link unconnected children to it.

    106 GitHub stars~5k tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Enrich

    CatChen/knowledge-wiki-template

    Expand thin concept articles in the knowledge wiki using web search.

    106 GitHub stars~636 tokensUpdated 3 mo ago
    Auto-check passed

  • Knowledge Wiki Merge

    CatChen/knowledge-wiki-template

    Interactively find and merge duplicate concept files in the knowledge wiki.

    106 GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Knowledge Wiki Lint

What does Knowledge Wiki Lint do?

Audit and repair the knowledge wiki. An agent skill from CatChen/knowledge-wiki-template. Knowledge Wiki Lint is an agent skill from CatChen/knowledge-wiki-template. Audit and repair the knowledge wiki.

When should I use Knowledge Wiki Lint?

Knowledge Wiki Lint fits situations like: tasks that involve LLM wikis.

How do I install Knowledge Wiki Lint in Claude Code?

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

How do I install Knowledge Wiki Lint in Codex?

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

Can I use Knowledge 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 CatChen/knowledge-wiki-template --skill knowledge-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/knowledge-wiki-lint, .gemini/skills/knowledge-wiki-lint, .github/skills/knowledge-wiki-lint and .opencode/skills/knowledge-wiki-lint in your project.

What does Knowledge Wiki Lint need to run?

Going by SKILL.md and its folder, Knowledge Wiki Lint needs the command-line tools its instructions call (node and git).

Does Knowledge Wiki Lint access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Knowledge 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 Knowledge Wiki Lint use?

Knowledge 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 Knowledge Wiki Lint use?

About 3.5k tokens (SKILL.md is roughly 14k 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 Knowledge Wiki Lint?

Skills that share tags, products or a category with Knowledge Wiki Lint: Karpathy LLM Wiki (Astro-Han/karpathy-llm-wiki, 2.4k stars), LLM Wiki Knowledge Graph (Egonex-AI/Understand-Anything, 86k stars), Hermes History Ingest (Ar9av/obsidian-wiki, 3.5k stars) and LLM Wiki (lewislulu/llm-wiki-skill, 655 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Knowledge Wiki Lint?

CatChen (a GitHub user) maintains it in CatChen/knowledge-wiki-template, which has 106 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on June 24, 2026.

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