open-source-teardown

明星开源项目拆解：从宣传/PPT/README 进入源码，验证真实架构、明星特性、算法含量、营销水分、可学习点和不 follow 的 tradeoff。 Use when: operator要求拆解热门 GitHub 项目、竞品 agent/runtime、外部 skill/tool 框架，或问“它到底有什么真本事/我们能学什么”。 Not for: 普通资料搜索（用 deep-research）、社区 issue/PR 运营（用 opensource-ops）、只需要架构头脑风暴（用 collaborative-thinking）。 Output: feature-discussions/YYYY-MM-DD-{project}-deep-dive/ 下的代码证据报告 + 对比结论 + 候选 lesson/skill。 GOTCHA: 不许只看 README 下判断；每个明星特性必须追到代码路径、状态突变点、反馈闭环和算法输入输出。

Quality

96%

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

92%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.

The body is concise, actionable, and clearly sequenced with built-in validation checkpoints. The one weakness is progressive disclosure: three refs/*.md paths are referenced but do not exist on disk.

Suggestions

Create the referenced refs/report-template.md, refs/teardown-method.md, and refs/user-mind-evaluation.md files (or remove the dangling links) so progressive disclosure resolves to real content.

Move the Common Mistakes table or the algorithm-peeling detail into a refs/ file if the body grows, keeping SKILL.md as a tight overview pointing one level deep.

Confirm each inline *(internal reference removed)* / refs link resolves to a tracked file before relying on it for navigation.

Dimension	Reasoning	Score
Conciseness	The body is lean, uses tables and tight lists, and assumes Claude's competence without explaining concepts it already knows.	3 / 3
Actionability	Provides concrete commands (git ls-files, find . -type d -empty, rg, git rev-parse HEAD) and an explicit claim→code-path tracing chain, giving copy-paste-ready process guidance.	3 / 3
Workflow Clarity	Steps 0–6 are clearly sequenced with hard-rule checkpoints acting as validation gates (e.g. 断一环就只能写…不能写闭环), plus a Common Mistakes table for error recovery.	3 / 3
Progressive Disclosure	The body signals references (refs/report-template.md, refs/teardown-method.md, refs/user-mind-evaluation.md) but no references/ directory or bundle files exist, so the referenced paths are broken rather than genuinely one level deep.	2 / 3
	Total	11 / 12 Passed

Description

100%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.

The description is specific, well-triggered, and clearly differentiated from sibling skills. It answers both what and when with concrete audit actions and a dedicated triggers list.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 验证真实架构、明星特性、算法含量、营销水分、可学习点和不 follow 的 tradeoff — a concrete audit pipeline rather than vague language.	3 / 3
Completeness	Explicitly states what the skill does (源码审计流程) and when to use it via Use when / Not for clauses, answering both what and when.	3 / 3
Trigger Term Quality	The triggers list covers natural phrases users would say, e.g. 拆解开源项目, 我们能学什么, codex cli 源码, marketing vs reality, with good variation.	3 / 3
Distinctiveness Conflict Risk	Clear niche (源码优先能力审计) with explicit Not for routing to deep-research, opensource-ops, and collaborative-thinking, making mis-trigger unlikely.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 3 missing	Warning

	Total	14 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/open-source-teardown/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.