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 ./eval/local/skills/benchmarks/dependency/openspec/openspec-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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, actionable stance document grounded in real OpenSpec commands and artifact paths. Its main weaknesses are repetition across the stance/guardrail sections and the absence of any validation/checkpoint flow, which is partly inherent to a non-procedural stance skill.

Suggestions

Consolidate the overlapping 'The Stance', 'What You Don't Have To Do', and 'Guardrails' sections into a single concise list to remove repeated don't-implement/don't-rush themes and trim tokens.

In the 'When a change exists' sub-flow, add an explicit checkpoint such as confirming the change name via `openspec list --json` before reading artifacts, so the one concrete sequence has a clear validation step.

Tighten the illustrative ASCII diagrams to the one or two most representative cases rather than four full dialogue examples, preserving clarity while reducing length.

DimensionReasoningScore

Conciseness

The ~170-line body is mostly efficient and avoids explaining concepts Claude already knows, but the Stance, 'What You Don't Have To Do', and Guardrails sections repeat the same don't-implement/don't-rush themes, so it could be tightened beyond minor trimming.

3 / 5

Actionability

Provides genuinely executable guidance such as `openspec list --json`, concrete artifact paths (proposal.md, design.md, tasks.md), and a capture-location table, plus illustrative dialogue flows; minor gaps remain since much is stance/attitude direction rather than copy-paste runnable steps.

4 / 5

Workflow Clarity

The skill is intentionally 'a stance, not a workflow' with no fixed steps; the most concrete sub-sequence (when a change exists) lists steps but has no validation checkpoints, matching the anchor for steps present with checkpoints missing.

3 / 5

Progressive Disclosure

No bundle files exist and none are needed; the single self-contained document is well-organized with clear section headers and easy navigation, satisfying the simple-skill exception for a clean, reference-free stance skill.

5 / 5

Total

15

/

20

Passed

Description

62%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 is well-formed: third-person voice, explicit 'Use when' trigger, and a clear stance niche. It is held back from the top band by action language that is more abstract than concrete and a somewhat narrow set of trigger keywords.

DimensionReasoningScore

Specificity

Names the domain ('explore mode', 'thinking partner') and a few actions ('exploring ideas, investigating problems, clarifying requirements'), but the actions are conceptual rather than a comprehensive list of concrete operations, matching the anchor for 1-2 concrete actions.

3 / 5

Completeness

Clearly states both what it does ('a thinking partner for exploring ideas, investigating problems, and clarifying requirements') and when to use it ('Use when the user wants to think through something before or during a change'); the when-clause is explicit but could be slightly more specific.

4 / 5

Trigger Term Quality

Includes relevant natural phrases like 'explore', 'think through something', and 'before or during a change', but the vocabulary is narrow and misses common synonyms or variations a user might say.

3 / 5

Distinctiveness Conflict Risk

'Explore mode / thinking partner' is a mostly distinct niche unlikely to trigger for implementation skills, though 'exploring ideas, investigating problems' is broad enough to overlap with general brainstorming skills.

4 / 5

Total

14

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
rpamis/comet
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.