prioritize
Converge on what matters most. Take a set of options — assumptions, ideas, opportunities, or objectives — and decide where to focus. Evaluates, ranks, and connects prioritization to concrete next steps.
48
53%
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/prioritize/SKILL.mdQuality
Discovery
50%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 communicates the general purpose of prioritization and decision-making but relies on somewhat abstract language ('converge on what matters most') rather than concrete, specific actions. It lacks an explicit 'Use when...' clause, which limits Claude's ability to reliably select this skill. The trigger terms are reasonable but not comprehensive enough to clearly distinguish it from adjacent strategy or planning skills.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to prioritize, rank options, narrow down choices, or decide where to focus among competing alternatives.'
Make the actions more concrete — specify outputs like 'produces a ranked list, a prioritization matrix, or a focused shortlist with rationale for each decision.'
Include more natural trigger terms users would say, such as 'narrow down', 'trade-offs', 'what should we focus on', 'rank', 'top priorities', 'decision matrix'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names some actions ('evaluates, ranks, connects prioritization to concrete next steps') and the domain (prioritization of options), but the actions are somewhat abstract and not fully concrete — what does 'converge on what matters most' actually produce? | 2 / 3 |
Completeness | The 'what' is partially addressed (evaluates, ranks, connects to next steps), but there is no explicit 'Use when...' clause or equivalent trigger guidance telling Claude when to select this skill. The when is only implied. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'assumptions, ideas, opportunities, objectives, prioritization, ranks' that users might say, but misses common natural phrases like 'prioritize', 'rank options', 'decide what to focus on', 'narrow down', or 'trade-offs'. The terms are present but not comprehensive. | 2 / 3 |
Distinctiveness Conflict Risk | The description is somewhat specific to prioritization workflows, but terms like 'ideas', 'opportunities', 'objectives', and 'next steps' are broad enough to overlap with brainstorming, strategy, or planning skills. It lacks a clear niche with distinct triggers. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
57%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 instruction-only skill that clearly defines the agent's stance, boundaries, and transitions. Its main weakness is that the actual prioritization process is implicit rather than explicitly sequenced — the skill tells Claude how to behave during prioritization but doesn't provide a concrete step-by-step workflow for conducting it. The progressive disclosure is excellent, with appropriate delegation to reference files.
Suggestions
Add a brief numbered workflow showing the sequence of a prioritization conversation (e.g., 1. Gather current ratings, 2. Challenge ratings with constraint questions, 3. Surface contradictions, 4. Confirm updated ratings, 5. Connect to next action).
Include at least one concrete inline example of a prioritization interaction showing input state (e.g., a set of assumptions with ratings) and the expected output (ranked list with rationale and next step), rather than deferring all specifics to the reference file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient but includes some unnecessary elaboration. Sections like 'The Central Tension' and 'When Ratings Don't Match Reality' provide useful guidance but could be tightened. The conversational tone adds some padding (e.g., 'Everything feels important when you're close to it. Your job is to create distance.'). | 2 / 3 |
Actionability | The skill provides concrete example prompts and transition triggers, which is good for an instruction-only skill. However, it lacks specifics on how to actually perform prioritization — no concrete frameworks are given inline (they're deferred to references/prioritize.md), and the guidance remains at the level of conversational strategies rather than executable steps. | 2 / 3 |
Workflow Clarity | The Transitions section provides a clear decision tree for what comes after prioritization, and the 'Connecting to Action' section emphasizes next steps. However, the actual prioritization workflow itself — how to sequence the evaluation, what steps to follow, when to confirm ratings — is not laid out as a clear sequence. The process is described conversationally rather than as an ordered workflow. | 2 / 3 |
Progressive Disclosure | The skill appropriately references external files for detailed frameworks (references/prioritize.md), artifact guidelines (../artifacts/guidelines.md), and the opportunity model (../artifacts/model.md). References are one level deep, clearly signaled, and the SKILL.md itself serves as a focused overview of stance and behavior rather than inlining all reference material. | 3 / 3 |
Total | 9 / 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.