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

61%

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 highly actionable and well-sequenced with strong validation checkpoints and checklists, but it is a long monolithic file with no progressive disclosure into bundle files and one inert internal reference. Splitting reference material into separate files and resolving the removed reference would improve navigation.

Suggestions

Move the detailed multi-worktree port-offset tables and sidecar design into a dedicated reference file under references/ and link to it one level deep, reducing the main file length.

Resolve or remove the dangling "(internal reference removed)" placeholder so navigation does not dead-end.

Trim narrative incident lessons (e.g., the intake #2816 backstory) to a one-line caution so the body stays operationally dense.

Dimension	Reasoning	Score
Conciseness	Mostly operational and command-dense with little over-explanation of basic git concepts, but several narrative sections (the intake #2816 incident lesson, browser/port guard backstory) could be trimmed without losing actionability.	3 / 5
Actionability	Provides fully executable, copy-paste-ready bash commands throughout (git worktree add, env -u NODE_ENV pnpm install, .env heredocs, gh pr list/diff) plus concrete port-offset tables and derivation formulas covering the common cases.	5 / 5
Workflow Clarity	Clear sequenced workflow (sync check → PR preflight → create → install → env → verify → cleanup) with explicit validation checkpoints (ahead/behind echo, Redis 6399 production boundary, runtime guard), error-recovery feedback loops, and safety checklists.	5 / 5
Progressive Disclosure	Has clear section headers and structure, but it is a ~265-line monolithic SKILL.md with no real bundle files (references/, scripts/, assets/ absent) and a dangling "(internal reference removed)" link; bulk content like the full port-offset table is inlined rather than split out.	3 / 5
	Total	16 / 20 Passed

Description

46%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 concretely states the skill's purpose and boundary but omits any user-facing trigger guidance and leans on internal jargon (classifier, co-creation docs) rather than natural phrases a user would say. Adding a "Use when..." clause with natural synonyms would lift the weakest dimensions.

Suggestions

Add an explicit "Use when..." trigger clause (e.g., "Use when starting feature work, opening a new worktree, or beginning development") to satisfy the completeness/trigger requirements.

Replace or supplement internal jargon ("classifier 放行", "co-creation docs direct push", "第一方执行面") with natural user-facing terms and synonyms so users would naturally say them.

List the concrete capabilities more comprehensively (e.g., isolation, Redis port config, multi-worktree port offsets, PR-conflict preflight, cleanup) to raise specificity beyond two actions.

Dimension	Reasoning	Score
Specificity	Names the domain (code/scripts/API/first-party execution surfaces) and two concrete actions (create isolated git worktree, configure Redis 6398), but coverage is not comprehensive — only ~2 actions stated.	3 / 5
Completeness	Has a clear "what" (create isolated worktree + configure Redis 6398) but no explicit "when / Use when..." trigger guidance; per the rubric a missing Use-when clause caps completeness at 3.	3 / 5
Trigger Term Quality	Largely technical jargon ("first-party execution surface", "classifier", "co-creation docs direct push") with no natural user-facing trigger phrases or synonyms; only generic keywords like code/script/worktree appear.	2 / 5
Distinctiveness Conflict Risk	Targets a clear niche (git worktree isolation + Redis 6398 + first-party execution surfaces) with minimal overlap risk, though it lacks explicit distinct trigger phrasing to fully separate it from adjacent dev-workflow skills.	4 / 5
	Total	12 / 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: 090626a

Reviewed: 1 day 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.