CtrlK
BlogDocsLog inGet started
Tessl Logo

comet-hotfix

Comet 预设 —— 通过 open-build-verify-archive 短流程修复已有行为 bug。

57

Quality

65%

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

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 a highly actionable, well-sequenced workflow with strong validation checkpoints and feedback loops, anchored in concrete copy-paste commands. Its main weaknesses are repetition across sections that hurts conciseness and dense inlined command detail that belongs in separated reference files.

Suggestions

Consolidate the escalation/质变信号 rules into the single 升级判定 section and reference it from Step 3 and 连续执行模式 instead of restating, to reduce repetition and tighten conciseness.

Extract the dense Step 0 `comet task` / `comet memory` flag catalog into a dedicated reference file (e.g. `references/comet-task.md`) and link to it, improving progressive disclosure and token efficiency.

Provide a local bundle pointer or short fallback for the `comet-classic/reference/*.md` dependencies so the skill remains navigable when comet-classic is not co-located.

DimensionReasoningScore

Conciseness

The body is dense and largely avoids explaining concepts Claude already knows, but it restates the same material multiple times — the escalation signals appear in Step 3, the 升级判定 section, and 连续执行模式, and the open→build→根因→verify→archive chain is repeated — so it could be noticeably tightened. It sits above the padded anchor 2 but below the trim anchor 4.

3 / 5

Actionability

Provides copy-paste-ready, concrete commands throughout (e.g. `comet state init <name> hotfix`, `comet guard <change-name> build --apply`, `comet task <project-root> --task ... --json`) plus named artifacts (proposal.md/design.md/tasks.md) covering the common workflow cases. It matches the "fully executable; copy-paste ready" anchor.

5 / 5

Workflow Clarity

A clearly sequenced 6-step process with explicit validation checkpoints (`comet state check`, `comet guard ... --apply`, `comet state next` auto/manual, `verify_result: pass` required before archive), feedback loops (root-cause-elimination returns to Step 2, systematic-debugging on failures), and checklists (退出条件, tasks.md checkboxes). This matches the anchor-5 example with feedback loops and checklists.

5 / 5

Progressive Disclosure

Sections are well-organized and references to `comet-classic/reference/*.md` are clearly signaled and one level deep, but no local bundle exists (references/, scripts/, assets/ absent) and dense inline blocks — notably the Step 0 `comet task` memory/context paragraph and the repeated escalation detail — read as content that should be split into separate files. This fits the "some structure but content that should be separate is inline" anchor better than the well-split anchor 4.

3 / 5

Total

16

/

20

Passed

Description

53%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 concisely names a clear niche (hotfix bug-fix flow) and its phase sequence, but stops short of comprehensive capability coverage and omits any explicit "Use when..." trigger guidance. It is a solid, specific one-liner that would benefit from an explicit trigger clause.

Suggestions

Add an explicit trigger clause, e.g. "Use when fixing an existing behavior bug without new capabilities, interface changes, or architecture adjustments."

Surface a couple of natural user phrases ("hotfix", "bug fix", "快速修复") earlier and drop or downplay the jargon "Comet 预设" so the trigger terms read more like what a user would actually say.

Optionally enumerate the concrete artifacts the flow produces (proposal.md, design.md, tasks.md) to lift specificity toward the higher anchor.

DimensionReasoningScore

Specificity

Names the domain ("Comet 预设") and the concrete phase flow ("open-build-verify-archive 短流程") plus one purpose ("修复已有行为 bug"), which is 1-2 concrete actions but not comprehensive. It does not list several distinct concrete actions like the anchor-5 example, and is more specific than the single-action anchor-2 example.

3 / 5

Completeness

Provides a clear "what" (fix existing behavior bugs via the short open-build-verify-archive flow) but no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the rubric guideline. The "when" is only weakly implied, not stated.

3 / 5

Trigger Term Quality

Contains relevant natural keywords ("hotfix", "修复已有行为 bug") a user might say, but also leans on jargon ("Comet 预设", "open-build-verify-archive") and lacks common synonyms or variations, matching the "some relevant keywords but missing variations" anchor. Not enough natural-term coverage for a 4.

3 / 5

Distinctiveness Conflict Risk

The "Comet 预设 —— hotfix" framing carves a clear niche (short bug-fix flow) with minimal conflict against unrelated skills, but it overlaps with closely related sibling Comet skills (e.g. comet-classic), matching the "mostly distinct; minor overlap risk" anchor rather than the conflict-free anchor 5.

4 / 5

Total

13

/

20

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.