CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-classic

Comet Classic 工作流(OpenSpec + Superpowers)。当用户明确调用 /comet-classic、要求启动或恢复 Comet Classic,或 resume-probe 返回可无歧义恢复的 active Classic change 时使用。

67

Quality

80%

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-classic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 a highly actionable, well-sequenced state-machine workflow with strong validation checkpoints and a clear progressive-disclosure reference appendix. Its main weakness is conciseness: several dense prose paragraphs would be tighter as bullets, and the referenced appendix files are not shipped inside the bundle.

Suggestions

Break the long 记忆接入 and 阶段衔接 paragraphs into bulleted rules to improve scannability and token efficiency.

Either ship the referenced comet-classic/reference/*.md files inside the skill bundle or note explicitly that they live in an external reference root, so progressive-disclosure navigation resolves within the skill.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes domain competence (no padding with basic concepts), but several paragraphs are long run-on compression blocks (e.g. the 记忆接入 paragraph and the auto-transition explanation) that could be tightened into shorter bullets; mostly efficient with some over-explanation.

3 / 5

Actionability

Every phase routes to a concrete, executable command (comet classic intent route --stdin, comet state transition, comet resume-probe --json, comet guard --apply) with a copy-pasteable CometIntentFrame skeleton and explicit per-route branch actions covering the common cases.

5 / 5

Workflow Clarity

Step 0→1→2 are explicitly sequenced with '命中即停' ordering, a breakpoint-recovery rule, an error-handling lookup table, decision-point blocklist, and a red-flag checklist providing explicit validation checkpoints and feedback loops for the risky state-mutation operations.

5 / 5

Progressive Disclosure

The decision-core is an overview with a clearly signaled one-level-deep reference appendix (comet-yaml-fields, file-structure, auto-transition, decision-point, etc.); however those reference files are not present as bundle files in this skill, so navigation resolves outside the bundle rather than within it, leaving a minor organization gap below a clean 5.

4 / 5

Total

17

/

20

Passed

Description

78%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 cleanly states both what the skill is and when to use it, with concrete trigger phrases and a strongly scoped invocation that minimizes conflict with sibling skills. The main gap is a lack of enumerated concrete actions and broader synonym coverage.

Suggestions

Add 1-2 concrete lifecycle actions (e.g. 'opens, designs, builds, verifies, and archives changes') to lift specificity toward comprehensive coverage.

Include a few natural-language synonyms and the English trigger variant so users phrasing the request differently still activate the skill.

DimensionReasoningScore

Specificity

Names the domain (Comet Classic workflow) and the concrete two-engine composition (OpenSpec + Superpowers), plus the concrete trigger surface (/comet-classic invocation, resume-probe result); it does not enumerate the multiple discrete lifecycle actions the body covers, so it sits above 3 but not fully comprehensive at 5.

4 / 5

Completeness

Both 'what' (Comet Classic 工作流 with OpenSpec + Superpowers) and 'when' (explicit '当…时使用' clause with three concrete trigger conditions) are present and clear; the 'when' could be slightly more specific about the resume branch to reach 5.

4 / 5

Trigger Term Quality

Includes natural trigger phrases users would say ('明确调用 /comet-classic', '启动或恢复 Comet Classic') plus the resume-probe trigger path; it is missing common synonyms and the English/extension variants that would push it to a full 5.

4 / 5

Distinctiveness Conflict Risk

The skill name 'comet-classic' and the scoped trigger (only on explicit /comet-classic invocation or an unambiguous resume-probe active Classic change) give it a clear niche with minimal overlap risk against sibling comet presets.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rpamis/comet
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.