comet-native

当用户明确调用 /comet-native、要求启动或恢复 Native change，或入口路由到 Native 时使用；负责澄清需求、读取状态并推动 Shape → Build → Verify → Archive。

Quality

88%

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%

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

The content is a detailed, highly actionable workflow with strong sequencing and validation checkpoints. Its main weaknesses are verbosity from repeated stipulations across modes and a monolithic structure whose external reference links are broken.

Suggestions

Consolidate the shared rules between Sequential and Batch clarification into one section, then note only the per-mode differences, to cut repetition and tighten conciseness.

Create the missing `reference/commands.md`, `reference/artifacts.md`, and `reference/recovery.md` files (or correct the paths) so the signaled navigation resolves, and move the large command/format detail out of SKILL.md into them to reduce the monolithic wall of text.

De-duplicate the recurring prohibitions (e.g. "do not enter Build or call next", "do not persist hidden reasoning") into a single canonical statement referenced where needed.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence and avoids explaining basic concepts, but it is heavily padded with repeated prohibitions (e.g. "do not enter Build or call next", "do not persist hidden reasoning") and substantial overlap between the Sequential and Batch mode sections that could be tightened.	2 / 3
Actionability	It supplies concrete, copy-paste-ready commands with real flags throughout — `comet native next <change> --summary <summary> --confirmed`, `comet native archive <change> --expect-preflight <sha256>`, `comet native spec remove` — matching the fully-executable anchor.	3 / 3
Workflow Clarity	Shape → Build → Verify → Archive is clearly sequenced with explicit validation checkpoints and feedback loops: Verify's fail→Build repair-episode logic, the two-step archive preflight→commit, and stale-evidence resealing all match the highest anchor.	3 / 3
Progressive Disclosure	References are well-signaled and one level deep ("command reference", "artifact reference", "recovery reference"), but the body itself is a ~266-line monolith with content that should be split out, and the three cited `reference/*.md` files do not exist on disk, breaking navigation.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concise, specific, and provides explicit triggers for both what the skill does and when to invoke it. It uses third-person/imperative voice and avoids fluff or over-claims.

Dimension	Reasoning	Score
Specificity	The description names multiple concrete actions — "clarify requirements, read state, and drive Shape → Build → Verify → Archive" — rather than vague language, matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	It answers both 'what' (clarify requirements, read state, drive the four phases) and 'when' with an explicit "Use when..." clause, satisfying the highest anchor.	3 / 3
Trigger Term Quality	Phrases like "the user explicitly invokes /comet-native" and "asks to start or resume a Native change" are natural terms a user would actually say, giving good trigger coverage rather than jargon.	3 / 3
Distinctiveness Conflict Risk	The triggers are narrowly scoped to /comet-native and Native changes, a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: rpamis/comet
Path: assets/skills-zh/comet-native/SKILL.md
Commit: 2945693

Reviewed: about 10 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.