CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quick-check

Check one focused fact before making a claim

Quality

63%

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

Fix and improve this skill with Tessl

tessl review fix ./crates/engine/tests/fixtures/extension_host/skills-root/profiles/review-skills/quick-check/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

55%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.

The body is admirably token-efficient but underspecifies the procedure it mandates. Critical terms like 'verification boundary' and 'the exact source' are undefined, so Claude must guess what to inspect and what to report, leaving the skill's single action ambiguous.

Suggestions

Define 'verification boundary' concretely, e.g. the report should state what was checked, against which source, and what remains unverified.

Specify how to locate 'the exact source' (open the cited file, URL, or line rather than relying on memory) and show a short example of the expected report format.

Add a brief validation step, such as quoting the source snippet that supports or refutes the fact, so the reported boundary is itself verifiable.

DimensionReasoningScore

Conciseness

"Inspect the exact source and report the verification boundary." is maximally lean — a single directive sentence with zero padding, no explanations of concepts Claude already knows, and every token earning its place. This matches the 'lean and efficient; assumes Claude's competence' anchor exactly.

5 / 5

Actionability

The body gives two high-level directives ("Inspect the exact source", "report the verification boundary") but no specifics: which source counts as 'exact', how to inspect it, or what a 'verification boundary' is. This is minimal concrete guidance missing the specific steps to execute — above score 1 because it instructs rather than merely describes, but well below score 3's concrete-but-incomplete level.

2 / 5

Workflow Clarity

A rough inspect-then-report sequence is present, but the steps are poorly defined and the key term ('verification boundary') is undefined. The simple-skill exception requires the single action to be unambiguous; since it is not, this sits at 'rough sequence present but many gaps; steps poorly defined'.

2 / 5

Progressive Disclosure

At one line with no bundle files, nothing that belongs in a separate file is inlined and no references are buried, so placement is appropriate. It falls short of 5 only because the body has no organizational structure at all (no sections or overview framing), leaving a minor organization gap.

4 / 5

Total

13

/

20

Passed

Description

53%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.

The description is concise and identifies a clear niche, but it compresses what and when into a single tagline-style clause without explicit trigger guidance. It would rarely fire incorrectly, but it also underspecifies when Claude should invoke it and lacks the natural terms users say when they need fact verification.

Suggestions

Add an explicit trigger clause, e.g. "Use when about to state a fact, quote, or statistic whose accuracy is uncertain, or when the user asks to verify or double-check something."

Include natural trigger terms users would actually say: "verify", "fact-check", "confirm", "double-check", "is this true".

State what the check produces (e.g., a confirmed/rejected verdict with the supporting source) to sharpen the 'what' beyond a single action.

DimensionReasoningScore

Specificity

"Check one focused fact" names the fact-verification domain and one concrete action, matching the '1-2 concrete actions, but not comprehensive' anchor. It stops short of score 4, which requires several specific actions, and is more concrete than score 2's domain-only naming.

3 / 5

Completeness

The 'what' is clear ("Check one focused fact"), but the 'when' ("before making a claim") is purpose framing rather than an explicit 'Use when...' trigger clause, so completeness is capped at 3 per the judging guidelines. It is above score 2 because both elements are at least weakly present.

3 / 5

Trigger Term Quality

The description contains some relevant keywords ("check", "fact", "claim") but misses the natural phrases a user would say, such as "verify", "fact-check", "confirm", or "is this true". This fits 'some relevant keywords but missing common variations or synonyms' rather than the good coverage of score 4.

3 / 5

Distinctiveness Conflict Risk

"Check one focused fact before making a claim" carves a mostly distinct single-fact-verification niche with only minor overlap risk against general research/search skills. It does not reach 5 because no distinct trigger phrases are given to minimize conflict further.

4 / 5

Total

13

/

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

Hmbown/Codewhale

Path

crates/engine/tests/fixtures/extension_host/skills-root/profiles/review-skills/quick-check/SKILL.md

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.