CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-tweak

仅在用户明确调用 /comet-tweak,或由 Comet 根 Skill/runtime 路由到 tweak preset 时使用;处理可收敛为单一 OpenSpec change 的轻量或中等变更。

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

Quality

Content

85%

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

The body is a well-structured, highly actionable multi-phase workflow with explicit commands, skill loads, validation guards, and feedback loops, plus clear one-level references to detailed docs. Its only real weakness is redundancy: the delta-spec-not-escalation rule and escalation logic are restated multiple times.

Suggestions

Consolidate the escalation/升级判定 logic into its dedicated section and have other phases reference it once, instead of restating the delta-spec-not-escalation rule and signal lists in the build, verify, and overview sections.

Trim repeated reinforcement phrases (e.g., the four near-identical '立即执行:使用 Skill 工具加载 X 技能。禁止跳过此步骤。' lines) into a single stated convention referenced by each phase.

DimensionReasoningScore

Conciseness

The body is mostly necessary operational guidance and avoids explaining concepts Claude already knows, but the 'delta spec is a normal product and not an escalation reason' point and escalation logic are repeated across the build section, the 升级判定 section, and inline reminders, so it could be tightened; this matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the lean level-3 anchor.

2 / 3

Actionability

It provides concrete, copy-paste-ready commands (e.g., `node "$COMET_STATE" init <name> tweak`, `node "$COMET_GUARD" <change-name> build --apply`, `node "$COMET_STATE" transition <name> preset-escalate`), explicit skill loads, named artifacts (proposal.md/design.md/tasks.md/delta spec), and a commit-message format — fully executable guidance.

3 / 3

Workflow Clarity

The open → build → verify → archive sequence is explicit, with validation checkpoints (phase guards, `check`, `verify_result: pass` required before archive) and feedback loops (systematic-debugging debug-gate on failures, escalate/continue decision points), matching the clear-sequence-with-validation-and-feedback anchor.

3 / 3

Progressive Disclosure

SKILL.md acts as an overview and points to one-level-deep, clearly signaled reference docs (e.g., `comet/reference/scripts.md`, `decision-point.md`, `auto-transition.md`, `debug-gate.md`), with content appropriately split rather than deeply nested, matching the well-signaled one-level reference anchor.

3 / 3

Total

11

/

12

Passed

Description

50%

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 provides an explicit 'Use when' trigger and a recognizable niche, but leans on internal terminology ('可收敛为单一 OpenSpec change') and describes scope rather than concrete actions, weakening trigger-term quality and the 'what' statement. It is serviceable but not maximally clear or user-natural.

Suggestions

Rewrite the trigger condition in natural user language (e.g., 'Use when the user wants a small or medium change that fits in one OpenSpec change') instead of '可收敛为单一 OpenSpec change' jargon.

Add one or two concrete capability verbs stating what the skill actually does (e.g., 'orchestrates a streamlined OpenSpec change: open, build, verify, archive') so the 'what' is explicit, not just the 'when'.

Sharpen the boundary versus full /comet with a plain-language cue (e.g., 'for changes that don't need a full design doc') to reduce overlap/conflict risk.

DimensionReasoningScore

Specificity

Names the domain ('OpenSpec change', 'tweak workflow') and a couple of actions ('进行...变更', '恢复 tweak workflow'), but does not list multiple concrete capabilities, so it sits at the 'names domain and some actions, but not comprehensive' anchor rather than the multi-action level 3.

2 / 3

Completeness

The 'when' is explicit via 'Use when...', but the 'what' is abstract — the description characterizes scope/conditions rather than stating a concrete capability — so it does not clearly answer both what and what at the level-3 anchor.

2 / 3

Trigger Term Quality

It has a 'Use when...' clause and a somewhat natural phrase ('轻量或中等变更'), but the core condition '可收敛为单一 OpenSpec change' is technical jargon a user would not naturally say, leaving only some relevant keywords rather than full natural-term coverage.

2 / 3

Distinctiveness Conflict Risk

The 'tweak' / 'single OpenSpec change' / '不需要完整设计' framing carves a niche, but it is technically stated and could still overlap with the full /comet workflow in a user's mind, matching 'somewhat specific but could still overlap with similar skills.'

2 / 3

Total

8

/

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.