wiki-query

Use when an LLM Wiki operation issue asks a question. Answer from wiki pages and raw sources with citations, name gaps plainly, and offer to file durable synthesis when the answer should compound.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%Weight 40%Scale 1-5

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

An exemplary lean instruction-only skill: concrete tools and parameters, a well-sequenced workflow with verification, and clean section structure that needs no external bundle. No meaningful weaknesses against the rubric.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it names tools, paths, and parameters without explaining what a wiki is or padding with concepts Claude already knows; every line earns its place.	5 / 5
Actionability	Provides fully executable instruction-only guidance: exact tools (wiki_read_page, wiki_read_source), exact parameters (wikiId, spaceSlug), exact paths (wiki/index.md, raw/), and a concrete answer structure with inline citation format.	5 / 5
Workflow Clarity	A clear 6-step numbered sequence with explicit decision branches (durable-synthesis offer in step 5, cannot-answer fallback in step 6) and an explicit Verification checklist before closing the operation issue.	5 / 5
Progressive Disclosure	Under 50 lines with no need for external references and well-organized sections (Inputs, Workflow, Voice, Verification, Tools), satisfying the simple-skill exception for a top progressive_disclosure score.	5 / 5
	Total	20 / 20 Passed

Description

76%Weight 40%Scale 1-5

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

A clear, action-oriented description that explicitly covers both what and when with a distinct wiki-query niche. Its main weakness is trigger phrasing that leans on internal 'operation issue' jargon rather than natural user language.

Suggestions

Add natural-language trigger synonyms users would actually say, e.g. 'Use when a user asks the wiki a question or wants to query wiki content', alongside the operation-issue trigger.

Consider mentioning the operationType:query discriminator only if it aids routing; lead the trigger with plain phrasing like 'query the wiki' to improve trigger_term_quality.

The 'offer to file durable synthesis when the answer should compound' clause is specific but slightly opaque; a plainer gloss (e.g. 'offer to save reusable syntheses') could sharpen specificity without padding.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('Answer from wiki pages and raw sources with citations', 'name gaps plainly', 'offer to file durable synthesis'), fitting 'several specific actions; minor gaps' rather than the comprehensive 5 or the 1-2-action 3.	4 / 5
Completeness	Explicitly answers both what ('Answer from wiki pages... with citations, name gaps... offer to file durable synthesis') and when ('Use when an LLM Wiki operation issue asks a question') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Has relevant keywords ('wiki', 'asks a question') but the trigger 'LLM Wiki operation issue' is internal jargon and misses natural variations like 'query the wiki', matching 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The query-operation niche is mostly distinct, but shared wiki tooling and the synthesis-filing step create minor overlap risk with sibling wiki-ingest/edit skills, fitting 'mostly distinct; minor overlap risk' over the minimal-conflict 5.	4 / 5
	Total	16 / 20 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: paperclipai/paperclip
Path: packages/plugins/plugin-llm-wiki/skills/wiki-query/SKILL.md
Commit: 890ab9a

Reviewed: about 16 hours 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.