gate-worktree-git-safety

Use when changing recursive gate containment, run worktree placement, bare-gate Git calls, GitHub PR targeting, or post-receive hooks.

Quality

74%

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/gate-worktree-git-safety/SKILL.md

Quality

Content

68%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 an information-dense, actionable internal reference with concrete symbols and commands, well sectioned for its length. Its main weakness is the absence of explicit validation/feedback loops for the destructive Git and PR operations it governs, which caps workflow clarity.

Suggestions

Add explicit validation checkpoints for the destructive operations (e.g. 'Before pushing, run the listed Regression tests; only proceed when green') to lift workflow clarity above 3.

Promote the bold section labels to real markdown headers (## Filesystem and Paths) to improve navigation and scanability.

Split the longest run-on bullets into a directive line plus a short rationale so each rule is faster to apply.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (named packages, test symbols, issue numbers) with every clause carrying specific information, though several run-on bullets pack rationale that could be trimmed slightly.	4 / 5
Actionability	Concrete directives name exact symbols and commands ('Route every gate git call through git.Run', 'Edit internal/skill/skill.go, then run make skill', 'use git.RunBare'), giving mostly executable guidance with minor gaps and no copy-paste block.	4 / 5
Workflow Clarity	The body is a topic-organized ruleset, not a sequenced workflow, and although it governs destructive Git/push/PR operations it lacks explicit validate-then-proceed checkpoints; 'Regressions:' lines act only as implicit verification, capping this at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	Content is well organized into five labeled sections with no external references needed (under 50 lines), but sections use bold-text labels rather than real markdown headers, leaving minor navigation gaps versus the top anchor.	4 / 5
	Total	15 / 20 Passed

Description

71%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 is specific, explicit about when to invoke, and highly distinct, but its trigger terms lean heavily on internal jargon without natural-language synonyms. It answers both 'what' and 'when' though folded into a single 'Use when' clause.

Suggestions

Add natural-language synonyms alongside the jargon (e.g. 'worktree setup/placement', 'Git operations on bare repos') so the triggers match phrasings a user would actually say.

Separate the 'what' from the 'when' — state the capability first, then the 'Use when...' trigger clause — to reach the top completeness anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('changing recursive gate containment, run worktree placement, bare-gate Git calls, GitHub PR targeting, or post-receive hooks') rather than vague language, though they are domain-jargon named rather than verb-led.	4 / 5
Completeness	An explicit 'Use when' clause supplies the 'when' and the enumerated operations supply the 'what', but the two are merged into one clause rather than stated as independently as the 5-anchor example.	4 / 5
Trigger Term Quality	Relevant keywords exist (worktree, Git, GitHub PR, post-receive hooks) but they are internal jargon with no natural synonyms or variations a user would commonly say, fitting 'some relevant keywords but missing common variations.'	3 / 5
Distinctiveness Conflict Risk	The triggers are an extremely specific internal niche (recursive gate containment, bare-gate Git, post-receive hook path resolution) with minimal overlap risk against any general skill.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: kunchenguid/no-mistakes
Path: .agents/skills/gate-worktree-git-safety/SKILL.md
Commit: 14e8dd1

Reviewed: 5 days 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.