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

73%

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, self-contained stance skill with genuinely actionable elements (a context command, artifact paths, and a capture mapping table) and clear navigation. Its weaknesses are verbosity from repeated principles and four elaborate ASCII example dialogues, and behavioral guidance that is not always concretely executable.

Suggestions

Dedupe the overlapping principles across "The Stance", "What You Don't Have To Do", and "Guardrails" into a single list to reclaim token budget.

Trim the four full ASCII-dialogue examples to two representative ones; the stance is conveyed without all four.

Consider moving the extended example dialogues into a separate references file (e.g., EXAMPLES.md) so the main body stays a lean overview, which would also lift progressive_disclosure toward anchor 5.

Dimension	Reasoning	Score
Conciseness	It assumes Claude's intelligence (no concept explanations) and the ASCII diagrams demonstrate the core visualization stance, but four elaborate example dialogues plus principles repeated across "The Stance", "What You Don't Have To Do", and "Guardrails" are padding that could be tightened, matching anchor 3.	3 / 5
Actionability	Provides concrete executable elements (`openspec list --json`, specific artifact paths like `openspec/changes/<name>/proposal.md`, and an insight-type-to-artifact capture table), but much of the guidance is behavioral ("challenge assumptions", "be curious") rather than fully executable, fitting anchor 4.	4 / 5
Workflow Clarity	A clear overall flow (check context → no-change / change-exists branch → numbered read/reference/capture/decide steps → ending discovery) is present; the skill is non-destructive so no validation checkpoints are required, but it is a multi-section stance rather than a single unambiguous action, keeping it at anchor 4.	4 / 5
Progressive Disclosure	Well-organized with clear section headers, self-contained with no nested or buried references and easy navigation; minor organization gaps (principle repetition across sections, four large inline dialogues) prevent it from reaching anchor 5.	4 / 5
	Total	15 / 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.

The description cleanly answers both what the skill does and when to use it, with an explicit "Use when..." clause and natural trigger phrases. Its main weakness is that the named activities are abstract behavioral descriptors rather than concrete operations, and "think through something" is broad enough to risk minor overlap with general thinking skills.

Suggestions

Sharpen the "what" with more concrete, distinguishable verbs (e.g., "maps architecture, surfaces integration points, sketches tradeoffs") instead of the abstract "exploring ideas, investigating problems".

Add a synonym or two to the trigger clause (e.g., "brainstorm" or "talk through") to broaden natural-term coverage and reduce overlap ambiguity with generic thinking helpers.

Dimension	Reasoning	Score
Specificity	Names three activities ("exploring ideas, investigating problems, and clarifying requirements") but these are abstract behavioral descriptors rather than concrete operations, matching anchor 3's "1-2 concrete actions, not comprehensive" better than anchor 4's technical-action examples.	3 / 5
Completeness	Clearly states the "what" ("a thinking partner for exploring ideas, investigating problems, and clarifying requirements") and an explicit "Use when the user wants to think through something before or during a change" trigger, matching anchor 5's structure.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ("think through something", "explore mode", "before or during a change") with good coverage, but lacks comprehensive synonyms like "brainstorm" or "talk through", falling short of anchor 5.	4 / 5
Distinctiveness Conflict Risk	"Enter explore mode" carves a distinct niche, but the trigger "think through something" is broad enough to carry minor overlap risk with general brainstorming skills, so it does not reach anchor 5's "minimal conflict risk."	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/livedown
Path: .claude/skills/openspec-explore/SKILL.md
Commit: db0bd53

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.