CtrlK
BlogDocsLog inGet started
Tessl Logo

change-review

Use when reviewing a set of changes before they merge in a Repowise-indexed repository, a PR, a branch diff, or the working-tree changes you just made. Activates for "review this PR", "is this safe to merge", "what is the blast radius of these changes", or "did I miss anything".

72

Quality

88%

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

82%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 dense, actionable guide that sequences the review workflow well and gives concrete tool calls with field-level semantics. Tightening a few explanatory passages and making validation cues explicit would lift conciseness and workflow clarity.

Suggestions

Tighten the prose around field semantics (e.g. the tests_to_run_basis paragraph) to remove wording that restates what the field names already convey, improving conciseness.

Add an explicit validation checkpoint in the main workflow — e.g. 'If get_change_risk returns a warning band, do not treat an all-zero score as safe; re-scope the revspec first' — to make the feedback loop structural rather than narrative.

Consider moving the per-field directive reference detail into a one-level-deep reference file so the SKILL.md body stays a tight overview, strengthening progressive disclosure.

DimensionReasoningScore

Conciseness

Lean and tool-specific with no padding on basics Claude already knows ('No LLM, no network.' earns its place), but a few explanatory sentences about field semantics could be trimmed, keeping it just below the fully-lean anchor 5.

4 / 5

Actionability

Provides concrete, copy-paste-ready invocations covering the common cases — 'get_change_risk(revspec="main..HEAD")', 'gh pr diff <number>', 'git diff --name-only main...HEAD' — plus specific return-field semantics, matching the fully-executable anchor 5.

5 / 5

Workflow Clarity

Clear sequenced workflow ('Score the whole change first' → 'Then drill into the directive block' → numbered 'go deeper where it matters') with an error-handling section and a validation cue ('A warning field means... not a clean bill of health'), but lacks explicit validate-and-retry checkpoints for the analytical workflow.

4 / 5

Progressive Disclosure

Well-organized into clearly signaled sections with no nested or buried references and a self-contained body; no bundle files exist to reference, and the sectioning is good but not the maximally clean overview-with-one-level-deep-refs pattern of anchor 5.

4 / 5

Total

17

/

20

Passed

Description

95%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, trigger-rich description that explicitly pairs capability with concrete activation phrases and a well-scoped niche. Only minor: it could enumerate the distinct review actions rather than contexts to push specificity to 5.

DimensionReasoningScore

Specificity

Names the domain (reviewing changes pre-merge) and several concrete contexts — 'a PR, a branch diff, or the working-tree changes you just made' — but does not enumerate multiple distinct actions, leaving it just short of the comprehensive anchor 5.

4 / 5

Completeness

Explicitly answers both 'what' (reviewing a set of changes before they merge) and 'when' ('Use when...'; 'Activates for...') with concrete trigger phrases, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Quotes natural user phrases verbatim — '"review this PR", "is this safe to merge", "what is the blast radius of these changes", or "did I miss anything"' — covering synonyms and paraphrases a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche tied to a Repowise-indexed repository with distinct review-specific triggers, posing minimal overlap risk with other skills.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
repowise-dev/repowise
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.