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.

76

1.04x
Quality

64%

Does it follow best practices?

Impact

94%

1.04x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.codex/skills/openspec-explore/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-conceived skill that clearly defines an exploratory thinking mode with strong guardrails (no implementation). Its main weakness is verbosity—the extensive example dialogues, while helpful for illustrating the stance, consume significant tokens and could be condensed. The OpenSpec integration section is the most actionable and well-structured part, while the rest is more illustrative than instructive.

Suggestions

Condense the example dialogues significantly—keep one or two brief examples and move the rest to a separate EXAMPLES.md file to improve both conciseness and progressive disclosure.

Tighten the 'What You Might Do' section by removing the ASCII diagram example (which is meta—showing a diagram about using diagrams) and relying on the examples section to demonstrate visualization.

DimensionReasoningScore

Conciseness

The skill is reasonably well-written but is verbose for what it communicates. The extensive example dialogues with ASCII art, while illustrative, are lengthy and could be condensed. The 'What You Don't Have To Do' section and some repeated emphasis on 'don't implement' add bulk. However, much of the content does earn its place since this is a stance/mode definition rather than a procedural skill.

2 / 3

Actionability

The skill provides some concrete guidance (bash commands like `openspec list --json`, file paths to read, a table mapping insight types to artifacts) but is largely descriptive of a stance rather than prescriptive. The example dialogues show what explore mode looks like but aren't executable instructions—they're illustrative scenarios. The OpenSpec integration section is the most actionable part.

2 / 3

Workflow Clarity

This skill explicitly declares itself as 'a stance, not a workflow' with no fixed steps or required sequence, which is appropriate for its purpose. The content is clear about what to do (think, visualize, investigate) and what not to do (implement, auto-capture). The OpenSpec awareness section provides clear conditional workflows (when no change exists vs. when one exists). For this type of skill, the clarity is excellent.

3 / 3

Progressive Disclosure

The content is entirely self-contained in one file with no bundle files. While the sections are well-organized with clear headers, the extensive example dialogues and ASCII art make this a long document that could benefit from splitting examples into a separate reference file. The OpenSpec artifact paths are referenced but there are no linked supporting documents.

2 / 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 has good structural completeness with an explicit 'Use when...' clause, but the capabilities described are abstract and conceptual rather than concrete and specific. The trigger terms are reasonable but could be broader to capture more natural user language, and the skill's scope is broad enough that it could conflict with planning, debugging, or design-oriented skills.

Suggestions

Add more concrete examples of what 'explore mode' actually does differently from normal interaction, e.g., 'Asks clarifying questions, maps trade-offs, outlines options before committing to implementation'.

Expand trigger terms with natural user phrases like 'brainstorm', 'think about', 'figure out', 'plan', 'not sure how to approach', 'weigh options'.

Sharpen distinctiveness by specifying what kinds of 'changes' this applies to and how it differs from skills that also involve investigation or analysis.

DimensionReasoningScore

Specificity

Names the domain ('thinking partner') and some actions ('exploring ideas, investigating problems, clarifying requirements'), but these are fairly abstract and not concrete actions like 'extract text' or 'fill forms'. The actions described are more conceptual than operational.

2 / 3

Completeness

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'). The 'Use when...' clause is explicit.

3 / 3

Trigger Term Quality

Includes some relevant terms like 'explore', 'thinking', 'ideas', 'problems', 'requirements', but misses common natural variations users might say such as 'brainstorm', 'discuss', 'figure out', 'plan', 'design', 'what should I do', 'help me decide'. The phrase 'explore mode' is somewhat jargon-like.

2 / 3

Distinctiveness Conflict Risk

The concept of 'thinking through something' and 'exploring ideas' is fairly broad and could overlap with many other skills that involve planning, design, or analysis. The trigger 'before or during a change' helps narrow it somewhat, but 'investigating problems' could conflict with debugging or troubleshooting skills.

2 / 3

Total

9

/

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.

Validation11 / 11 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.