talk-stage5-script
Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.
86
85%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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-structured description that clearly communicates specific deliverables and when to use the skill. Its main weakness is that trigger terms lean heavily on workflow-specific jargon ('Stage 4', 'Kimi prompt', '5-act pitch') which may not match how users naturally phrase requests. The explicit 'Use when' clause and concrete output list are strong points.
Suggestions
Add more natural trigger terms users might say, such as 'presentation', 'deck', 'slides', 'conference talk', or 'keynote' to improve discoverability.
Consider briefly clarifying what 'Kimi' refers to for broader context, or add alternative phrasing like 'AI slide generation tool' alongside it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'complete 5-act pitch with speaker notes', 'slide-by-slide specification', and 'ready-to-paste Kimi prompt for AI slide generation'. Also specifies a prerequisite ('validated angle and title from Stage 4'). | 3 / 3 |
Completeness | Clearly answers both what ('produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt') and when ('Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt'). Has an explicit 'Use when' clause with clear trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'pitch', 'speaker notes', 'slide spec', 'presentation prompt', and 'talk angle', but these are somewhat specialized to a specific workflow. Missing common variations users might say like 'presentation', 'deck', 'slides', 'talk preparation'. The term 'Kimi prompt' is very niche and 'Stage 4' is internal jargon. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very specific niche: 5-act pitch structure, Kimi prompt generation, and dependency on Stage 4 validation. Unlikely to conflict with other skills due to the unique combination of outputs and the specific workflow stage requirement. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides highly actionable guidance with complete output templates, clear workflow sequencing, and thorough validation. The format specifications for all three deliverables are precise and copy-paste ready. Minor verbosity in the introductory sections (duplicated purpose statements) slightly reduces token efficiency, but overall the content density is high and well-organized.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content earns its place — the detailed format templates are necessary reference material. However, some sections like 'What This Skill Does' largely duplicate the workflow that follows, and the 'When to Use This Skill' section repeats the prerequisite. The tips section adds some value but could be tighter. | 2 / 3 |
Actionability | Highly actionable with complete, copy-paste-ready markdown templates for all three output files (pitch.md, slides.md, kimi-prompt.md). Concrete rules like '1 idea per slide', 'max 10 words', and specific timing formulas (10% buffer, 2-3 min/slide) give precise executable guidance. The Kimi usage instructions are step-by-step. | 3 / 3 |
Workflow Clarity | Clear 6-step sequence with explicit prerequisite validation ('Do not run this stage without that confirmation'), a comprehensive validation checklist with 8 items, and specific verification steps like 'Verify no {PLACEHOLDER} remains'. The Kimi prompt usage section includes an iterative refinement feedback loop. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections progressing from overview to detailed templates to anti-patterns to validation. References to external files (Kimi template, related stages) are one level deep and clearly signaled with relative links. The format templates are appropriately inline since they're the core deliverable specifications. | 3 / 3 |
Total | 11 / 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.