talk-stage4-position
Generates 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer feedback draft, then enforces a mandatory CHECKPOINT for user confirmation before scripting. Use when deciding how to frame a talk, preparing a CFP submission, or choosing between multiple narrative angles.
89
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 an excellent skill description that clearly articulates specific deliverables (talk angles, strength/weakness analysis, title options, CFP descriptions, peer feedback draft), includes a distinctive workflow element (mandatory CHECKPOINT), and provides explicit trigger guidance with natural user terms. It covers the full evaluation criteria with strong specificity, natural trigger terms, completeness, and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generates 3-4 strategic talk angles, strength/weakness analysis, title options, CFP descriptions, peer feedback draft, and enforces a mandatory CHECKPOINT. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both what (generates strategic talk angles with analysis, titles, CFP descriptions, feedback draft) and when ('Use when deciding how to frame a talk, preparing a CFP submission, or choosing between multiple narrative angles'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'talk angles', 'CFP submission', 'frame a talk', 'narrative angles', 'title options'. These are terms a user preparing a conference talk would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on conference talk preparation and CFP submissions. The specific mention of talk angles, CFP descriptions, and the CHECKPOINT workflow makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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, highly actionable skill with clear workflow sequencing and an important mandatory checkpoint. Its main weakness is that it inlines extensive output templates that could be externalized for better token efficiency and progressive disclosure. The anti-patterns section and validation checklist are strong additions that help Claude avoid common mistakes.
Suggestions
Move the detailed output format templates (angles.md, titre.md, descriptions.md) to separate reference files and link to them from SKILL.md, keeping only brief summaries inline.
Trim the recommendation section template in angles.md format — the numbered sub-sections (1-4) are overly prescriptive and could be condensed to a shorter structural guide.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long due to extensive template formats inline. While the templates serve as concrete guidance, the full markdown templates for angles.md, titre.md, and descriptions.md could be externalized to separate files. Some sections like 'Tips' add value but the overall length (~180 lines) is heavy for what could be more concise. | 2 / 3 |
Actionability | The skill provides highly concrete, copy-paste-ready templates for every output file, exact checkpoint text to display, specific rules (3-4 angles, 100/250 word targets), anti-patterns to avoid, and a validation checklist. Claude knows exactly what to produce and in what format. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with an explicit mandatory CHECKPOINT as a validation/confirmation gate before proceeding. The checkpoint includes a specific display format and the rule 'Do not invoke Stage 5 without explicit user confirmation' is a clear feedback loop. The validation checklist reinforces completeness. | 3 / 3 |
Progressive Disclosure | The skill references external files (templates/feedback-draft.md, related stages) which is good, but the bulk of the template formats are inlined rather than externalized. The angles.md, titre.md, and descriptions.md templates could be in separate reference files, with the SKILL.md serving as a leaner overview. The structure is clear but the balance between overview and detail leans too far toward inline detail. | 2 / 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 | |
- Commit
4ef3dec
- 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.