CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

78%

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/gate-worktree-git-safety/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 dense, high-signal rulebook: every section pairs concrete project invariants with named regression tests, and structure is appropriate for a short no-bundle skill. The only recurring weakness is sentence-level density — several bullets are overlong single sentences that could be split for readability without adding tokens.

DimensionReasoningScore

Conciseness

Nearly every token carries project-specific facts Claude could not know (internal package names, issue numbers, test names) with zero padding or explanation of known concepts, which is efficient. A few bullets are 100+ word single sentences with stacked clauses (e.g., the worktree_roots bullet) that could be tightened, keeping it below the lean-everywhere anchor.

4 / 5

Actionability

Concrete, executable guidance throughout — 'Route every gate git call through git.Run', 'Edit internal/skill/skill.go, then run make skill', 'use git.RunBare', 'route through the shared prSelector' — with specific files, commands, and fail-closed rules. Some bullets state policy without an executable command, so it is not fully copy-paste-ready.

4 / 5

Workflow Clarity

This is a per-subsystem rulebook rather than a multi-step workflow, and each section names its regression tests (e.g., 'Regressions: TestPostReceiveHook_ResolvesAbsoluteGateDir'), supplying most validation checkpoints. No fix-and-retry loop is spelled out, so it stops short of the explicit-validation anchor. The destructive-operations cap is not triggered: the skill explicitly mandates refusal and fail-closed behavior for the risky operations it governs.

4 / 5

Progressive Disclosure

The ~28-line body is organized into clear bolded section headers with no bundle files needed, and its single external reference (docs/src/content/docs/reference/global-config.md) is clearly signaled and one level deep — matching the under-50-line, well-organized exception.

5 / 5

Total

17

/

20

Passed

Description

70%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.

A trigger-first description with strong, specific domain terms and low conflict risk, but it never tells the reader what the skill does with those areas. Adding a 'what' clause (e.g., the invariants and regression tests to apply) would raise completeness substantially.

Suggestions

Add a leading 'what' clause stating what the skill provides, e.g., 'Apply safety invariants and regression checks when changing...'.

Include natural synonyms a user might say, such as 'worktree root', 'pre-receive/push hook', or 'gate repo' alongside the current terms.

State the outcome of using the skill (e.g., 'so marker removal, cwd changes, and direct pushes cannot bypass refusal') so the 'what' is explicit rather than implied.

DimensionReasoningScore

Specificity

The description enumerates five concrete areas ('recursive gate containment, run worktree placement, bare-gate Git calls, GitHub PR targeting, or post-receive hooks'), matching the several-specific-actions anchor, but it lists trigger topics rather than the actions the skill performs, so coverage is not comprehensive.

4 / 5

Completeness

The 'when' is explicit ('Use when changing...'), but the 'what' is only weakly implied by the topic enumeration — the description never states what the skill actually provides (safety invariants and regression guidance for those areas), placing it between the only-'when' anchor and a fully complete one.

3 / 5

Trigger Term Quality

Terms like 'worktree placement', 'bare-gate Git calls', 'GitHub PR targeting', and 'post-receive hooks' are exactly the phrases a developer in this codebase would naturally say, giving good keyword coverage, but no synonyms or variations are offered to reach comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

Triggers are tied to named, niche subsystems (bare gate repos, post-receive hook gate path, worktree placement) that no other plausible skill would claim, giving a clear niche with minimal conflict risk.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

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.