comet-open

Comet Phase 1: Open. Invoke with /comet-open. Explore ideas through OpenSpec, confirm requirements clarification, then create change structure (proposal + design + tasks).

Quality

76%

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-open/SKILL.md

Quality

Content

73%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.

A well-sequenced, highly actionable workflow skill with strong validation checkpoints and feedback loops. Its main weakness is moderate verbosity from restated constraints, and the lengthy inlined PRD-split logic that could be factored into a dedicated reference file.

Suggestions

Consolidate the repeated kebab-case naming and "must not create artifacts before confirmation" rules into a single authoritative statement referenced from each step, to reduce restated constraints and trim tokens.

Extract the detailed PRD-split preflight logic (Step 1a) into a dedicated reference file (e.g., references/prd-split.md) and keep only the decision summary and conditions inline, improving both conciseness and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and action-oriented, but the kebab-case naming rule and several "must/must not" constraints are restated across Steps 1c, 2, and the naming guard, and the PRD-split section is lengthy — some repetition could be tightened without losing clarity.	3 / 5
Actionability	It provides concrete executable bash commands with real flags and JSON payloads (openspec status/instructions, comet-env.sh discovery, state init/check, guard --apply), with only minor gaps where it relies on the referenced skills' own guidance rather than inlining specifics.	4 / 5
Workflow Clarity	A clearly numbered 0–5 sequence with multiple explicit blocking-point validation checkpoints (1a/1b/1c, Step 3 verification, Step 4 completeness check, Step 5 confirmation) and feedback loops for error recovery (re-request confirmation on "Needs adjustment", re-run on validation failure, idempotent re-execution), including for the batch PRD-split operation.	5 / 5
Progressive Disclosure	Structure is good with clearly signaled one-level-deep references to external files (comet/reference/decision-point.md, auto-transition.md) and delegation to other skills via the Skill tool; no references/scripts/assets bundle directory exists in this skill, and the inlined PRD-split logic is long enough that it could live in a separate reference file.	4 / 5
	Total	16 / 20 Passed

Description

78%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.

A strong, specific description that names concrete actions and an explicit invocation trigger, with minimal conflict risk. It falls just short of top marks because the "when" guidance is an invoke command rather than a natural trigger condition, and a few natural keyword variations are absent.

Suggestions

Reframe the trigger as an explicit "Use when..." clause (e.g., "Use when starting a new OpenSpec change or when the user wants to explore requirements and create a proposal/design/tasks") so the "when" is a clear condition, not just an invoke command.

Add one or two natural user-facing terms or synonyms (e.g., "new change", "requirements gathering", "proposal") to broaden trigger-term coverage beyond the Comet/OpenSpec jargon.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "Explore ideas through OpenSpec", "confirm requirements clarification", "create change structure (proposal + design + tasks)" — giving good coverage of the phase's outputs with only minor gaps around the underlying OpenSpec mechanics.	4 / 5
Completeness	It clearly answers "what" (explore, confirm requirements, create change structure) and provides an explicit invocation trigger ("Invoke with /comet-open") for "when", but the "when" is a command rather than a fully fleshed-out "Use when..." trigger condition.	4 / 5
Trigger Term Quality	"Invoke with /comet-open" is an explicit trigger and natural terms like "requirements", "proposal", and "explore ideas" appear, though the phrasing leans on jargon ("OpenSpec", "Comet Phase 1") and omits a few common variations.	4 / 5
Distinctiveness Conflict Risk	The description carves a clear niche tied to the specific Comet/OpenSpec workflow and the `/comet-open` invocation with named artifacts, making wrong-skill triggering very unlikely.	5 / 5
	Total	17 / 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-open/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.