comet-verify

Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.

Quality

75%

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-verify/SKILL.md

Quality

Content

88%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 a well-structured, highly actionable verification workflow with explicit checkpoints and feedback loops, suffering only from minor verbosity and a long single-file form that could offload some detail to reference files.

Suggestions

Move the repeated dirty-worktree / decision-point / spec-drift handling prose into the already-referenced comet/reference/*.md files and keep only the decision rule inline to tighten conciseness.

De-duplicate the verify-fail transition command block by defining it once and referencing it from Steps 1, 1b, and 2b.

Consider extracting the lightweight vs. full verification checklists (2a/2b) into a bundled reference file so the SKILL.md body reads as a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is dense but almost every line is actionable workflow detail rather than concepts Claude already knows; minor repetition of the verify-fail transition command and some verbose notes could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready bash commands with clear '<change-name>' placeholders, concrete decision rules, and explicit state-management invocations covering the common cases.	5 / 5
Workflow Clarity	Steps are clearly sequenced (0a -> 0b -> 1 -> 1b -> 2 -> 2a/2b -> 3 -> 4) with explicit validation checkpoints, a blocking decision point, retry-limit feedback loop, and pass criteria — matching the anchor with feedback loops for error recovery.	5 / 5
Progressive Disclosure	Good section structure with clearly signaled one-level-deep references (comet/reference/dirty-worktree.md, decision-point.md, auto-transition.md, context-recovery.md); no bundle files exist, and the single-file body is fairly long for a monolithic overview.	4 / 5
	Total	18 / 20 Passed

Description

62%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 niche-specific with an explicit invocation trigger, but its action list is brief and the 'when' guidance leans on a command rather than natural trigger situations.

Suggestions

Add 1-2 more concrete actions (e.g., 'run scale-based verification checks, record verification evidence') to lift specificity toward comprehensive coverage.

Expand the trigger clause beyond the slash command to natural situations, e.g., 'Use when finishing a Comet change after build, to verify implementation against design and handle the development branch.'

Include synonyms users might say ('verify a change', 'close out a phase', 'finish a development branch') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Comet Phase 4: Verify and Close') and two concrete actions ('Verify implementation matches design', 'handle development branch'), matching the anchor for 1-2 concrete actions but not comprehensive coverage.	3 / 5
Completeness	Clearly states what the skill does and provides an explicit trigger ('Invoke with /comet-verify'); the 'when' is present but could be more situationally specific rather than only a command.	4 / 5
Trigger Term Quality	Includes the relevant term 'verify' and an explicit invocation trigger ('Invoke with /comet-verify'), but lacks common variations or synonyms a user might naturally say.	3 / 5
Distinctiveness Conflict Risk	The 'Comet Phase 4' framing gives it a clear niche with a distinct slash-command trigger, with only minor overlap risk against generic verification skills.	4 / 5
	Total	14 / 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-verify/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.