openspec-explore

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

Quality

58%

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/dependency/openspec/openspec-explore/SKILL.md

Quality

Content

50%

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

The body is well-structured and includes some genuinely actionable OpenSpec operational guidance, but it is verbose with recurring redundancy and leans heavily on stance philosophy over concrete instruction.

Suggestions

Consolidate the repeated stance guidance — merge 'What You Don't Have To Do', 'The Stance', and 'Guardrails' so 'don't implement' and the philosophy appear once.

Move the four long entry-point example dialogues into a reference file and keep only one representative example inline.

Tighten the OpenSpec Awareness section into the concrete command, file paths, and capture table, trimming the surrounding prose.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but it is ~280 lines with notable redundancy — 'don't implement' and the stance philosophy recur across the IMPORTANT note, 'The Stance', 'Guardrails', and 'What You Don't Have To Do'.	2 / 3
Actionability	Concrete operational guidance exists (the `openspec list --json` command, specific artifact paths, and the insight-to-artifact capture table), but the bulk is stance philosophy rather than executable instruction.	2 / 3
Workflow Clarity	The 'When a change exists' section gives a clear numbered 1-4 sequence and there is an explicit context check, but the skill deliberately has no fixed workflow and offers no validation checkpoints for its sub-processes.	2 / 3
Progressive Disclosure	It is a single self-contained file with clear section headers and no external references, but at ~280 lines the lengthy example-dialogue blocks are inline content that could be separated, so it is not fully lean.	2 / 3
	Total	8 / 12 Passed

Description

67%

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 cleanly states both purpose and an explicit use-when trigger, but its actions are abstract and its triggers are generic enough to risk overlap with other skills.

Suggestions

Replace abstract verbs ('exploring ideas', 'investigating problems') with more concrete, distinguishable actions to lift specificity.

Add more natural trigger variations users would actually say (e.g. 'brainstorm', 'talk through', 'spike an idea') to improve trigger coverage.

Tie the trigger more tightly to the OpenSpec workflow so it conflicts less with general thinking assistance.

Dimension	Reasoning	Score
Specificity	It names several actions ('exploring ideas, investigating problems, and clarifying requirements') but they are abstract conceptual activities rather than the concrete operations the top anchor requires.	2 / 3
Completeness	It explicitly answers what it does ('a thinking partner for exploring ideas...') and when to use it ('Use when the user wants to think through something...'), satisfying both halves with an explicit trigger.	3 / 3
Trigger Term Quality	The 'Use when the user wants to think through something before or during a change' clause is a natural trigger, but the keyword set is fairly generic and lacks common variations, so it does not reach full coverage.	2 / 3
Distinctiveness Conflict Risk	'Enter explore mode' gives it a niche, but the triggers ('think through something', 'explore ideas') are broad and would overlap with general conversation and many other skills.	2 / 3
	Total	9 / 12 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/dependency/openspec/openspec-explore/SKILL.md
Commit: 2945693

Reviewed: about 9 hours 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.