comet-native

Comet Native 工作流。当用户明确调用 /comet-native、要求启动或恢复 Native change，或入口路由到 Native 时使用。

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./assets/skills-zh/comet-native/SKILL.md

Quality

Content

60%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 well-structured and highly actionable with clear phased workflows and concrete commands, but it is significantly over-written — long prescriptive paragraphs could be condensed into tables/checklists to respect the token budget. Progressive disclosure and navigation are handled well.

Suggestions

Condense the long prescriptive paragraphs in Shape, Build, and Verify into tables or bullet checklists (e.g., the runId/integration rules) to cut token weight while preserving the rules.

Pull a few representative command templates out of prose into short fenced blocks so they are copy-paste ready, especially for `dispatch-verifier` and `archive --dry-run` flows.

Move the dense Supervisor Change / multi-session fallback logic into a dedicated reference file and keep only the decision trigger inline, reducing the main body's wall-of-text.

Dimension	Reasoning	Score
Conciseness	The body is a dense wall of prescriptive prose (≈110 lines, many paragraphs running 200+ words) that re-explains state-machine rules and fallback logic in exhausting detail; while accurate, much of it could be condensed into tables or checklists, making it noticeably verbose with several padded sections.	2 / 5
Actionability	It provides concrete, executable commands throughout (e.g., `comet native status <change-name> --json`, `comet task … --json`, `archive --dry-run`) with specific flags and an explicit finish-option table, leaving only minor gaps where exact command templates are implied rather than shown.	4 / 5
Workflow Clarity	Phases are clearly sequenced (开始或恢复 → Shape → Build ↔ Verify Loop → Archive → 后续指令) with explicit completion criteria per phase and feedback loops (verify → revise → rebuild), though some validation checkpoints are buried in prose rather than enumerated.	4 / 5
Progressive Disclosure	It appropriately points to one-level-deep references ([工作区选择参考], [澄清参考], [产物参考], [命令参考], [恢复参考]) and signals when to read each, keeping the overview inline; the referenced files are not present in the bundle to verify, but the signaling and structure are good with only minor organization gaps.	4 / 5
	Total	14 / 20 Passed

Description

56%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 has strong, specific trigger terms and good distinctiveness, but it is weak on capability specificity and only weakly implies the 'what'. It would benefit from listing concrete actions and an explicit capability summary.

Suggestions

Add 1-2 concrete capabilities after the domain label (e.g., what the workflow actually does) so 'what' is explicit, not just implied by '工作流'.

Expand the trigger clause into a clearer 'Use when…' sentence that pairs the when-conditions with the skill's purpose.

Consider third-person action verbs ('Orchestrates…', 'Manages…') to replace the bare noun phrase 'Comet Native 工作流' and improve specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Comet Native 工作流') but provides only generic action framing ('当…时使用') with no concrete capabilities enumerated, so it falls at the anchor for naming the domain with minimal/generic actions.	2 / 5
Completeness	It clearly states when to use the skill ('当用户明确调用…要求启动或恢复…入口路由到 Native') but the 'what' is reduced to the bare label 'Comet Native 工作流' with no concrete actions, and there is no explicit 'Use when…' capability statement, capping completeness per the missing-trigger-guidance rule.	3 / 5
Trigger Term Quality	It includes natural trigger phrases users would actually say ('调用 /comet-native', '启动或恢复 Native change') plus routing context, offering good keyword coverage with only minor synonym variations missing.	4 / 5
Distinctiveness Conflict Risk	The trigger '/comet-native' and 'Native change' are highly specific and unlikely to fire for unrelated skills, with only minor overlap risk against other Comet workflow skills.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 missing	Warning

	Total	15 / 16 Passed

Repository: rpamis/comet
Path: assets/skills-zh/comet-native/SKILL.md
Commit: c1118e1

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.