CtrlK
BlogDocsLog inGet started
Tessl Logo

local-clawsweeper-review

Run local ClawSweeper exact-item or committed-range reviews without GitHub mutation.

64

Quality

75%

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/local-clawsweeper-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 highly actionable with copy-paste commands and a well-sequenced, validated workflow including explicit safety guards and a closeout checklist. It is efficient and well-organized, with only minor over-explanation and a single-file structure that is appropriate but could offload some setup detail.

DimensionReasoningScore

Conciseness

The body is dense with executable commands and assumes Claude knows git/pnpm/codex, with only minor over-explanatory asides ('Device auth is the simplest shareable setup'); fits the score-4 anchor of efficient content with minor trims possible, not a 5 due to those asides.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands covering the common cases (exact-item, issue with --target-dir, pre-PR --local-range, smoke tests) plus auth snippets, matching the score-5 anchor.

5 / 5

Workflow Clarity

Sequenced sections from Locate through Closeout with explicit validation checkpoints (git status --short guards, dirty-checkout prohibitions) and an explicit Closeout checklist, matching the score-5 anchor for clear sequences with explicit validation and checklists.

5 / 5

Progressive Disclosure

No bundle files exist; the single ~170-line file is well-organized into clearly labeled sections with no nested references, fitting the score-4 anchor of good structure with minor organization gaps, but the dual PowerShell/POSIX first-time-setup blocks could be offloaded to keep it from a clean 5.

4 / 5

Total

18

/

20

Passed

Description

62%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 names concrete actions and a clearly distinct, branded niche, but it omits any explicit 'when to use' trigger guidance and relies on product jargon over natural user vocabulary, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'when' clause, e.g. 'Use when you want a read-only local ClawSweeper review before submitting, updating, or re-reviewing an issue or PR.'

Surface natural user-facing synonyms such as 'local review', 'dry-run review', or 'preview ClawSweeper output' alongside the product terms.

Optionally enumerate the concrete actions (exact-item review, committed-range review) more explicitly to push specificity toward 5.

DimensionReasoningScore

Specificity

Names the tool and two concrete review modes (exact-item, committed-range) plus a no-mutation constraint, matching the score-4 anchor of several specific actions with minor gaps; not a 5 since it is one action in two modes rather than comprehensive coverage.

4 / 5

Completeness

The 'what' is clear (run local read-only ClawSweeper reviews) but there is no 'Use when...' or equivalent explicit 'when' trigger, which per the guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Has some natural terms (local, reviews, GitHub) but leans on product jargon (ClawSweeper, exact-item, committed-range) and misses common synonyms like preview, dry run, or check; fits the score-3 anchor of relevant keywords missing common variations.

3 / 5

Distinctiveness Conflict Risk

The product-specific ClawSweeper name plus read-only/local constraint carves a clear niche with minimal overlap risk, matching the score-5 anchor of a distinct niche with minimal conflict.

5 / 5

Total

15

/

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
openclaw/clawsweeper
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.