clawpatch

Operate Clawpatch for semantic feature mapping, automated review, explicit finding fixes, revalidation, reports, and state recovery.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/clawpatch/SKILL.md

Quality

Content

77%

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 well-sequenced, validation-checked workflows specific to Clawpatch. Its weaknesses are length (with some redundancy) and a monolithic structure that does not progressively disclose reference material into separate files.

Suggestions

Collapse the two forced re-review shell loops in "Force Re-Review All Features" into a single recoverable JSONL version to remove redundancy.

Move the long Command Reference and Mapping Notes into a separate reference file (e.g. references/command-reference.md) with a one-line pointer from SKILL.md to improve progressive disclosure and reduce inline bulk.

Trim prose around provider controls and mapping notes to the rules Claude must follow, keeping only the executable commands and the hard constraints.

Dimension	Reasoning	Score
Conciseness	Mostly tool-specific information Claude needs, but the body is long and includes redundancy such as two near-duplicate forced re-review shell loops, so it could be tightened.	2 / 3
Actionability	Dense with concrete, executable commands (e.g. `clawpatch review --json`, `clawpatch fix --finding <findingId> --json`, jq-based JSONL loops) that are copy-paste ready.	3 / 3
Workflow Clarity	Multi-step processes are sequenced with explicit checkpoints: recoverable JSONL recording for the batch re-review, "Always inspect run.errors" after review, and a verification closeout that runs typecheck/lint/test before declaring done.	3 / 3
Progressive Disclosure	Sections are well-organized and external docs are clearly signaled, but the skill is a single ~400-line monolithic file with no bundle files; the long command reference and mapping notes are inline material that could be split out.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 is specific and clearly anchored to a distinct named tool, but it answers only "what" without an explicit "when to use it" trigger clause, and mixes natural terms with technical jargon. Adding a "Use when..." clause and more natural command-style phrasings would raise it.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for Clawpatch, automated code review, finding reports, or a forced re-review of existing Clawpatch feature records."

Replace jargon like "semantic feature mapping" and "state recovery" with terms users would naturally say, and include common variations such as "clawpatch review" and "clawpatch fix".

Lead with the primary trigger ("Clawpatch" / ".clawpatch") so the description reads as a natural user phrase rather than a capability list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "semantic feature mapping, automated review, explicit finding fixes, revalidation, reports, and state recovery" — matching the anchor that names several specific actions.	3 / 3
Completeness	Clearly answers what the skill does, but has no explicit "Use when..." trigger clause; per the judging guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Includes the core natural term "Clawpatch" plus action words (review, fix, reports), but leans technical with "semantic feature mapping" and "state recovery" and omits common command-style variations like "clawpatch review".	2 / 3
Distinctiveness Conflict Risk	Centers on the named tool "Clawpatch," giving it a clear niche with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/clawpatch/SKILL.md
Commit: 45116fd

Reviewed: about 14 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.