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

71%

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 ./.claude/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 is a well-structured, actionable instruction set for a thinking-partner stance with concrete commands, paths, and example transcripts. Its main weakness is conciseness: repeated guardrails and large illustrative blocks inflate the token budget for what is notionally a single-purpose skill.

Suggestions

Consolidate the guardrails so each rule (e.g. "don't implement") appears once; the IMPORTANT block, OpenSpec Awareness, and Guardrails sections currently restate the same constraints.

Move the long example dialogue transcripts and the ASCII diagram gallery into a separate references file, keeping the SKILL.md overview to the stance and core OpenSpec-awareness guidance.

Tighten the capture-location table and "What You Might Do" lists by merging near-duplicate bullets to reduce repetition.

Dimension	Reasoning	Score
Conciseness	The core prose is efficient, but ~278 lines for a single-purpose stance skill repeats guardrails across the IMPORTANT block, OpenSpec Awareness, and Guardrails sections, and the ASCII diagram gallery plus long transcript examples consume notable tokens.	3 / 5
Actionability	Provides concrete executable guidance for a non-code skill: the `openspec list --json` command, specific artifact paths, a capture-location table, and example dialogue transcripts showing what to say.	4 / 5
Workflow Clarity	Explicitly framed as a stance rather than a workflow, but the "when a change exists" path is a clear 4-step sequence with the "user decides / don't auto-capture" checkpoint; destructive code operations are disallowed, so validation loops are largely N/A.	4 / 5
Progressive Disclosure	Self-contained single file with well-organized section headers and clear navigation, though some lengthy inline example transcripts and the ASCII diagram gallery could be externalized to trim the overview.	4 / 5
	Total	15 / 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, third-person, and covers both what the skill does and when to use it with a natural trigger phrase. It is solid and specific, sitting comfortably above the midpoint but short of fully comprehensive concrete-action or trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and three concrete cognitive actions ("exploring ideas, investigating problems, and clarifying requirements"), with only minor gaps since these are modes rather than discrete operations.	4 / 5
Completeness	Clearly states what it does (thinking partner for explore/investigate/clarify) and when to use it ("Use when the user wants to think through something before or during a change"), though the "what" is somewhat abstract.	4 / 5
Trigger Term Quality	Includes a natural phrase users would say ("the user wants to think through something") plus relevant terms, but misses common synonyms like brainstorm, spike, or design discussion.	4 / 5
Distinctiveness Conflict Risk	"Explore mode" / thinking partner is a reasonably distinct niche anchored to the change workflow, with only minor overlap risk against generic analysis/brainstorming skills.	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: dwmkerr/openspec-flow
Path: .claude/skills/openspec-explore/SKILL.md
Commit: e670a56

Reviewed: 4 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.