CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

comet-native

Comet Native 工作流。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。

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./assets/skills-zh/comet-native/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

This is a sophisticated, well-structured workflow skill with explicit phase completion criteria, feedback loops, and a thoughtfully designed on-demand reading system. Its main weaknesses are density — long run-on paragraphs and rules repeated across sections that inflate the token budget — and the fact that all referenced reference files are missing from the bundle while their content is partly duplicated inline.

Suggestions

Move the detailed protocol variants (SDK Run 路径 continuation modes, Compat/legacy handling in '后续指令') into the referenced files (reference/commands.md, reference/recovery.md) and keep only the decision rules inline — the body currently duplicates what the references should carry.

Break the multi-clause run-on paragraphs (rules section, Builder step) into short bullet points, and deduplicate rules stated in both '必须遵守的规则' and the phase sections (e.g., failure-not-passing, artifact-position checks).

Ensure the referenced bundle files (reference/*.md and ../comet/reference/*.md) actually ship with the skill, or inline the minimal needed content — every '按需读取' link currently points to a file absent from the bundle.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but it is densely packed with run-on paragraphs (e.g., the multi-clause rule paragraphs in '必须遵守的规则' and the Builder step in 'SDK Run 路径') and repeats rules across sections (e.g., failure-not-passing appears in both the rules and Verify; '不能用另一文件中的同类内容代替' appears in both Build and Verify). It could be tightened noticeably without losing information, matching anchor 3 rather than 4.

3 / 5

Actionability

Concrete, executable guidance is present throughout: specific commands ('comet native select <change-name> --json', 'comet native status --json', 'native new --task'), flags ('--review current-session', '--accept-on-pass <用户授权摘要>'), files ('comet-state.yaml', '.comet/config.yaml' hook.allow_paths), and response types. Minor gaps remain: several actions defer exact syntax to Runtime responses or '--help', and some policy sentences ('由当前 Agent 根据不确定性和用户要求决定') are abstract, keeping it below anchor 5.

4 / 5

Workflow Clarity

The multi-phase workflow (开始或恢复 → Shape → Build ↔ Verify → Archive → 后续指令) is clearly sequenced with explicit validation checkpoints via per-phase '完成标准' sections and feedback loops ('未通过则回 Build 修复并重新提交', failure/timeout never counts as pass, recovery references for interruptions). It falls short of anchor 5 because interleaving three runtime variants (SDK, Compat, legacy) inside single paragraphs makes some sequences hard to follow on first read.

4 / 5

Progressive Disclosure

The '按需读取' section is genuinely well-designed — each reference link carries an explicit read condition (e.g., '状态包含 childSummary 时...读取 Supervisor 协作'), one level deep. However, none of the referenced files (reference/commands.md, reference/recovery.md, ../comet/reference/*.md, etc.) exist in the bundle, so the disclosure targets are unverifiable, and ~135 lines of dense protocol detail that belongs in those references (continuation modes, SDK/Compat protocol variants) are inlined in SKILL.md, matching anchor 3.

3 / 5

Total

14

/

20

Passed

Description

60%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 has an explicit, well-scoped trigger clause and is highly distinctive within its ecosystem, but it says essentially nothing about what the skill does — 'Comet Native 工作流' is a name, not a capability statement. Adding one or two concrete actions (e.g., saving requirements and acceptance conclusions, driving changes via the comet native CLI) would materially improve it.

Suggestions

Replace the bare domain label 'Comet Native 工作流' with 2-3 concrete capabilities, e.g., '保存需求与验收结论,通过 comet native CLI 推进 change 的 Shape、Build、Verify 和归档' — this would lift both specificity and completeness.

State the skill's purpose (what it does for the user) before the trigger clause, keeping the existing '当用户...时使用' sentence as the 'when'.

Consider adding a couple of natural trigger variations users might say (e.g., '推进 Native change', '恢复 Native 任务') to broaden keyword coverage.

DimensionReasoningScore

Specificity

The entire 'what' statement is "Comet Native 工作流" — a domain label with no concrete actions or capabilities named. It names the domain specifically (so above anchor 1's pure abstraction) but lists zero actions like 'saves requirements', 'runs changes', or 'archives results', matching anchor 2.

2 / 5

Completeness

The 'when' is fully explicit ("当用户明确调用 /comet-native...时使用"), but the 'what' is only a weak domain label — it never says what the workflow actually does. This falls between anchor 2 (only 'when', no 'what') and anchor 4 (both present and solid), landing at the midpoint.

3 / 5

Trigger Term Quality

Triggers are explicit and natural for this niche: "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" covers slash-command invocation, start, and resume. A few natural variations (e.g., plain 'comet native' mentions, English phrasing) are missing, keeping it below anchor 5.

4 / 5

Distinctiveness Conflict Risk

Triggers are tightly scoped to this skill's own name and artifacts ("/comet-native", "Native change", "入口路由到 Native"), giving it a clear niche with minimal risk of firing for unrelated skills.

5 / 5

Total

14

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 20 possibly missing (reference/artifacts.md#正式产物, reference/artifacts.md#源文档完整覆盖, reference/clarification.md#澄清, reference/clarification.md#需求变化后的重新确认, reference/commands.md#builder-交接, +15 more), 3 suspicious

Warning

Total

15

/

16

Passed

Repository

rpamis/comet

Path

assets/skills-zh/comet-native/SKILL.md

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.