CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-worktree-clean

Use when the user wants to audit local git worktrees against origin/x, choose by number or A, and decide whether stale worktree directories, already-merged worktrees, or no-delta worktrees can be cleaned up. Triggers on "worktree clean", "worktree 合并到 x", "检测哪些 worktree 已进 x".

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 concise, fully actionable with executable commands, and structured as a clear five-step workflow with explicit validation and confirmation gates around a destructive operation. Progressive disclosure is strong, offloading mechanics to one bundled script.

DimensionReasoningScore

Conciseness

Lean body with no padding or explanation of concepts Claude already knows; rules, steps, and the output contract each earn their place and assume competence.

5 / 5

Actionability

Every step has copy-paste-ready commands (list, check with 1/1,3/A variants, cleanup-candidates, git worktree remove, rm -rf) covering the common selection cases, plus concrete reply-format prompts for the user.

5 / 5

Workflow Clarity

Five clearly sequenced steps with explicit validation checkpoints — fetch origin/x before check, user confirms before any deletion, sandbox-approval rerun loops, and a hard guardrail against concluding from merge commits alone.

5 / 5

Progressive Disclosure

Bulk implementation is correctly externalized to a single one-level script referenced consistently; body sections are well organized. Slightly below 5 because the result-vocabulary glossary and output contract are inline rather than in a separate reference, though this is reasonable for an ~80-line file.

4 / 5

Total

19

/

20

Passed

Description

92%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, complete, and distinct: it states concrete capabilities, provides an explicit 'Use when...' trigger with natural phrases, and carves out a clear niche. Minor room to add a couple more common trigger synonyms.

DimensionReasoningScore

Specificity

Names the domain plus multiple concrete actions — 'audit local git worktrees against origin/x', 'choose by number or A', and decide cleanup for 'stale worktree directories, already-merged worktrees, or no-delta worktrees' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Opens with an explicit 'Use when...' clause stating both what the skill does and when to trigger it, with concrete trigger phrases — matching the anchor for clearly answering both what and when.

5 / 5

Trigger Term Quality

Includes natural triggers a user would say ('worktree clean', 'worktree 合并到 x', '检测哪些 worktree 已进 x') but is missing a few common variants such as 'prune worktrees' or 'remove worktree'.

4 / 5

Distinctiveness Conflict Risk

Targets a specific niche (auditing git worktrees against origin/x by code content) with distinct bilingual triggers and low overlap risk against general git/cleanup skills.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
OneKeyHQ/app-monorepo
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.