CtrlK
BlogDocsLog inGet started
Tessl Logo

review-sweep

Mine review comments for broader diff-wide fixes instead of handling each line in isolation

61

Quality

73%

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 ./.agents/skills/review-sweep/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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 content is an exemplary instruction-only skill: tightly written, immediately actionable, with a clear workflow and explicit decision boundaries between safe and unsafe sweeping. The only meaningful gap is the absence of an explicit error-recovery/feedback loop in the workflow for the batch application of fixes.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no concept explanations, no padding, and every rule ('Keep the blast radius proportional to confidence', 'Anything you cannot explain in one sentence') earns its place. It matches the 'lean and efficient; every token earns its place' anchor rather than the 4 anchor, which would require trimmable over-explanation.

5 / 5

Actionability

For an instruction-only skill the guidance is fully actionable: a concrete classification scheme (safety, docs clarity, code-shape, test robustness, architecture), an explicit clear/maybe/not-apply split, and a deterministic apply rule ('Apply only the clear set automatically'). It matches 'fully executable... specific examples cover the common cases' via the enumerated good/bad sweep targets rather than the 4 anchor's 'minor gaps'.

5 / 5

Workflow Clarity

The 8-step workflow is clearly sequenced and includes a verification checkpoint ('Verify the changed seam directly'), so the batch-operation cap of 3 does not apply. It falls short of 5 because there is no explicit error-recovery feedback loop (e.g. what to do if verification of the changed seam fails), matching 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

This is a single-file, judgment-style skill with well-organized sections (Goal, Core Rules, Good/Bad Sweep Targets, Workflow, Output Rule); no bundle files exist and none are needed, so nothing is inlined that belongs in a separate file and there are no nested references. It matches the well-organized-sections ideal rather than the 4 anchor, which requires organization gaps.

5 / 5

Total

19

/

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 communicates a clear and genuinely specific strategy, but it omits an explicit 'when to use' trigger clause and lacks natural keyword synonyms, which pulls down completeness and trigger-term quality. Adding a 'Use when...' sentence with common phrasings like 'code review' or 'PR feedback' would raise it substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when handling PR review feedback, addressing code review comments, or fixing issues across a pull request diff.'

Include natural synonyms such as 'code review', 'PR feedback', 'pull request', and 'review thread' so users' phrasing matches the description.

Name one or two more concrete actions (e.g. 'extract the underlying rule from each comment and apply it across the diff') to broaden coverage without adding fluff.

DimensionReasoningScore

Specificity

"Mine review comments for broader diff-wide fixes" names the domain (review comments) and one concrete strategy, but does not enumerate several distinct actions, matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is above a 2 because the stated action is specific rather than generic, and below a 4 because no list of multiple concrete capabilities is present.

3 / 5

Completeness

The 'what' is clear ("Mine review comments for broader diff-wide fixes"), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3. Not a 4 because the 'when' is at best weakly implied by "instead of handling each line in isolation".

3 / 5

Trigger Term Quality

Natural phrases like "review comments" and "diff-wide fixes" are present, but common variations users would say ("code review", "PR feedback", "pull request comments", "address review comments") are missing, matching 'some relevant keywords but missing common variations or synonyms'. Not a 4 because keyword coverage is noticeably incomplete.

3 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche (infer rules from review comments and sweep the whole diff rather than fixing lines in isolation), with only minor overlap risk against general code-review skills. Not a 5 because the phrasing does not state distinctive triggers that fully separate it from adjacent review/fix skills.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
udecode/plate
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.