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.

73

Quality

90%

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

92%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.

A tight, well-structured instruction skill: concrete tool-level guidance, a clear sequenced workflow with verification checkpoints, and no padding or concept explanations. The only knock is a few minor redundancies and rhetorical flourishes that could be trimmed from the Voice and Workflow sections.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it names tools, paths, and formats without explaining concepts — e.g. 'Open the target space's `wiki/index.md` first' and the exact citation syntax. Minor trims exist: 'it is the navigation aid', 'The wiki points to `raw/` precisely so you can verify', and the Voice bullet 'The query response is itself a candidate for filing into `wiki/synthesis/`' restates step 5, which places it at the minor-trimming anchor rather than fully lean at 5.

4 / 5

Actionability

Fully concrete instruction-only guidance: named tools (`wiki_read_page`, `wiki_read_source`), exact citation formats ('(see [[wiki/concepts/managed-resources]])' or '(see raw/<filename>)'), concrete output structure ('Direct answer first, in 1–4 sentences'), and an exact log-entry format ('query | filed synthesis'). Per the scoring notes, absence of code is not penalized for instruction skills when guidance is this executable.

5 / 5

Workflow Clarity

A clearly sequenced 6-step workflow with explicit checkpoints: read the index before pages, verify thin claims against `raw/`, plain failure handling ('When the wiki cannot answer... Never bluff'), and a closing verification checklist ('Every claim in the answer cites a wiki page or raw source'). The opt-in guard on writing synthesis ('Do not write the synthesis page silently') and checklist coverage of the write path provide the validation the 5 anchor requires.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is ~41 lines of well-organized sections (Inputs, Workflow, Voice, Verification, Tools) with no content that belongs in a separate reference file. Under the rubric's simple-skill note, a sub-50-line skill with no need for external references scores 5 on well-organized sections alone.

5 / 5

Total

19

/

20

Passed

Description

87%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 strong description that clearly and explicitly states both what the skill does and when to use it, in a distinct niche with a concrete trigger. Keyword coverage is good but misses a few natural phrasings users might use when asking wiki questions.

DimensionReasoningScore

Specificity

Names the domain ('LLM Wiki operation issue' queries) and several concrete actions — 'Answer from wiki pages and raw sources with citations, name gaps plainly, and offer to file durable synthesis'. Actions are specific but slightly abstract (no mention of reading pages, following wiki-links, or the fallback path when the wiki cannot answer), leaving minor coverage gaps that keep it below the comprehensive anchor at 5.

4 / 5

Completeness

Explicitly answers both parts: 'Use when an LLM Wiki operation issue asks a question' gives the when with a concrete trigger, and 'Answer from wiki pages and raw sources with citations, name gaps plainly, and offer to file durable synthesis' gives the what. Both are clear and concrete, matching the top anchor; it does not fall to 4 because neither half is implicit or vague.

5 / 5

Trigger Term Quality

Includes natural terms a user in this environment would say — 'wiki', 'asks a question', 'query', 'citations', 'gaps'. Missing a few natural variations such as 'look up', 'search the wiki', or 'answer from the wiki', so it sits at good-but-not-comprehensive keyword coverage rather than the full synonym coverage of the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The trigger is tightly scoped to a query-type operation issue against a specific wiki space, a clear niche that is unlikely to fire for ingest/distill/write-style wiki skills. Third-person-imperative voice, no buzzwords or over-claims, so minimal conflict risk per the 5 anchor.

5 / 5

Total

18

/

20

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.

Validation — 16 / 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.