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.

82

1.04x
Quality

75%

Does it follow best practices?

Impact

94%

1.04x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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.

An effective instruction-only stance skill with concrete commands, paths, and a useful capture table, plus a clear (if deliberately non-linear) structure. Its main weakness is verbosity from extended example dialogues and ASCII art that could be trimmed.

Suggestions

Trim the multi-line example transcripts in 'Handling Different Entry Points' to one or two representative samples rather than four full dialogues, to reduce padding.

Condense the large decorative ASCII diagram in the 'Visualize' section to a compact example, keeping the visualization guidance without the box-art overhead.

Consider splitting the entry-point examples into a separate reference file so the core stance and capture-table guidance stay lean in SKILL.md.

DimensionReasoningScore

Conciseness

The guidance is mostly efficient and assumes Claude's competence, but the lengthy illustrative transcripts in 'Handling Different Entry Points' and repeated ASCII diagrams pad the body beyond what earns its place; it could be tightened without losing clarity, so it sits at the midpoint rather than the lean 4-5 band.

3 / 5

Actionability

Provides concrete, executable guidance — a real command (`openspec list --json`), specific artifact paths, and a capture table mapping insight types to files — with only minor gaps, fitting the 'mostly executable' anchor below copy-paste-ready 5.

4 / 5

Workflow Clarity

Deliberately declares itself a stance rather than a workflow, and the 'When a change exists' branch gives a clear numbered sequence with an explicit 'The user decides' checkpoint; no destructive or batch operations require validation loops, so it clears the cap and lands just below the fully-explicit 5.

4 / 5

Progressive Disclosure

A single self-contained file with well-organized, clearly headed sections and no external references; the long inline example transcripts are a minor organization gap that keeps it below the cleanly-split 5.

4 / 5

Total

15

/

20

Passed

Description

83%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 strong description that clearly states both capability and trigger conditions in third person with concrete actions. It is comprehensive on completeness and only slightly under-develops synonym coverage and distinctiveness.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions — 'exploring ideas, investigating problems, and clarifying requirements' — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive 5.

4 / 5

Completeness

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') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ('think through something', 'explore', 'investigating problems', 'before or during a change') with good but not exhaustive synonym coverage, placing it just below the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The 'explore mode' niche is mostly distinct with clear triggers, though the broad 'thinking partner' framing carries minor overlap risk with general conversational help, keeping it below the minimal-conflict 5.

4 / 5

Total

17

/

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
arm/mlia
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.