comet-hotfix

Comet preset path: Bug fix / hotfix. Skip brainstorming, directly open → build → verify → archive. Applicable for behavior fixes, scenarios not involving new capability design.

Quality

78%

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 ./eval/local/skills/benchmarks/039-release/comet-classic-039-hotfix/SKILL.md

Quality

Content

81%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 tightly written orchestration skill with concrete commands, a clearly sequenced workflow, and strong validation/feedback checkpoints. Its main weaknesses are minor repetition and deferral of execution detail to loaded sub-skills plus external reference files that are not link-formatted.

Suggestions

Consolidate the repeated 'open → build → verify → archive' chain and the 'Skipping this step is prohibited' phrasing into a single stated convention to trim redundancy.

Format reference paths as markdown links (e.g., [debug-gate.md](comet/reference/debug-gate.md)) and note the comet-skill installation dependency so navigation is unambiguous.

For steps that defer to sub-skills, inline the one or two concrete commands a user needs to issue so the skill is more copy-paste-ready when the sub-skill is unavailable.

Dimension	Reasoning	Score
Conciseness	Operational and free of concept explanation Claude already knows, but repeats the execution chain and the 'Skipping this step is prohibited' sentence across steps; minor trimming possible, so not a 5.	4 / 5
Actionability	Provides concrete, executable bash (comet-env sourcing, '$COMET_BASH $COMET_STATE init', phase guards, commit format 'fix: <brief fix description>') and specific paths; minor gaps arise where steps defer to loaded sub-skills ('follow its guidance'), keeping it below fully copy-paste-ready.	4 / 5
Workflow Clarity	A clearly sequenced 6-step process (0-5) with explicit validation checkpoints (root-cause elimination check, phase guards with --apply, verify_result: pass before archive, NEXT: auto/manual/done) and feedback loops (root cause not eliminated → return to step 2; failures → systematic-debugging), matching the top anchor.	5 / 5
Progressive Disclosure	Well-structured overview that delegates detailed protocols to one-level-deep references (comet/reference/debug-gate.md, dirty-worktree.md, decision-point.md, auto-transition.md); references are backtick paths to the external parent comet skill rather than clickable links, so below the 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

75%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 concise and does a good job stating both the workflow (open→build→verify→archive) and the applicability boundary (behavior fixes, no new capability). It falls just short of top marks because the 'when' phrasing is 'Applicable for' rather than an explicit 'Use when...' trigger and keyword coverage could include a few more synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('Bug fix / hotfix') and several concrete actions via the chain 'open → build → verify → archive' plus the 'Skip brainstorming' directive; not quite a comprehensive enumeration of distinct operations, so below the 5 anchor.	4 / 5
Completeness	States both what ('directly open → build → verify → archive') and when ('Applicable for behavior fixes, scenarios not involving new capability design'); the 'when' uses 'Applicable for' rather than a crisp 'Use when...' with concrete triggers, so below 5.	4 / 5
Trigger Term Quality	Includes natural terms a user would actually say ('Bug fix', 'hotfix', 'behavior fixes'); a few synonyms like 'patch', 'defect', or 'regression' are missing, keeping it below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clearly carves a hotfix niche and explicitly excludes 'new capability design' to distinguish from full /comet; minor overlap risk remains with the closely related comet-build/verify/archive skills it reuses.	4 / 5
	Total	16 / 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: eval/local/skills/benchmarks/039-release/comet-classic-039-hotfix/SKILL.md
Commit: 899d1fb

Reviewed: 7 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.