llm-wiki agent skill by praneybehl

At a glance

Before you install

Read from the skill's files at the directory's October 19, 2026 snapshot: what ships with it, what its code reads, and the terms it is published under.

• Bundled scripts: 15 script files (15 Python). Your agent may run them, so read them first.
• Environment variables its scripts read: ANTHROPIC_API_KEY. Check SKILL.md for which ones it needs.
• Network: its scripts use an HTTP client or a cloud SDK, and name api.anthropic.com and graphml.graphdrawing.org.
• License: MIT, an open-source or open-content license.

Install llm-wiki

The skills CLI works with Claude Code, Codex, Cursor and other agents; the other routes copy the folder by hand.

npx skills add https://github.com/praneybehl/llm-wiki-plugin/tree/main/skills/llm-wiki

tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/praneybehl/llm-wiki-plugin.git "$tmp/repo"
mkdir -p .claude/skills
cp -R "$tmp/repo/"skills/llm-wiki .claude/skills/
rm -rf "$tmp"

python3 ~/.codex/skills/.system/skill-installer/scripts/install-skill-from-github.py \
    --repo praneybehl/llm-wiki-plugin \
    --path skills/llm-wiki

praneybehl/llm-wiki-plugin is third-party code. Read SKILL.md and any bundled scripts before you install it.

How the author describes it

Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate success/failure patterns, and propose, evaluate, apply or roll back evidence-linked skill improvements. Trigger on "add this to my wiki", "what does the wiki say", "learn from this task", "improve this procedure", /wiki:learn or /wiki:evolve. Use index-first navigation, atomic pages and local hybrid search.

From the description field of SKILL.md. Agents read this line to decide when to load the skill.

Sections in SKILL.md

• The pattern in one paragraph
• When to use this skill
• Architecture: three layers, three operations
• Graph layer (compiled, optional)
• Storage scope and layout
• The scalability discipline
• Initializing a new wiki
• The ingest workflow (summary)
• The query workflow (summary)
• The lint workflow (summary)
• Failure modes to guard against
• Reference files
• Bundled scripts
• Templates
• Learning from task experience and evolving skills

Files in the skill folder

• SKILL.md
• assets/SCHEMA.md.template
• assets/evolution_README.md.template
• assets/experience.json.template
• assets/graph_README.md.template
• assets/graph_gitignore.template
• assets/index.md.template
• assets/log.md.template
• assets/ontology.yaml.template
• assets/page.md.template
• assets/pattern.md.template
• assets/wiki-cache_gitignore.template
• references/agent-memory-integration.md
• references/architecture.md
• references/evolution-workflow.md
• references/graph-workflow.md
• references/ingest-workflow.md
• references/lint-workflow.md
• references/page-conventions.md
• references/query-workflow.md
• references/retrieval-setup.md
• references/scaling-playbook.md
• scripts/init_wiki.py
• scripts/setup_wiki.py

Showing 24 of 37 files. Browse the folder on GitHub.

Suede Skill Check: 80/100 · B

llm-wiki passes the required frontmatter check and all seven graded checks, which cover the SKILL.md format, a declared license and a commit in the last year. Those checks earn 56 of the score’s points; the rest come from description quality, instruction depth, bundled files, maintenance and curated-list citations. How the score works.

Where this skill is cited

praneybehl/llm-wiki-plugin appears in 2 curated lists: BehiSecc/awesome-claude-skills, karanb192/awesome-claude-skills.

More productivity skills

All productivity and knowledge work skills