CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-provenance-review

Flag concrete false-positive proof introduced by changed specs, not test helper or channel preferences. Advisory only; never gates Warden clearance.

58

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.warden/skills/spec-provenance-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a tight, well-structured instruction-only skill with concrete criteria, illustrative examples, and a prescriptive output template; its only weakness is minor verbosity in one clarifying example.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, never explaining what specs or test helpers are; the pricing-example clarification is somewhat verbose and could be trimmed, keeping it just below the fully-lean anchor.

4 / 5

Actionability

Concrete, actionable guidance throughout: an 'ALL of these hold' criterion, three reportable examples, a detailed do-not-report list, and a prescriptive output template; the residual judgment of identifying a concrete broken behavior keeps it from a 5.

4 / 5

Workflow Clarity

A coherent review sequence (scope → question → criteria → exclusions → output format) with a terminal checkpoint ('If that evidence is missing, report nothing'); as a read-only analysis task it needs no validate-fix loop.

4 / 5

Progressive Disclosure

Self-contained, under 50 lines, with well-organized sections and no external references needed, satisfying the simple-skill exception for progressive disclosure.

5 / 5

Total

17

/

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 sharply scoped to a specific review niche with clear anti-overlap boundaries, but it relies on domain jargon for triggers and omits an explicit 'Use when…' clause, leaving both completeness and trigger quality at the midpoint.

Suggestions

Add an explicit 'Use when…' trigger clause (e.g., 'Use when reviewing changes under evals/specs or evals/worlds for specs that may pass while their claimed behavior is broken') to lift completeness above 3.

Soften internal jargon ('Warden clearance', 'channel preferences') or pair it with natural user-facing phrasing so the trigger terms read as something a user would actually say.

Optionally name a second concrete action (e.g., 'quote the claimed behavior and identify the reachable failure') to move specificity toward 4-5.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ('Flag concrete false-positive proof introduced by changed specs'); the negation clauses are boundaries rather than additional actions, so it does not reach the 'several specific actions' anchor.

3 / 5

Completeness

The 'what' is clear, but there is no explicit 'Use when…' trigger clause; the 'when' is only weakly implied (during spec review), capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Relevant domain keywords ('false-positive', 'changed specs') appear, but the description leans on internal jargon ('Warden clearance', 'channel preferences') and lacks more natural user phrasings.

3 / 5

Distinctiveness Conflict Risk

A very narrow niche that explicitly distinguishes itself from related reviews ('not test helper or channel preferences'); minimal overlap risk with general spec-review skills, just shy of fully distinct triggers.

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
different-ai/openwork
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.