comet-build

Comet Classic 阶段 3 —— 恢复或创建实施计划并执行其任务。

Quality

73%

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

Quality

Content

88%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 content is a well-engineered, executable build-phase workflow with strong actionability, sequencing, and validation checkpoints. Main improvement area is progressive disclosure: actually providing the referenced comet-classic/reference/*.md bundle files would let the inlined protocol detail be trimmed.

Suggestions

Create the referenced comet-classic/reference/*.md bundle files (decision-point, context-recovery, subagent-dispatch, debug-gate, scripts, etc.) so protocol detail can be offloaded from the body.

De-duplicate the repeated language constraint and guard-command guidance by stating each once and cross-referencing.

Consolidate the repeatedly enumerated guard-failure conditions for build_mode/subagent_dispatch/tdd_mode/review_mode into a single table to reduce repetition.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational, using tables and command blocks and largely assuming Claude's competence. A few sections repeat guidance (the language constraint and guard commands recur), leaving minor over-explanation that could be trimmed.	4 / 5
Actionability	Guidance is fully executable: concrete comet/git commands, literal subagent output lines ('PLAN_PATH:', 'SKILL_UNAVAILABLE'), exact state-field names, and guard semantics. Specific examples cover the common cases.	5 / 5
Workflow Clarity	Steps 0-5 are clearly sequenced with an entry check, idempotency rules, a single joint decision point, an exception-debug protocol, explicit exit conditions, and a guard feedback loop — explicit validation checkpoints for risky/batch operations.	5 / 5
Progressive Disclosure	Structure is good with clear sections and clearly signaled one-level-deep references to comet-classic/reference/*.md, but no bundle files exist in this skill directory to offload the substantial inlined protocol detail, leaving minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

57%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 appropriately scoped and distinct but lacks an explicit trigger clause and natural-language keywords. Adding a 'Use when...' phrase with user-natural terms like 'build' or 'execute the plan' would lift completeness and trigger quality.

Suggestions

Append a 'Use when...' clause, e.g. 'Use when resuming or running the Comet Classic build (phase 3) for an active change.'

Add natural-language trigger terms beyond jargon, such as 'build the change', 'execute the plan', or 'run phase 3'.

Optionally enumerate a second concrete action (e.g. 'record build evidence and run the phase guard') to improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain (Comet Classic phase 3) and two concrete actions — '恢复或创建实施计划' and '执行其任务' — but coverage is not comprehensive. It matches the anchor that names a domain with 1-2 concrete actions.	3 / 5
Completeness	It gives a clear 'what' (restore/create a plan and execute its tasks) but provides no explicit 'Use when...' trigger clause. Per the judging guidelines, a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	'Comet Classic 阶段 3' is relevant but niche jargon; it lacks the natural variations a user would say (e.g. 'build', 'run the plan'). It has some relevant keywords but misses common synonyms, matching the anchor for partial keyword coverage.	3 / 5
Distinctiveness Conflict Risk	It is scoped to a specific phase of a specific workflow (Comet Classic phase 3), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	14 / 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: assets/skills-zh/comet-build/SKILL.md
Commit: 99fd749

Reviewed: 6 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.