CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-open

Comet Classic 阶段 1 —— 开启 OpenSpec change 并建立 proposal/design/tasks/.comet.yaml 产物。

59

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

Quality

Content

77%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 well-sequenced, highly actionable orchestration workflow with strong validation and recovery safeguards, scoring top marks on actionability and workflow clarity. Its weaknesses are repetition of the compatibility preflight across steps and inlining of lengthy sub-procedures (notably batch splitting) that would benefit from extraction into reference files.

Suggestions

Define the OpenSpec compatibility preflight once and reference it from Steps 0c, 2, 3 and 4 to remove repeated detail and improve conciseness.

Extract the long Step 1a PRD-splitting / batch-orchestration protocol into a dedicated reference file (e.g. references/batch-splitting.md) and summarize it in SKILL.md to improve progressive disclosure.

Tighten repeated guardrail phrasing (multiple '必须停止并报告' / '不得...' restatements of the same constraint) into a single stated rule per concern.

DimensionReasoningScore

Conciseness

The body is dense procedural guidance that assumes domain competence (no basic concept padding), but the OpenSpec compatibility preflight is restated across Steps 0c, 2, 3, 4 and the recovery algorithm, so it could be tightened; not 4 because the repetition is more than minor.

3 / 5

Actionability

It provides many concrete, copy-paste-ready commands with real flags (e.g. 'comet classic openspec -- status --change "<name>" --json', 'comet state init <name> full --isolation <selected-isolation>', 'comet guard <change-name> open --apply') covering the common cases with obvious parameter substitution.

5 / 5

Workflow Clarity

Steps are explicitly sequenced (0 through 5 plus exit/auto-transition) with validation checkpoints ('comet state check <name> open', compatibility preflight), an idempotent recovery algorithm with validate-fix-retry feedback loops, and a hard batch-completion checklist for the destructive/batch path.

5 / 5

Progressive Disclosure

It signals one-level-deep references to external docs (comet-classic/reference/*.md) and external skills with clear section headers, but large sub-procedures such as the Step 1a batch orchestration are inlined rather than split into own bundle files, and no references/scripts/assets bundles ship with this skill.

3 / 5

Total

16

/

20

Passed

Description

58%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 and distinct, clearly stating what the skill does and which artifacts it produces, but it omits any 'Use when...' trigger guidance and leans on technical jargon over natural user phrasing. Adding an explicit when-to-use clause and a few natural trigger terms would lift completeness and trigger_term_quality.

Suggestions

Append an explicit 'Use when...' clause, e.g. 'Use when starting or resuming a Comet Classic change at the open phase, or when the user asks to open/propose a new change.'

Add natural trigger terms users would actually say (e.g. 'open a change', 'start a new spec', 'create proposal') alongside the technical artifact names.

Clarify scope boundaries versus sibling phase skills (e.g. '阶段 1 only; hands off to design/build') to further reduce overlap risk.

DimensionReasoningScore

Specificity

The description names the domain ('Comet Classic 阶段 1', 'OpenSpec change') and several concrete artifacts ('proposal/design/tasks/.comet.yaml 产物'), listing multiple specific actions; it stops short of 5 because the action set is narrow (open + establish artifacts) rather than comprehensively multi-action.

4 / 5

Completeness

It gives a clear 'what' (open an OpenSpec change and establish proposal/design/tasks/.comet.yaml artifacts) but lacks any 'when'/'Use when...' trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

It surfaces relevant domain keywords (OpenSpec change, proposal, design, tasks) but they are technical jargon with no natural user-facing phrasing or synonyms, so coverage is partial rather than comprehensive.

3 / 5

Distinctiveness Conflict Risk

The 'Comet Classic 阶段 1' framing carves a clear niche, but sibling phase skills in the same family (e.g. design/build) share the Comet Classic prefix, leaving minor overlap risk with closely related skills.

4 / 5

Total

14

/

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.