CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-design

仅在用户明确调用 /comet-design,或由 Comet 根 Skill/runtime 路由到 full workflow 的 design 阶段时使用;创建或恢复深度技术 Design Doc。

59

Quality

67%

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

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, highly actionable workflow with excellent sequencing and validation checkpoints. Its main weaknesses are verbosity from repeated emphasis and a monolithic body that underuses progressive disclosure despite pointing to external references.

Suggestions

De-duplicate the repeated constraints: state the minimal Design Doc frontmatter once and reference it, and consolidate the '禁止手写 summary / 禁止跳过' prohibitions into a single rules block instead of restating per step.

Extract the handoff-file format reference (design-context.json/md and spec-context.json/md field lists) and the brainstorm-summary.md template into a reference file, keeping SKILL.md as an overview that links to them.

Tighten the 1e 主动式上下文压缩 section to a concise rule list; the current prose repeats the recovery-file list already given in 1d.

DimensionReasoningScore

Conciseness

The content is actionable and domain-specific rather than explaining basics Claude knows, but it is verbose: prohibitions are repeated, the minimal frontmatter is specified twice (1b and Step 2), and the context-compression sections are wordy and could be tightened.

2 / 3

Actionability

Provides fully executable commands (node "$COMET_STATE" check, node "$COMET_HANDOFF" ... --write, node "$COMET_GUARD" ... --apply), concrete file paths, and copy-paste-ready yaml/frontmatter templates with clearly parameterized placeholders.

3 / 3

Workflow Clarity

Clear sequenced steps (0, 1a–1e, 2, 3) with explicit validation checkpoints: entry check, a blocking user-confirmation point at 1c, guard --apply enforcement, and a concrete exit-condition checklist.

3 / 3

Progressive Disclosure

Cross-cutting concerns are well-signaled via one-level references (comet/reference/scripts.md, context-recovery.md, decision-point.md, auto-transition.md), but the body is long and monolithic with inline handoff-format and template detail that could be split out; no bundle files are present to verify the referenced paths.

2 / 3

Total

10

/

12

Passed

Description

57%

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 clearly targeted and unambiguous about its trigger conditions, with a strong distinctiveness profile, but it describes when to use the skill far more concretely than what the skill actually does. Adding an explicit capability statement would raise completeness and specificity.

Suggestions

Lead with a concrete action clause before the trigger, e.g. 'Produces a Superpowers Design Doc for a Comet change by deepening the open-phase handoff into a technical design. Use when ...'

State the core outputs explicitly (Design Doc at docs/superpowers/specs/, Spec Patch回写, phase推进 to build) so 'what it does' is not left implied.

Add a few broader natural-language phrasings (e.g. 'design 阶段', '深度技术设计', '技术方案') alongside the current jargon to improve trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and concrete triggering states ('已完成 open 阶段', '缺少 Superpowers Design Doc', '从 OpenSpec 交接包恢复') but lists no concrete actions the skill performs, so it is not comprehensive.

2 / 3

Completeness

Explicitly answers 'when' via 'Use when ...', but the 'what' (produce a Superpowers Design Doc / run the design phase) is only implied rather than stated as a concrete action, so it does not fully answer both.

2 / 3

Trigger Term Quality

Has an explicit 'Use when' clause and relevant domain keywords (Comet change, Design Doc, OpenSpec 交接包), but the terms are jargon-dense and narrow, missing common variations a user might phrase.

2 / 3

Distinctiveness Conflict Risk

Highly specific to the Comet design-phase workflow with distinct triggers (open 阶段完成, missing Design Doc, handoff recovery), making it unlikely to fire for the wrong skill.

3 / 3

Total

9

/

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.