CtrlK
BlogDocsLog inGet started
Tessl Logo

convention-graph-discovery

约定图发现方法论:进一个 repo 先识别 repo-specific conventions,再定义 domain/extractor 接 Convention Graph 引擎。Use when: 进入陌生 repo、要画约定图、要找“改 X 影响谁”的约定层关联、 F242/Convention Graph Layer 工作。Not for: 普通符号跳转/LSP、文档索引检索、记忆图谱、直接使用 codegraph/GitNexus。Output: domain 定义 + extractor 计划 + gap/freshness/provenance 报告。 GOTCHA: 沉淀的是“怎么画图”的方法,不是把 cat-cafe 的 extractor 硬搬到所有 repo。

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 with executable commands and a well-sequenced, validation-backed protocol. It is token-efficient and well-structured, with only minor conciseness and disclosure-split opportunities.

DimensionReasoningScore

Conciseness

Mostly lean — it assumes Claude knows LSP/grep and uses compact tables without explaining basic concepts — but a few motivational restatements in 价值门禁 and minor metaphor asides ("看这个 repo 的规矩") could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready bash commands with real CLI invocations, env-var parameterization, expected JSON output fields, and concrete per-step deliverables in the Discovery Protocol.

5 / 5

Workflow Clarity

A numbered 7-step Discovery Protocol with clear sequence and explicit validation checkpoints — baseline comparison (step 6), no-silent-0-hit gap reporting (step 7), plus a Pressure Test checklist with negative-fixture and stale=true checks and a re-index feedback loop.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections with no nested references and self-contained content; since no bundle files exist all detail sits appropriately inline, though the ~116-line body could potentially split the protocol/reference material out.

4 / 5

Total

18

/

20

Passed

Description

92%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 is specific, complete, and distinctive, with explicit what/when/output clauses and a strong trigger list. It avoids over-claims and uses neutral third-person voice with no first/second-person phrasing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — identifying repo-specific conventions, defining domain/extractor, wiring into the Convention Graph engine, and producing gap/freshness/provenance reports — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what ("识别 repo-specific conventions…再定义 domain/extractor…接 Convention Graph 引擎", "Output: domain 定义 + extractor 计划 + gap/freshness/provenance 报告") and when ("Use when:…" with concrete trigger phrases).

5 / 5

Trigger Term Quality

Includes a dedicated triggers list ("约定图", "convention graph", "进陌生 repo", "改 X 影响谁", "F242") plus inline Use-when phrases with synonyms, though a few additional natural phrasings could be added.

4 / 5

Distinctiveness Conflict Risk

Clear niche (repo convention-graph discovery) reinforced by an explicit "Not for" exclusion list (LSP, memory graph, codegraph/GitNexus) and a GOTCHA distinguishing it from cat-cafe's extractor, minimizing conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository
zts212653/clowder-ai
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.