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

57%

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

48%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 well-organized as a stance definition and includes some concrete commands and paths, but it is noticeably verbose with redundant sections and illustrative-only examples, and it keeps all material inline with no progressive disclosure to supporting files.

Suggestions

Consolidate the redundant stance material ('The Stance', 'What You Don't Have To Do', 'Guardrails') into a single concise section and trim one or two of the full dialogue examples to reduce padding.

Move the long worked examples and the insight-capture table into a references/ file (e.g. EXAMPLES.md) and link to it from a short overview, enabling one-level-deep progressive disclosure.

Convert at least one illustrative dialogue into a concrete, copy-paste-ready command or step sequence to raise actionability.

Dimension	Reasoning	Score
Conciseness	The ~290-line body restates the same stance points across 'The Stance', 'What You Might Do', 'Guardrails', and 'What You Don't Have To Do', and repeats the no-implementation rule several times; the multiple full example dialogues and large ASCII diagrams add noticeable padding beyond what Claude already needs.	2 / 5
Actionability	Most guidance is stance-oriented rather than executable, but it does include concrete commands ('openspec list --json'), specific artifact paths, and a capture-location table; the dialogue examples are illustrative rather than copy-paste ready, leaving it below the executable score-4 anchor.	3 / 5
Workflow Clarity	It explicitly declares 'a stance, not a workflow' and provides a clear numbered 4-step sequence for the 'when a change exists' branch; the skill is non-destructive so the validation-cap does not apply, though the overall workflow is intentionally loose which keeps it just below a score-5.	4 / 5
Progressive Disclosure	No bundle files exist and all content (large example dialogues, the capture table, ASCII diagrams) is inlined in a single SKILL.md; section headers provide some structure, but material that clearly belongs in separate reference files is not split out.	3 / 5
	Total	12 / 20 Passed

Description

66%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 clearly states both what the skill does and when to use it with natural trigger language, but its capabilities are framed as abstract stances rather than concrete actions and the triggers are broad enough to risk overlap with general reasoning skills.

Suggestions

Replace abstract stance verbs with a couple of concrete operational actions (e.g., 'maps existing architecture, sketches tradeoffs and ASCII diagrams, surfaces risks') to lift specificity.

Tighten the 'Use when' clause with more pointed trigger phrases (e.g., 'before starting a change', 'when a problem feels unclear', 'when comparing approaches') to reduce overlap with generic reasoning.

Add a distinctive keyword or scope qualifier (e.g., 'OpenSpec explore mode') so it is less likely to fire for unrelated brainstorming.

Dimension	Reasoning	Score
Specificity	Names the domain and several activities ('exploring ideas, investigating problems, and clarifying requirements'), but these are abstract mental stances rather than concrete operational actions like the score-4/5 anchors require.	3 / 5
Completeness	Answers both 'what' (a thinking partner for exploring/investigating/clarifying) and 'when' ('Use when the user wants to think through something before or during a change'); the 'when' is explicit but not as crisply enumerated with concrete trigger phrases as a score-5 example.	4 / 5
Trigger Term Quality	Includes natural phrases users would say ('think through something', 'exploring ideas', 'investigating problems', 'clarifying requirements') with good coverage, though it lacks synonym variants and explicit keyword enumerations of a score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	'Explore mode' is a recognizable niche distinct from implementation skills, but the trigger phrasing ('think through something', 'explore ideas') is broad enough to overlap with general reasoning or planning skills, so it does not reach the minimal-conflict score-4/5 anchors.	3 / 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: PBH-BTN/PeerBanHelper
Path: .claude/skills/openspec-explore/SKILL.md
Commit: f8e9b1b

Reviewed: 3 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.