CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/openspec-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 into clear sections with a few concrete anchors (a command, file paths, a capture table), but it is verbose for a stance skill — heavy on illustrative example dialogues and ASCII art — and monolithic with no progressive disclosure to reference files. Tightening the examples and splitting detail out would lift the weaker dimensions.

Suggestions

Trim the four multi-line example dialogues to one or two compact illustrations; the ASCII diagrams and full transcripts pad the token budget without adding proportionate guidance.

Extract the OpenSpec capture table and artifact-path reference into a separate file (e.g., references/capture.md) and link to it, giving the overview lean progressive-disclosure structure.

Convert 'you might do' stance lists into more imperative, concrete guidance so the actionability moves from illustrative to instructive.

DimensionReasoningScore

Conciseness

The ~300-line body is padded with four lengthy example dialogues and large ASCII diagrams that illustrate rather than instruct, though it avoids explaining basic concepts Claude already knows — fitting the 'mostly efficient but could be tightened' anchor.

2 / 3

Actionability

It offers some concrete guidance (the `openspec list --json` command, explicit artifact paths, and an insight-to-file capture table) but the bulk is 'you might do' illustrative stance material rather than direct, executable instruction.

2 / 3

Workflow Clarity

The skill explicitly disclaims a fixed workflow ('This is a stance, not a workflow'), and while entry-point handling and guardrails are organized with a 4-step 'when a change exists' sequence, there are no validation checkpoints and process clarity is moderate rather than crisp.

2 / 3

Progressive Disclosure

The body is a well-sectioned but monolithic single file (~300 lines) with no external reference files at all, matching the anchor for structure present but content that could be split remaining inline.

2 / 3

Total

8

/

12

Passed

Description

77%

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 capabilities and an explicit trigger, with concrete named actions. Its main weakness is distinctiveness and trigger specificity — 'thinking partner' and 'think through something' are generic enough to risk overlapping with other skills or firing broadly.

Suggestions

Sharpen the trigger with more distinctive phrasing (e.g., 'Use when the user wants to brainstorm, compare approaches, or think through a problem before committing to a change') to reduce overlap with general conversational skills.

Tie the 'when' clause more tightly to the OpenSpec lifecycle the body describes (e.g., 'before starting a change with /opsx:new or /opsx:ff') to strengthen distinctiveness.

Consider adding a negative boundary in the description (e.g., 'for thinking, not implementing') so it is less likely to trigger for implementation requests.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'exploring ideas, investigating problems, and clarifying requirements' — matching the anchor for naming several specific activities rather than vague abstractions.

3 / 3

Completeness

Explicitly answers both what it does ('a thinking partner for exploring ideas...') and when to use it ('Use when the user wants to think through something before or during a change'), satisfying the explicit 'Use when...' clause requirement.

3 / 3

Trigger Term Quality

'think through something' and 'explore ideas' are natural user phrases, but the terms are fairly generic and miss common variations like 'brainstorm' or 'compare options'; not the comprehensive coverage of a 3.

2 / 3

Distinctiveness Conflict Risk

'thinking partner for exploring ideas' is a broad conversational mode that could overlap with many skills; the 'before or during a change' qualifier narrows it somewhat but it remains a somewhat generic niche.

2 / 3

Total

10

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
PBH-BTN/PeerBanHelper
Reviewed

Table of Contents

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.