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

65%

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 ./skills/openspec-explore/SKILL.md

Quality

Content

67%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 pairs a strong, concrete OpenSpec capture workflow with executable CLI commands, but balances it against verbose stance philosophy and dense paragraph-form workflow steps that hurt readability. Structure is clean with no bundle files needed.

Suggestions

Trim the stance philosophy and decorative ASCII banners to lift conciseness toward anchor 4-5; Claude already understands exploratory thinking stances.

Break the dense paragraph steps 2-4 of the capture workflow into shorter bullet/numbered sub-steps with explicit validation checkpoints to push workflow_clarity to 5.

Consider moving the four long worked-example conversations into a separate examples reference file to improve progressive disclosure and reduce inline bulk.

Dimension	Reasoning	Score
Conciseness	The operational CLI guidance is efficient, but stance philosophy Claude already understands ('This is a stance, not a workflow', six stance bullets) and decorative ASCII banners/boxes add padding; fits 'mostly efficient but includes some unnecessary explanation or could be tightened'.	3 / 5
Actionability	Provides copy-paste-ready commands with explicit flag and store semantics (openspec list/new change/status/instructions) and a concrete capture workflow, but roughly half the body is non-executable stance philosophy, keeping it at 'mostly executable guidance with minor gaps' rather than fully executable throughout.	4 / 5
Workflow Clarity	The capture workflow is explicitly numbered 1-4 with dependency ordering, validation via re-running status, and conditional-skip handling; held below 5 because steps 2-4 are dense ~150-word paragraphs that obscure the sequence and checkpoints.	4 / 5
Progressive Disclosure	No bundle files exist; content is well-organized under clear section headers (The Stance, OpenSpec Awareness, Handling Different Entry Points, Guardrails) which suffices for a no-bundle skill, though the four long ASCII worked examples could be split out, so it is not the maximally-split anchor 5.	4 / 5
	Total	15 / 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 cleanly states both what the skill does and when to use it with a natural trigger phrase, placing it above average. It is held back by abstract thinking-verbs rather than concrete operations and limited synonym coverage.

Suggestions

Add concrete operational verbs (e.g., 'brainstorm approaches, map architecture, compare options') to lift specificity toward anchor 4-5.

Expand trigger terms with common synonyms users say ('brainstorm', 'work through', 'explore options') for better keyword coverage.

Sharpen the 'what' to concrete deliverables (e.g., 'produces diagrams, option comparisons, and OpenSpec change proposals') to push completeness to 5.

Dimension	Reasoning	Score
Specificity	Names the domain and three activities ('exploring ideas, investigating problems, clarifying requirements') but these are abstract thinking-verbs rather than concrete discrete operations, matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor; not a 4 because the actions are generic and non-operational.	3 / 5
Completeness	Explicitly answers both what ('thinking partner for exploring ideas, investigating problems, clarifying requirements') and when ('Use when the user wants to think through something before or during a change'); the 'what' is slightly soft so it does not reach the fully concrete anchor 5.	4 / 5
Trigger Term Quality	Includes the natural phrase 'think through something' and 'before or during a change', but misses common synonyms users would say (brainstorm, explore, work through); fits 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The 'explore mode / thinking partner' framing carves a distinct niche from implementation skills with minimal conflict risk, though 'investigating problems' could overlap with debugging skills, so it is not the fully-distinct anchor 5.	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: Fission-AI/OpenSpec
Path: skills/openspec-explore/SKILL.md
Commit: 6926ccb

Reviewed: about 17 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.