clawsweeper-status

ClawSweeper status: URLs, workflow health, active workers, ops snapshot.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/clawsweeper-status/SKILL.md

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, highly actionable, and well-structured: it points to a real bundled script, defines an explicit output contract, names bounded data sources, and provides interpretation rules with edge-case handling. The only weakness is the machine-specific absolute script path, which limits portability.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational — script path, options, output contract, data sources, and interpretation rules with no concept explanations or padding — matching anchor 3 ("every token earns its place"). Not 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	It gives the exact executable script path and concrete flags (--hours, --repo, --limit) with comments, plus a precise output contract and named API data sources, matching anchor 3 ("Fully executable code/commands; copy-paste ready"). Not 2 because there is no pseudocode and no missing key details.	3 / 3
Workflow Clarity	The sequence — run script, report the five named sections, use bounded data sources, apply interpretation rules — is unambiguous with an explicit empty-result handler ("none found in window") and a disagreement-checkpoint for stale counts, matching anchor 3. Not 2 because checkpoints are present rather than implicit.	3 / 3
Progressive Disclosure	The skill is a short SKILL.md organized into clear sections (Quick Start, Output Contract, Efficient Data Sources, Interpretation) pointing one level deep to the real bundled scripts/clawsweeper-status.sh, matching the simple-skill scoring note for a 3. Not 2 because content is well-organized and references are not nested.	3 / 3
	Total	12 / 12 Passed

Description

50%

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 clearly names its domain and the facets it surfaces, but uses abstract categories rather than concrete actions and omits any explicit "Use when..." trigger guidance. It is functional but would benefit from explicit trigger phrasing and more action-oriented verbs.

Suggestions

Add an explicit trigger clause, e.g. "Use when checking ClawSweeper workflow health, Codex worker capacity, or recent review/merge activity."

Replace abstract nouns ("URLs, workflow health, active workers, ops snapshot") with concrete actions a user would recognize, e.g. "Report ClawSweeper worker status, recent merged/reviewed PR URLs, and closed-item activity."

Include natural keyword variations users might say (e.g. "ClawSweeper status", "worker capacity", "review queue") to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Quotes "ClawSweeper status: URLs, workflow health, active workers, ops snapshot" name the domain and several facets, but these are abstract categories rather than concrete actions (no verbs like 'extract' or 'merge'), matching anchor 2. Not 1 because it is not vague, and not 3 because it lacks multiple specific concrete actions.	2 / 3
Completeness	The description states what it surfaces ("URLs, workflow health, active workers, ops snapshot") but has no "Use when..." trigger guidance; per the judging guidelines a missing explicit trigger caps completeness at 2. Not 1 because the 'what' is present.	2 / 3
Trigger Term Quality	"ClawSweeper status" is a natural phrase a user would say, but "active workers" and "ops snapshot" lean toward jargon and common variations are missing, matching anchor 2. Not 1 because some natural keywords exist, and not 3 because coverage is incomplete.	2 / 3
Distinctiveness Conflict Risk	The named system "ClawSweeper" gives it a niche, but generic terms like "ops snapshot", "workflow health", and "status" could overlap with a generic monitoring skill, matching anchor 2. Not 1 because it is not purely generic, and not 3 because it lacks the crisp trigger framing of the anchor 3 example.	2 / 3
	Total	8 / 12 Passed

Validation

100%

Warnings & errors only

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: steipete/agent-scripts
Path: skills/clawsweeper-status/SKILL.md
Commit: bb36883

Reviewed: about 15 hours ago

Table of Contents

Discovery Implementation Validation

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.