talk-stage3-concepts
Builds a numbered, categorized concept catalogue from the talk summary and timeline, scoring each concept HIGH / MEDIUM / LOW for talk potential with optional repo enrichment. Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest presentation potential.
75
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/skills/talk-pipeline/stage-3-concepts/SKILL.mdQuality
Discovery
85%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 is a well-crafted description that clearly communicates specific actions (building a scored concept catalogue) and explicit trigger conditions. Its main weakness is that the trigger terms are somewhat specialized—users might use more casual language when looking for this functionality. The description also uses second person ('you need') in the 'Use when' clause, though this is a minor issue since the main action uses third person.
Suggestions
Add more natural trigger terms users might say, such as 'brainstorm talk topics', 'rank ideas for a presentation', or 'what should I talk about'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: builds a numbered/categorized concept catalogue, scores concepts HIGH/MEDIUM/LOW for talk potential, includes optional repo enrichment. These are concrete, well-defined actions. | 3 / 3 |
Completeness | Clearly answers both what ('Builds a numbered, categorized concept catalogue...scoring each concept HIGH/MEDIUM/LOW') and when ('Use when you need a structured inventory of concepts before choosing a talk angle, or when assessing which ideas have the strongest presentation potential'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'concept catalogue', 'talk potential', 'presentation potential', 'talk angle', and 'structured inventory', but these are somewhat domain-specific. Users might more naturally say things like 'brainstorm topics', 'rank ideas', or 'pick a talk topic' which aren't covered. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche: concept cataloguing and scoring for talk/presentation preparation. The combination of numbered catalogue, scoring system, and talk-specific context makes it highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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 skill that clearly defines the output format, scoring criteria, and categories for concept cataloguing. Its main weakness is that the actual process of extracting and scoring concepts is described abstractly rather than with concrete, executable steps — it tells Claude what to produce but not precisely how to perform the extraction and scoring. The validation checklist is helpful but would benefit from being integrated into the workflow as explicit checkpoints.
Suggestions
Add concrete step-by-step instructions for how to actually extract concepts from the summary (e.g., 'scan each section heading and bullet point for distinct ideas, techniques, or decisions') rather than just saying 'full scan of the source material'.
Integrate validation checkpoints into the workflow steps — e.g., after extraction, verify concept count meets minimum before proceeding to scoring; after scoring, verify HIGH distribution is ≤30% before writing output.
Add a brief concrete example showing 3-4 sample concepts with their scoring rationale to make the scoring criteria more actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary explanation (e.g., 'What This Skill Does' largely repeats what's already clear from the workflow and output sections). The scoring criteria descriptions and category table are useful reference material, but some sections like 'Tips' restate what's already implied. Overall mostly efficient with some tightening possible. | 2 / 3 |
Actionability | The skill provides clear output format templates with concrete markdown structure, scoring criteria, and category definitions. However, it lacks executable commands or concrete code for the actual extraction/scoring process — it describes what to do conceptually (reads summary, extracts concepts, categorizes) without showing how. The output format is copy-paste ready, but the process steps are abstract. | 2 / 3 |
Workflow Clarity | The 'What This Skill Does' section lists steps 1-7 in sequence, and there's a validation checklist at the end. However, the validation is a post-hoc checklist rather than integrated checkpoints within the workflow. There's no explicit feedback loop for when concept counts are too low or scoring distribution is off — the checklist mentions calibration but doesn't describe what to do if validation fails. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections (When to Use, Input, Output, Scoring Criteria, Output Format, Anti-patterns, Validation, Tips). Related skills are linked with one-level-deep references. The enriched output variant is cleanly separated. Navigation between pipeline stages is clear and well-signaled. | 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 | |
- Commit
746adc8
- 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.