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

62%

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

57%

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-organized, self-contained stance skill with concrete OpenSpec command guidance and a clear capture table, and its sectioning aids navigation. Its weaknesses are token-heavy inline example transcripts and guidance that is largely attitudinal rather than executable, with no validation checkpoints.

Suggestions

Trim or condense the multi-line example dialogue transcripts and ASCII diagrams to reduce token load without losing the stance illustration.

Add a lightweight validation/checkpoint cue (e.g., confirming a store id resolved or that a referenced artifact exists before relying on it) to strengthen the change-exists workflow.

Consider moving the four long entry-point examples into a short reference file to better separate overview from illustrative detail.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but the lengthy inline example transcripts and large ASCII art blocks (collaboration spectrum, auth flow, CLI storage) could be tightened, matching the "mostly efficient but could be tightened" anchor.	2 / 3
Actionability	Concrete guidance is present (specific commands like `openspec status --change`, named JSON fields, and an insight-to-artifact capture table), but a substantial portion of the skill is attitudinal stance guidance rather than executable instruction, so it does not reach fully actionable.	2 / 3
Workflow Clarity	The "When a change exists" section gives a clear numbered 4-step sequence, but the skill deliberately rejects fixed workflows overall and includes no validation checkpoints, matching the "steps listed but checkpoints missing" anchor.	2 / 3
Progressive Disclosure	No bundle files exist and none are needed for this self-contained stance skill; the body is organized into clearly headed, separator-delimited sections (Stance, What You Might Do, OpenSpec Awareness, Entry Points, Guardrails) that make navigation easy, fitting the well-organized top anchor.	3 / 3
	Total	9 / 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 answers both what the skill does and when to use it with an explicit trigger, which is its main strength. It is held back by somewhat abstract action language and a trigger/keyword set that could overlap with generic thinking skills.

Suggestions

Replace abstract verbs ("exploring ideas", "clarifying requirements") with more concrete, distinctive actions to lift specificity.

Broaden trigger coverage with natural variations users would actually say (e.g., "brainstorm", "talk through", "spike", "think out loud").

Tie the trigger more tightly to the OpenSpec change context to reduce overlap with generic brainstorming skills.

Dimension	Reasoning	Score
Specificity	It names the domain and several actions ("exploring ideas, investigating problems, and clarifying requirements"), but these are abstract mental activities rather than the concrete operations the top anchor exemplifies, so it falls short of a 3.	2 / 3
Completeness	It clearly answers both what ("a thinking partner for exploring ideas, investigating problems, and clarifying requirements") and when ("Use when the user wants to think through something before or during a change") with an explicit trigger clause.	3 / 3
Trigger Term Quality	"think through something" is a natural phrase a user might say, but the overall keyword coverage is narrow with few common variations, matching the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	"before or during a change" anchors a niche, but "thinking partner for exploring ideas" is generic enough to overlap with general brainstorming/thinking skills, matching the "somewhat specific but could still overlap" anchor.	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: Fission-AI/OpenSpec
Path: skills/openspec-explore/SKILL.md
Commit: 6a5171e

Reviewed: 5 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.