orient
Home base for product discovery. Find your bearings in the opportunity space, think out loud about half-formed observations, make sense of what you're learning, and reflect on where the work stands.
36
35%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./discovery/skills/orient/SKILL.mdQuality
Discovery
0%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 reads as inspirational copy rather than a functional skill description. It lacks concrete actions, natural trigger terms, explicit 'when to use' guidance, and any distinguishing specificity. It would be nearly impossible for Claude to reliably select this skill from a set of alternatives.
Suggestions
Replace abstract language with concrete actions, e.g., 'Synthesize user research findings, map opportunity areas, track product discovery insights, and maintain a running log of observations and hypotheses.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user mentions product discovery, opportunity mapping, research synthesis, user insights, or wants to brainstorm product directions.'
Differentiate from general brainstorming or note-taking skills by specifying the product discovery domain and the types of artifacts produced (e.g., opportunity trees, insight summaries, assumption logs).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses entirely abstract, metaphorical language ('find your bearings', 'opportunity space', 'think out loud') without naming any concrete actions. There are no specific capabilities listed—just vague conceptual framing. | 1 / 3 |
Completeness | There is no explicit 'Use when...' clause or equivalent trigger guidance. The 'what' is extremely vague (thinking, reflecting, making sense), and the 'when' is entirely absent. Both dimensions are very weak. | 1 / 3 |
Trigger Term Quality | The keywords used ('opportunity space', 'half-formed observations', 'find your bearings') are not natural terms a user would type. A user seeking product discovery help would more likely say 'product research', 'user needs', 'market analysis', or 'discovery notes'. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so generic ('think out loud', 'reflect on where the work stands', 'make sense of what you're learning') that it could apply to virtually any brainstorming, journaling, or reflection skill. It has no distinct niche or triggers. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
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-structured conversational/advisory skill that clearly defines when and how Orient should engage with PMs across four distinct scenarios. Its strengths are excellent workflow clarity, good progressive disclosure with appropriate external references, and clear boundary-setting (what Orient does NOT do). Its main weakness is moderate verbosity — some explanatory prose could be tightened without losing clarity, and the response guidance could be more concrete in places.
Suggestions
Tighten the 'How to respond' sections by reducing explanatory prose and focusing on decision rules (e.g., replace 'The signal is when they start using more concrete language — naming a specific customer problem...' with a concise bullet list of crystallization signals).
Make the signal priority order explicit inline or as a compact reference list rather than relying on the reader to consult guidelines.md, since it's central to two of the four response patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably well-written but includes some verbose explanations that Claude could infer. For example, the detailed descriptions of PM mindsets ('The PM has something on their mind but it's not a clear request yet') and the extensive example quotes could be tightened. The 'Your Stance' section explains receptiveness at length when a few sentences would suffice. | 2 / 3 |
Actionability | The skill provides concrete guidance on how to respond to different scenarios (e.g., signal priority order, specific transition recommendations), but it's an instruction-only skill with no executable code, which is appropriate. However, the 'How to respond' sections are somewhat abstract — they describe a posture rather than giving precise, copy-paste-ready response templates or concrete decision criteria. The signal priority order is referenced but not fully defined here. | 2 / 3 |
Workflow Clarity | The skill clearly sequences the four entry scenarios (pre-formal thinking, re-entry, reflection, direction-seeking) with explicit response strategies for each. The transitions section provides clear decision criteria for when to hand off to other skills. Since this is a conversational/advisory skill rather than a destructive or batch operation, validation checkpoints aren't needed, and the workflow is unambiguous. | 3 / 3 |
Progressive Disclosure | The skill appropriately references external files (artifacts/SKILL.md, model.md, guidelines.md) for deeper content, keeping the main file focused on Orient's specific behavior. References are one level deep and clearly signaled. The content is well-organized with clear section headers for different use cases. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%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
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.