llm-wiki

Build and maintain a persistent knowledge base (LLM Wiki) using native backend tools. Supports ingesting PDFs, Markdown, and TXT files, and querying or linting the data. Use this whenever the user wants to add, retrieve, or manage their own local knowledge base and documents.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, well-structured, and actionable with named tools and files. Its main weakness is missing re-verification feedback loops for batch ingestion and lint repairs.

Suggestions

Add a re-lint step after repairing broken links (run wiki_lint again to confirm no broken links remain) to close the validation loop.

Clarify the index.md follow-up: specify the link format and that links must point to the new topic files with relative paths.

Add a verification check after ingestion (e.g., confirm log.md and index.md entries exist and links resolve) before declaring ingestion complete.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, explaining only the skill-specific 3-layer structure (manifest, log.md, index.md, schema) without padding or restating known concepts.	3 / 3
Actionability	It names the exact tools to call (wiki_ingest, wiki_query, wiki_lint) and the concrete follow-up file edits (log.md summary, index.md links), giving executable instruction-style guidance.	3 / 3
Workflow Clarity	Each operation is sequenced with a success checkpoint ("After the tool succeeds"), but the batch ingestion and lint-repair flows lack a re-verification step (e.g., re-running wiki_lint to confirm repairs), which caps clarity per the validation guideline.	2 / 3
Progressive Disclosure	At under 50 lines with no external bundle files needed, the body is well-organized into clear sections (architecture, setup, three core operations, key rules), satisfying the simple-skill exception.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete, and uses natural third-person voice with explicit trigger guidance. It cleanly answers both what the skill does and when to invoke it.

Dimension	Reasoning	Score
Specificity	"ingesting PDFs, Markdown, and TXT files, and querying or linting the data" plus "Build and maintain a persistent knowledge base" lists multiple concrete actions, matching the anchor that enumerates specific operations.	3 / 3
Completeness	It states what the skill does (build/maintain, ingest, query, lint) and gives an explicit "Use this whenever the user wants to add, retrieve, or manage their own local knowledge base and documents" trigger clause.	3 / 3
Trigger Term Quality	It surfaces natural user-facing terms — "PDFs, Markdown, TXT files", "knowledge base", "add, retrieve, or manage" — giving good coverage of phrasings a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The "persistent local LLM Wiki" / "local knowledge base" niche is distinctive and paired with specific triggers (ingest, query, lint), making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: XiaoLuoLYG/GOD
Path: jiuwenclaw/jiuwenclaw/resources/agent/jiuwenclaw_workspace/skills/llm-wiki/SKILL.md
Commit: 4fd5cfc

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.