CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

worktree

Use when: 创建代码/脚本/API工位或收尾。Not for: docs直推、代清其他owner。Output: 隔离worktree(Redis6398)、实际移除工位的released回执或具名retained回执。

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/worktree/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 exceptionally actionable and workflow-safe: exact commands, port tables, dual-check PR pre-flight, and validated checklists for destructive operations. Its weaknesses are length and offloading — tool-internal scanner/reaper semantics are inlined in a 330-line single file with a dangling reference instead of being split into one-level-deep reference files.

Suggestions

Move the reaper/scanner/ledger internals (the 出生来源与 PR 关联 prose and the trim retry semantics) into a one-level-deep reference file, keeping only the owner-facing rules in SKILL.md.

Replace or repair the '*(internal reference removed)*' stub with a real reference path or delete the sentence, since a dangling pointer misleads navigation.

Trim defensive edge-case narration (EXDEV behavior, multi-round retry accounting) to the one-line rule plus a pointer, cutting the body closer to a lean overview.

DimensionReasoningScore

Conciseness

Most content is non-obvious project-specific state (port tables, Redis boundaries, finish/retain semantics) that Claude cannot know, and commands are given without padding, so it is not score 2. But sections like the 出生来源与 PR 关联 scanner paragraphs ('API 每五分钟扫描...不伪造原 finish 的完成回执') and the trim/reaper retry semantics describe tool-internal behavior an executing agent does not need, matching 'mostly efficient but includes some unnecessary explanation or could be tightened'.

3 / 5

Actionability

Every operation ships copy-paste-ready commands: the worktree:new invocation with flags, .env heredocs with exact values, the port-offset derivation table, finish/retain/check invocations, and diagnostic commands like 'pnpm check:worktree-port-offset'. Placeholders like {feature-name} are standard templates, and edge cases (restore, sandbox policy, stash footer) each get an exact command or literal text to write.

5 / 5

Workflow Clarity

The lifecycle is explicitly sequenced (recall → main sync check with ahead/behind computation → in-flight PR two-step check → create → env → verify → finish) with explicit validation checkpoints throughout: Redis isolation verification, the 安全核查 checklists before creation and cleanup, --check receipt verification for destructive finish, and error-recovery guidance (what to do when out of sync, when archive/delete is interrupted). Destructive removal is guarded by owner/protection/process checks, satisfying the feedback-loop requirement.

5 / 5

Progressive Disclosure

Headers are clear and the document is navigable, but it is a ~330-line monolith with no bundle files: content that clearly belongs in a separate reference (reaper internals, scanner/ledger behavior, port-offset deep design) is inlined, and one pointer is a dead stub ('详细设计见 *(internal reference removed)*'). This matches 'some structure but content that should be separate is inline'; it is not score 2 because sections are well-labeled rather than a structureless wall.

3 / 5

Total

16

/

20

Passed

Description

62%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 follows a strong Use when / Not for / Output structure with explicit positive and negative triggers, which is better than most vague descriptions. However, it is written in telegraphic mixed-language project jargon that limits natural trigger matching and compresses the 'what' to fragments, keeping it in the middle-to-good range rather than excellent.

Suggestions

State the core capabilities as concrete third-person actions (e.g. 'Creates an isolated git worktree with a dedicated Redis port, and verifies release or retention at task completion') instead of the compressed '创建代码/脚本/API工位或收尾' fragment.

Add natural-language trigger phrases and synonyms users would actually say ('git worktree', 'set up a dev worktree', 'clean up / finish a worktree') to the description so it matches score-5 trigger coverage.

Briefly name the main sub-operations (multi-worktree port offsets, retain-with-expiry, restore from archive) so the 'what' is comprehensive rather than implied.

DimensionReasoningScore

Specificity

The description names the domain ("创建代码/脚本/API工位或收尾") and a couple of concrete outputs ("隔离worktree(Redis6398)", "released回执或具名retained回执"), which matches the '1-2 concrete actions, not comprehensive' anchor. It is not score 4 because the actions are compressed into telegraphic project jargon and coverage of the actual workflow (port offsets, retention, restore) is thin; not score 2 because the outputs and scope are genuinely concrete, not generic.

3 / 5

Completeness

Both halves are explicitly present: "Use when: 创建代码/脚本/API工位或收尾" plus a negative boundary "Not for: docs直推、代清其他owner", and the "Output:" clause says what the skill produces. It falls short of the 5 anchor because the 'what' is a terse jargon fragment rather than clearly stated capabilities with concrete trigger phrases, and the 'when' leans on project-specific vocabulary.

4 / 5

Trigger Term Quality

Relevant keywords exist ("worktree", "创建", "收尾", "docs直推"), but the terms are project-internal mixed-language jargon and miss common natural variations (e.g. 'git worktree', 'new branch', 'clean up worktree'), matching 'some relevant keywords but missing common variations or synonyms'. Not 4 because a user outside this project would not naturally say most of these phrases; not 2 because 'worktree' and the create/finish framing are terms real users would use.

3 / 5

Distinctiveness Conflict Risk

The worktree lifecycle niche is distinct and the explicit "Not for:" exclusions (docs direct-push, clearing other owners' worktrees) reduce overlap with documentation or cleanup skills. Minor overlap risk remains with generic git-workflow skills because the description presumes this project's tooling vocabulary, so it does not fully reach the 'clear niche with distinct triggers; minimal conflict risk' anchor.

4 / 5

Total

14

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 2 missing, 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository

zts212653/clowder-ai

Path

cat-cafe-skills/worktree/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.