CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The body is a tightly written, instruction-only skill with a clear workflow, concrete tooling, and an explicit verification checklist. It assumes Claude's intelligence and avoids both padding and nested references.

DimensionReasoningScore

Conciseness

The ~40-line body is lean and assumes Claude's competence — it defines no background concepts, and every section (Inputs, Workflow, Voice, Verification, Tools) earns its place, matching the lean-and-efficient anchor.

3 / 3

Actionability

Gives concrete, executable guidance for an instruction skill: named tools (wiki_read_page, wiki_read_source), required parameters (wikiId, spaceSlug), and a precise answer structure with example inline citations, so the code-absent penalty for instruction-only skills does not apply.

3 / 3

Workflow Clarity

A clearly sequenced six-step workflow (index → read pages → inspect raw sources → answer → decide durability → handle unanswerable) closes with an explicit verification checklist, meeting the clear-sequence-with-checklists anchor; the destructive-operation cap does not apply to a read/query skill.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the under-50-line skill is well-organized into labeled sections, and its inline wiki path references (wiki/index.md, raw/, wiki/synthesis/) are target-system locations rather than nested skill docs, so it scores 3 under the simple-skills note.

3 / 3

Total

12

/

12

Passed

Description

85%

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 strong, third-person, and explicitly covers both capability and trigger. Its only weak point is trigger-term breadth, which leans on system-internal jargon rather than the natural phrasings a user would say.

Suggestions

Broaden trigger terms to natural user phrasings — e.g. "Use when the user asks a question about the wiki, wants to look something up, or needs to check the docs" — alongside the existing operation-issue trigger.

Soften or gloss the jargon "LLM Wiki operation issue" so the trigger is recognizable to users who would not use that internal vocabulary.

Consider naming the domain more concretely up front (e.g. "Answer questions from a project's wiki") so the niche is obvious before the conditional clauses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "Answer from wiki pages and raw sources with citations", "name gaps plainly", and "offer to file durable synthesis" — matching the multi-action anchor rather than the partial-coverage anchor at 2.

3 / 3

Completeness

Explicitly states both what it does (answer with citations, name gaps, offer synthesis) and when to use it via an explicit "Use when..." clause, satisfying the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Includes relevant terms ("wiki", "asks a question") but leans on internal jargon ("LLM Wiki operation issue") and omits common user-facing variations like "look up", "search the wiki", or "find in the docs", so it sits at the some-keywords-but-incomplete anchor rather than full coverage.

2 / 3

Distinctiveness Conflict Risk

Targets a clear niche — answering questions from a specific wiki system via operation issues — with distinct triggers unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

11

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
paperclipai/paperclip
Reviewed

Table of Contents

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.