CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-open

仅在用户明确调用 /comet-open,或由 Comet 根 Skill/runtime 路由到 open 阶段时使用;创建或恢复 OpenSpec change,并补齐 proposal/design/tasks/.comet.yaml。

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

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 and exceptionally well-sequenced with strong validation feedback loops, but it is verbose with notable repetition and keeps most procedural detail inline rather than splitting it into bundled reference files.

Suggestions

Consolidate the repeated 'external-openspec-skill-override' and OpenSpec compatibility precheck rules into a single stated-once section to reduce token redundancy across steps 1, 1a, and 2.

Move the detailed JSON-schema compatibility predicates and the idempotent recovery algorithm into a bundled reference file (e.g. comet/reference/openspec-contract.md) and link to it from SKILL.md so the overview stays lean.

Actually ship the referenced comet/reference/*.md files in the skill's references/ bundle so the one-level-deep navigation is real rather than pointing at external paths.

DimensionReasoningScore

Conciseness

The body is operational and avoids explaining concepts Claude already knows, but ~265 lines with the compatibility precheck, changeRoot/applyRequires rules, and the external-skill-override block repeated three times pad the token budget and could be tightened.

2 / 3

Actionability

Provides copy-paste-ready commands (`comet classic openspec -- status ...`, `comet state init/select/check`, `comet guard ... --apply`) and exact JSON-field predicates and artifact trees, leaving no ambiguity about what to run.

3 / 3

Workflow Clarity

A clearly numbered sequence (0 through 5) with explicit validation checkpoints, blocked→missingDeps→fix→re-run feedback loops, an idempotent recovery algorithm, and mandatory hard checks before phase transition.

3 / 3

Progressive Disclosure

References to comet/reference/*.md and the openspec-* skills are clearly signaled and one level deep, but the body is a large monolithic wall of inline procedural detail and the referenced comet/reference/* files are not present in this skill's bundle (references/scripts/assets are empty).

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, third-person, and clearly states both what the skill does and when to use it, anchored to a specific slash-command trigger. It avoids fluff and over-claims while covering concrete artifacts.

DimensionReasoningScore

Specificity

Names multiple concrete actions on concrete artifacts — '创建或恢复 OpenSpec change' and '补齐 proposal/design/tasks/.comet.yaml' — rather than vague language.

3 / 3

Completeness

Explicitly answers both 'what' (create/resume OpenSpec change, backfill proposal/design/tasks/.comet.yaml) and 'when' ('仅在用户明确调用 /comet-open,或...路由到 open 阶段时使用').

3 / 3

Trigger Term Quality

Uses the natural invocation form '/comet-open' and '路由到 open 阶段', which are the terms a user/runtime would actually say to trigger this skill.

3 / 3

Distinctiveness Conflict Risk

The trigger is tightly bound to the specific /comet-open command and Comet/OpenSpec open phase routing, giving it a clear niche unlikely to conflict with other skills.

3 / 3

Total

12

/

12

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.