explore

See what's in the opportunity space, notice gaps, and generate options to fill them. Handles both graph viewing and divergent generation (brainstorming). These are a continuum, not separate activities.

Quality

35%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./discovery/skills/explore/SKILL.md

Quality

Content

70%

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-organized skill that excels at progressive disclosure and workflow clarity, with clear sequencing, validation checkpoints, and well-signaled references to deeper content. Its main weaknesses are moderate verbosity in philosophical/stance framing and a lack of concrete executable examples — the actionable details are largely deferred to referenced files rather than demonstrated inline.

Suggestions

Add a concrete example of a brainstorming interaction (e.g., sample PM request → graph check → generated output) to make the skill more actionable without requiring reference file lookups.

Trim the 'Your Stance' section to 1-2 sentences — the philosophical framing about abundance vs. precision is personality coaching that Claude can infer from the behavioral instructions.

Dimension	Reasoning	Score
Conciseness	The content includes some philosophical framing ('generative, expansive face of the discovery system', 'biased toward producing possibilities, toward abundance rather than precision') that is more about stance/personality than actionable instruction. The 'What Explore Does NOT Do' section and the stance section could be tightened, but overall it's not egregiously verbose.	2 / 3
Actionability	The skill provides clear conceptual guidance (bottom-up entry flow, transition triggers, saving artifacts workflow) but lacks concrete executable examples — no code, no specific commands, no template outputs. The actual 'how to brainstorm' and 'how to navigate the graph' are deferred entirely to referenced files, leaving the main skill somewhat abstract.	2 / 3
Workflow Clarity	The multi-step flow is clearly sequenced: read graph first → notice gaps → brainstorm to fill them. The saving artifacts section includes an explicit confirmation checkpoint ('Always confirm before saving'). Transitions to other skills are clearly enumerated with trigger conditions. The bottom-up entry path provides a clear alternative sequence with tracing steps.	3 / 3
Progressive Disclosure	Content is well-structured as an overview with clear one-level-deep references to navigate.md, brainstorm.md, and per-type artifact references (objective.md, opportunity.md, idea.md). References are well-signaled with context about what each contains. However, since no bundle files were provided, we cannot verify these paths exist, but the structure itself is exemplary.	3 / 3
	Total	10 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is too abstract and jargon-heavy to be useful for skill selection. It lacks concrete actions, natural trigger terms, and any explicit guidance on when Claude should select it. The language reads more like a philosophical framing than a functional skill description.

Suggestions

Replace abstract language with concrete actions — specify what 'viewing the opportunity space' and 'generating options' actually produce (e.g., 'Creates mind maps, generates brainstorming lists, identifies gaps in project plans').

Add an explicit 'Use when...' clause with natural trigger terms users would say, such as 'brainstorm', 'generate ideas', 'explore options', 'ideation', 'what are my options'.

Define the specific domain or context this skill applies to (e.g., product strategy, creative writing, problem-solving) to reduce conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'opportunity space', 'notice gaps', and 'generate options'. No concrete actions are listed — it's unclear what the skill actually does in practical terms (e.g., what kind of graph? what kind of brainstorming output?).	1 / 3
Completeness	The 'what' is vague and the 'when' is entirely missing — there is no 'Use when...' clause or equivalent explicit trigger guidance. The description fails to clearly answer either question.	1 / 3
Trigger Term Quality	The terms used ('opportunity space', 'divergent generation', 'continuum') are abstract jargon unlikely to match natural user queries. 'Brainstorming' is a useful trigger term but it's parenthetical and the only natural keyword present.	1 / 3
Distinctiveness Conflict Risk	The description is extremely generic and could overlap with any brainstorming, ideation, analysis, or visualization skill. There are no distinct triggers or a clear niche that would differentiate it from other skills.	1 / 3
	Total	4 / 12 Passed

Validation

81%

Warnings & errors only

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

Validation — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: audenaert/etak
Commit: 632c389

Reviewed: 27 days ago

Table of Contents

Discovery Implementation Validation

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.