worktree

创建 Git worktree 隔离开发环境，含 Redis 6398 安全配置。 Use when: 开始任何代码修改、新功能开发、bug fix。 Not for: 纯文档修改（≤5 行）、不涉及代码/脚本/API/第一方执行面的讨论。 Output: 隔离的 worktree + 正确的 Redis/环境配置。

Quality

83%

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

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable with strong validation checkpoints, but verbose and monolithic — it leans on internal incident IDs Claude can't expand and keeps substantial reference-grade material inline rather than in bundled files.

Suggestions

Move the multi-worktree port-offset table, WORKTREE_PORT_OFFSET derivation, and sidecar handling into a references/ file (e.g. PORT-OFFSET.md) and link to it from SKILL.md to improve progressive disclosure and reduce inline bulk.

Replace or inline-resolve the opaque incident/feature IDs (F073, F102, F182, F193, LL-015) with a one-line plain-language summary, since Claude cannot look them up; this trims tokens and removes dead context.

Consolidate the repeated 🔴 prohibitions into a single 'Forbidden actions' list to cut redundancy without losing the safety signal.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but padded by repeated 🔴 warnings and opaque internal incident/feature IDs (F073, F102, F182, F193, LL-015) that Claude cannot resolve, and a large port-offset table that could be tightened.	2 / 3
Actionability	Fully executable bash snippets, a concrete .env template, exact port numbers, and copy-paste-ready validation commands (pnpm test, pnpm check:worktree-port-offset).	3 / 3
Workflow Clarity	Clear sequenced flow (recall → sync check → create → verify → cleanup) with explicit validation checkpoints (ahead=0/behind=0, baseline test, pre-remove branch-merged check) and a safety checklist covering destructive ops.	3 / 3
Progressive Disclosure	Well-sectioned and single-level (no nested references), but monolithic: the multi-worktree port-offset table, sidecar design, and commit-footer details are inline content that could be split into reference files, and the one design reference is explicitly removed.	2 / 3
	Total	10 / 12 Passed

Description

90%Weight 40%Scale 1-3

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 specific, well-scoped description with explicit trigger guidance and exclusions; its only weakness is that it describes one main capability plus configuration rather than a broad set of actions.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions — "创建 Git worktree 隔离开发环境，含 Redis 6398 安全配置" — but lists essentially one capability plus its config rather than multiple distinct actions, so it is not a comprehensive multi-action list.	2 / 3
Completeness	Explicitly answers what ("创建 Git worktree...含 Redis 6398 安全配置") and when ("Use when: 开始任何代码修改、新功能开发、bug fix"), plus a "Not for:" exclusion clause.	3 / 3
Trigger Term Quality	Natural phrases a user would say are covered: triggers list "开始开发", "新 worktree", "开 worktree", and the body adds "新功能开发", "bug fix".	3 / 3
Distinctiveness Conflict Risk	A clear niche (git worktree isolation with Redis port safety) with distinct triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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: 80782c5

Reviewed: 11 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.