comet

Use when 用户要启动或恢复 Comet 工作流，需要根据 active change、.comet.yaml、hotfix/tweak 意图路由到对应阶段 Skill。

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./eval/local/skills/benchmarks/040-beta/comet/SKILL.md

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 highly actionable with concrete commands, a JSON skeleton, and a well-sequenced state-machine workflow including validation feedback loops. Its weaknesses are repeated confirmation-guidance padding and a progressive-disclosure defect: the nine referenced comet/reference/*.md files do not exist in the bundle.

Suggestions

Include the missing comet/reference/*.md files (auto-transition, comet-yaml-fields, context-recovery, debug-gate, decision-point, dirty-worktree, file-structure, intent-frame, scripts) in the bundle, or remove/inline the references so no navigation links are broken.

De-duplicate the user-confirmation guidance: keep one authoritative statement (e.g., the decision-point list) and replace the prose restatement and 红旗清单 table with a single pointer, cutting roughly 20-30 lines of repetition.

Consolidate the 预设升级判定 section so it states the rule once and points to /comet-hotfix and /comet-tweak rather than restating the three-layer分工 and 升级决策点 twice.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural/state-machine content Claude would not already know, but it repeats guidance several times — the 'must pause for user confirmation' rule appears in prose, the decision-point list, and the 红旗清单 table, and 升级判定 is restated — placing it at 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 4.	3 / 5
Actionability	It provides fully executable, copy-paste-ready guidance: concrete commands ('openspec list --json', 'node "$COMET_GUARD" <change> <phase> --apply', 'node "$COMET_STATE" transition <change> <event>'), a complete CometIntentFrame JSON skeleton, and exact routing/transition examples covering the common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced (Step 0 → 1 → 2 with '命中即停' ordering), 断点恢复 rules are explicit, validation happens via guard --apply and verify-fail feedback loops, and destructive operations like archive require final-confirmation checkpoints, matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	5 / 5
Progressive Disclosure	Structure and signaling are good — a dedicated appendix points one-level-deep to comet/reference/.md with bold labels and externalizes scripts to comet/scripts/ — but the nine referenced comet/reference/.md files are not present in the bundle, so the navigation is broken rather than complete, fitting 'some structure but references not clearly actionable / could be better organized' rather than 4.	3 / 5
	Total	16 / 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 clearly answers what the skill does and when to use it, with a natural trigger phrase and a highly distinct named-workflow niche. Its main weakness is that the 'what' is framed as routing decisions rather than fully concrete, comprehensive actions.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete signals it acts on — 'active change、.comet.yaml、hotfix/tweak 意图路由到对应阶段 Skill' — but the actions are routing decisions rather than a fully comprehensive list of concrete operations, fitting the 'several specific actions; minor gaps' anchor rather than 5.	4 / 5
Completeness	It has both an explicit 'Use when' clause and a what-it-does statement (route to phase skills based on active change/.comet.yaml/intent); both are present, but the 'what' is somewhat abstract (routing) and could be more concrete, matching the 'both what and when; when could be more explicit/specific' anchor.	4 / 5
Trigger Term Quality	The phrase '用户要启动或恢复 Comet 工作流' is a natural trigger a user would actually say, plus hotfix/tweak keywords; coverage is good but a few common synonyms or variations are missing, so it sits at the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	The trigger is tied to a uniquely named system ('Comet 工作流') with named phase sub-skills (/comet-hotfix, /comet-tweak, etc.), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rpamis/comet
Path: eval/local/skills/benchmarks/040-beta/comet/SKILL.md
Commit: 2ff42ff

Reviewed: 2 days 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.