worktree

为代码、脚本、API 与第一方执行面创建隔离 Git worktree，并配置 Redis 6398；classifier 放行的 co-creation docs direct push 不进入本流程。

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

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 a strongly actionable, well-sequenced operational workflow with real validation gates and safety checklists — its strongest dimensions. Its weaknesses are repetition and inline incident narrative that inflate token cost, and a monolithic single-file layout with a dead reference where progressive disclosure into bundle files is warranted.

Suggestions

Split the multi-worktree OFFSET table, sidecar-handling details, and Thread-Context footer spec into a reference file (e.g. references/port-offset.md) linked from a short summary section, reducing SKILL.md to a lean overview.

Remove or repair the dangling "详细设计见 *(internal reference removed)*" pointer — either delete it or point it at a real file path in the bundle.

Consolidate the cat-cafe-runtime / 6399 / 3003-3004 warnings (currently repeated in 目录位置, Redis 隔离, and 安全核查) into one compact guardrail section, and compress the dated 2026-07-09 incident anecdote into a one-line rationale.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean operational rules and commands with no padding explaining concepts Claude already knows, but it could be tightened: the cat-cafe-runtime / 6399 warnings repeat across three sections (目录位置, Redis 隔离, 安全核查) and the dated incident anecdote ("教训（2026-07-09 intake #2816 连环事故）…366 行恢复补丁全部作废") is inline justification rather than instruction, fitting the 'mostly efficient but could be tightened' anchor.	3 / 5
Actionability	Guidance is fully executable throughout: copy-paste commands ("git worktree add ../cat-cafe-{feature-name} -b feat/{feature-name}"), complete .env heredocs, a concrete sync gate ("AHEAD=$(git rev-list --count origin/main..main)"), the gh pr two-step check, and a full OFFSET port-derivation table; this matches the 'copy-paste ready, covers the common cases' anchor.	5 / 5
Workflow Clarity	The multi-step process is clearly sequenced (recall → main sync check → in-flight PR check → create → configure → verify → merge cleanup) with explicit validation checkpoints and feedback loops: the ahead/behind=0 gate with corrective steps, the Redis URL verification ("必须是 redis://localhost:6398"), and the two 安全核查 checklists that guard the destructive cleanup (worktree remove / branch -d) — matching the top anchor including checklists for complex processes.	5 / 5
Progressive Disclosure	Section headers give the ~250-line body reasonable structure, but substantial content that belongs in separate files is inlined (the WORKTREE_PORT_OFFSET derivation table, sidecar handling details, Thread-Context footer spec) and there is a dangling reference — "详细设计见 (internal reference removed)" — pointing at nothing (no references/ directory exists in the bundle), fitting the 'some structure but content that should be separate is inline' anchor.	3 / 5
	Total	16 / 20 Passed

Description

53%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 has a clear 'what' and a distinctive niche (worktree isolation + Redis 6398), but it lacks any positive 'use when' trigger guidance and leans on project-internal jargon that limits natural keyword coverage. It reads as a scope boundary statement rather than a discovery-oriented description.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g. 开始任何非 trivial 的功能开发、需要隔离分支/隔离 Redis 环境时使用), which would raise completeness above the cap of 3.

Include natural trigger variations users would actually say — e.g. "branch isolation", "隔离分支", "isolate changes" — alongside the existing keywords, instead of relying on the separate triggers field.

Replace or briefly gloss project-internal jargon ("第一方执行面", "classifier 放行的 co-creation docs") so the boundary statement is interpretable without external context.

Dimension	Reasoning	Score
Specificity	The description names its domain (代码、脚本、API 与第一方执行面) and exactly two concrete actions ("创建隔离 Git worktree" and "配置 Redis 6398"), matching the anchor for 1-2 concrete actions; it omits the many other capabilities the body covers (sync checks, PR collision checks, port offsets, cleanup), so it does not reach the 'several specific actions' anchor.	3 / 5
Completeness	The 'what' is clear (create an isolated Git worktree and configure Redis 6398) but there is no positive 'Use when...' clause — only a negative exclusion ("co-creation docs direct push 不进入本流程"); per the judging guidelines a missing when-clause caps completeness at 3, and an exclusion alone does not qualify as the explicit trigger guidance needed for 4.	3 / 5
Trigger Term Quality	Relevant keywords are present ("Git worktree", "Redis", "代码", "脚本", "API") but they sit alongside project-internal jargon ("第一方执行面", "classifier 放行") and common natural variations (e.g. "branch isolation", "isolate changes") are missing, fitting the 'some relevant keywords but missing variations' anchor rather than the good-coverage anchor.	3 / 5
Distinctiveness Conflict Risk	The pairing of worktree isolation with a specific Redis port (6398) carves out a clear niche that is unlikely to trigger the wrong skill, though it could still overlap with a generic git-worktree skill; this fits 'mostly distinct; minor overlap risk' better than the anchor 5, which would require distinct trigger phrases stated in the description itself.	4 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/worktree/SKILL.md
Commit: 61389cc

Reviewed: 2 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.