CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

local-clawsweeper-review

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

Quality

76%

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.

A strong operational skill body: concrete, executable commands dominate, the workflow is well sequenced with real validation checkpoints and error-recovery loops, and the closeout checklist guards against the mutation risks it flags upfront. The only weaknesses are minor repetition and setup/auth detail that could be moved to a reference file.

DimensionReasoningScore

Conciseness

The body is dense, imperative, and command-first with no explanations of concepts Claude already knows. Minor repetition (e.g. '--target-dir' guidance repeated across 'Target Checkout Modes', a few hedging sentences around diagnostics and the dist entrypoint) keeps it just below the lean anchor.

4 / 5

Actionability

Commands are copy-paste ready throughout — from 'corepack enable' / 'pnpm install' to 'pnpm run review -- --local-only --item-number <pr-number>', per-shell auth login snippets, and the git clean-checkout sequence — and cover the common cases (issue vs PR, dirty checkout, auth failure, smoke run). The single implicit placeholder '<artifact-dir>' is inferable from 'artifacts/local-review-<pr-number>/'.

5 / 5

Workflow Clarity

A clear sequence (locate, setup, run, read artifact, closeout) with explicit validation checkpoints ('git status --short' before use, clean-checkout guards, '--ff-only' pull) and error-recovery feedback loops (auth failure stops with the setup command; runtime failure reports the artifact path and stderr). The Closeout section acts as a final checklist, matching the top anchor.

5 / 5

Progressive Disclosure

Well-organized single-file skill with clear sections and no nested or buried references. At ~190 lines with no reference split, first-time setup/auth detail (device auth, per-shell API-key handling, dist entrypoint notes) is inline material that could live in a one-level-deep reference file, so it fits 'good structure with minor organization gaps' rather than the fully split top anchor.

4 / 5

Total

18

/

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 states a concrete, distinctive capability but omits any trigger guidance, which is its main weakness and caps completeness. Adding an explicit 'Use when...' clause with natural phrasing users would actually say would lift both completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a local, read-only, or pre-submission ClawSweeper review before posting, updating, or re-reviewing an issue or PR.'

Include natural trigger variations users would say — 'dry-run review', 'review locally before submitting', 'without posting to GitHub' — to improve trigger-term coverage.

State the distinction from non-local reviewing explicitly (e.g. 'for runs that must not touch GitHub') so it does not trigger for ordinary ClawSweeper PR reviews.

DimensionReasoningScore

Specificity

'Run local ClawSweeper exact-item or committed-range reviews' names the domain and one concrete action with two modes, but does not list several distinct specific actions. It sits at the 'domain plus 1-2 concrete actions' anchor rather than 'several specific actions'.

3 / 5

Completeness

The 'what' is clear (run local exact-item or committed-range reviews without GitHub mutation), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

'local' and 'reviews' are natural terms users would say, but common variations such as 'read-only', 'dry-run', 'pre-submission review', or 'before posting to GitHub' are missing. That matches 'some relevant keywords but missing common variations' rather than good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

The niche tool name 'ClawSweeper' plus 'local' and 'without GitHub mutation' makes it mostly distinct with minimal conflict risk. It falls short of the top anchor because a generic request like 'review my PR with ClawSweeper' could overlap a closely related non-local review skill.

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

openclaw/clawsweeper

Path

.agents/skills/local-clawsweeper-review/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.