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 conditions. The natural language trigger terms cover the key scenarios where a user would need this skill.
| 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 3-4 strategic talk angles with strength/weakness analysis, title options, CFP descriptions, and a peer 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 mandatory CHECKPOINT workflow make 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 a clear multi-step workflow and a strong mandatory checkpoint mechanism. Its main weakness is that it inlines all four output format templates, making it longer than necessary — these could be split into referenced files. The anti-patterns, validation checklist, and tips sections add genuine value without being verbose.
Suggestions
Move the detailed output format templates (angles.md, titre.md, descriptions.md formats) into a referenced file like `templates/stage-4-formats.md` to reduce the SKILL.md size and improve progressive disclosure.
The feedback-draft.md format section appears to be missing from the skill body despite being listed as an output — either add it inline or clarify that it's fully defined in the referenced template file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines) with extensive template formats that could be referenced externally. However, most content is structural templates rather than explanatory fluff — it doesn't over-explain concepts Claude knows, but the inline templates for all four output files add significant bulk that could be in separate reference files. | 2 / 3 |
Actionability | The skill provides highly concrete, copy-paste-ready output formats with exact markdown structures, specific file naming conventions, a verbatim CHECKPOINT message to display, and clear rules (e.g., 'minimum 3 angles, maximum 4'). The anti-patterns and validation checklist add further specificity. | 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 is emphasized multiple times with a verbatim display format, and the anti-patterns section explicitly flags skipping it. The validation checklist provides a final verification step. | 3 / 3 |
Progressive Disclosure | The skill references external files well (templates, related stages) and has clear navigation to prerequisites and next steps. However, the four full output format templates are inlined rather than referenced from separate files, making the SKILL.md itself quite long when these could be in a formats/ directory with one-level-deep references. | 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
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.