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

56%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.

A well-organized stance skill with genuinely concrete OpenSpec integration guidance (commands, artifact paths, capture table). Its weaknesses are verbosity from long illustrative dialogues and a progressive-disclosure structure that inlines example-heavy content rather than splitting it out.

Suggestions

Trim the four extended example dialogues to one or two short exemplars, or move them to a references/examples file, cutting the body's length substantially.

Convert the decorative ASCII box in the "Visualize" section into a one-line instruction; it spends ~15 lines saying "use diagrams".

Condense the stance bullets and "What You Don't Have To Do" into fewer, tighter directives since Claude already understands collaborative exploration behavior.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not explain concepts Claude already knows, but at ~270 lines it carries noticeable padding: four extended sample dialogues (~100 lines), a decorative ASCII box that merely says "use ASCII diagrams liberally", and sections like "What You Don't Have To Do" that could be condensed.

3 / 5

Actionability

Concrete guidance exists ("openspec list --json", artifact paths like "openspec/changes/<name>/proposal.md", and the insight-to-artifact capture table), but the core stance sections ("Curious, not prescriptive", "Patient") are abstract direction rather than executable instruction, leaving guidance incomplete for an instruction-only skill.

3 / 5

Workflow Clarity

The capture workflow is clearly sequenced (read artifacts, reference them naturally, offer to capture, user decides) with an explicit context-check entry step and well-defined ending options; it loses a point only because the deliberately non-workflow framing leaves some transitions implicit.

4 / 5

Progressive Disclosure

The single file is well-sectioned with clear headers, but no bundle files exist and ~100 lines of example dialogues are inlined content that, at this total length, would be better placed in a separate examples reference.

3 / 5

Total

13

/

20

Passed

Description

70%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.

A solid description with an explicit 'Use when...' trigger clause and natural language users would actually say. Its main weakness is that the capability statement is abstract and role-based rather than listing concrete actions.

Suggestions

Replace abstract activity phrases with concrete actions the skill performs (e.g., "asks clarifying questions, maps existing architecture, compares approaches, sketches ASCII diagrams of tradeoffs").

Add common trigger synonyms such as brainstorming, discussing an approach, or evaluating options to broaden natural keyword coverage.

Distinguish the skill from generic brainstorming by signaling the openspec change/proposal context in the description itself.

DimensionReasoningScore

Specificity

The description names the domain and a few activities ("exploring ideas, investigating problems, and clarifying requirements"), but these are abstract activities rather than several concrete capabilities, so it falls short of the comprehensive action list of level 4-5.

3 / 5

Completeness

It explicitly 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"), but the 'what' is role-flavored rather than a concrete capability list, so it does not fully match the level 5 anchor.

4 / 5

Trigger Term Quality

Natural phrases like "think through something" and "before or during a change" would plausibly be said by a user, giving good keyword coverage, though common variations such as "brainstorm", "discuss", or "explore options" are missing, keeping it below level 5.

4 / 5

Distinctiveness Conflict Risk

The "explore mode" framing and "before or during a change" timing carve a mostly distinct niche with explicit triggers, though there is minor overlap risk with generic brainstorming or requirements-clarification skills.

4 / 5

Total

15

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
KunAgent/Kun
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.