菜单
Analyze feature requests and provide technical effort estimates with risk assessment
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Review an exec-talk's README and produce an exec.recipe.yml. Uses a 3-agent collaborative council to analyze section weighting, executive audience fit, narrative arc, and action clarity. Always overwrites any existing recipe. Triggers: "review the talk", "create the recipe", "is this landing for execs", "section weighting", "coverage gap", "recipe", "executive framing".
Review a tech-talk's README and produce a deck.recipe.yml. Uses a 3-agent collaborative council to analyze section weighting, narrative arc, and coverage gaps. Always overwrites any existing recipe. Triggers: "review the talk", "create the recipe", "is this the best use of our time", "section weighting", "coverage gap", "recipe".
Read from and write to the Workbench project memory store. Use when starting complex content work (query for prior context) or finishing a session that changed content (record drawer entries). Never invoke during agent pre-flight gates.
Add persona-grounded audience framing to a tech-talk. Selects 2–3 relevant personas, adds a "Who This Hits" box and up to 3 reaction lines to the README, and adds persona speaker notes to the slide deck. Triggers: "add personas", "who this hits", "persona reactions", "audience framing".
Use this skill when asked to verify, validate, fact-check, or review any data entry, lore fact, character bio, episode record, quote, or show content for accuracy against canonical project sources and the live database. Triggers on: check data, verify data, fact-check, accuracy check, data accuracy, check entry, verify entry, review accuracy, is this accurate, canon check, lore check, check this data, verify this, review this entry, check for errors, validate data, is this right, is this canon.
Use this skill when asked to verify, validate, or fact-check a lore entry, character description, seed data record, or any Breaking Bad content against the canonical reference in docs/breaking-bad-universe.md. Triggers on: check lore, verify lore, fact-check, canon check, lore accuracy, is this correct, seed data accuracy.
| name | effort-estimator |
| description | Analyze feature requests and provide technical effort estimates with risk assessment |
| level | 2 |
Note: This is a sample skill that estimates technical effort for feature requests. Your version should be tailored to your team's velocity and complexity factors.
This skill analyzes feature descriptions (written in product/business language) and provides:
Use this skill when:
Example: Add social media share buttons to character pages
Example: Add episode filtering by genre on the browse page
Example: Episode Detail pages with transcripts, character appearances, and streaming links
Example: Full-text search across all content with autocomplete
When estimating effort, consider these complexity multipliers:
| Factor | Impact |
|---|---|
| New table(s) required | +50% effort |
| Many-to-many relationships | +30% effort |
| Data migration needed | +25% effort |
| External data sources | +40% effort |
| Factor | Impact |
|---|---|
| New external API | +50% effort |
| Authentication changes | +30% effort |
| Real-time updates needed | +40% effort |
| Third-party service | +25% effort |
| Factor | Impact |
|---|---|
| Complex state management | +25% effort |
| Animations/transitions | +20% effort |
| Offline support | +40% effort |
| Accessibility requirements | +15% effort |
| Factor | Impact |
|---|---|
| E2E testing required | +20% effort |
| Performance testing | +25% effort |
| Security testing | +30% effort |
| Edge case coverage | +15% effort |
When analyzing a feature request:
Reference docs/ARCHITECTURE.md to understand:
Feature: [Feature Name]
Backend:
- Routes: [list changes needed]
- Services: [business logic changes]
- Database: [schema changes, migrations]
- Estimate: [Small/Medium/Large]
Frontend:
- Pages: [new or modified pages]
- Components: [new or modified components]
- State: [state management changes]
- Estimate: [Small/Medium/Large]
Testing:
- Unit tests: [scope]
- Integration tests: [scope]
- E2E tests: [if applicable]
- Estimate: [Small/Medium/Large]
Infrastructure:
- Changes needed: [if any]
- Estimate: [None/Small/Medium]
| Risk | Likelihood | Impact | Mitigation |
|---|---|---|---|
| [Risk name] | High/Medium/Low | High/Medium/Low | [How to reduce] |
## Effort Estimate: [Feature Name]
**Overall**: [Small/Medium/Large/Extra Large]
**Confidence**: [High/Medium/Low]
**Story Points**: [Range, e.g., 13-21]
**Calendar Time**: [Range, e.g., 1-2 weeks]
### Breakdown
| Area | Effort | Notes |
|------|--------|-------|
| Backend | [Small/Medium] | [Key work] |
| Frontend | [Small/Medium] | [Key work] |
| Testing | [Small/Medium] | [Scope] |
| Infrastructure | [None/Small] | [If needed] |
### Risks
- [Risk 1]: [Mitigation]
- [Risk 2]: [Mitigation]
### Recommendations
- [Break down suggestion if Large/XL]
- [Dependencies to resolve first]
- [Spikes or research needed]
Feature: "Users want to click on an episode and see full details including synopsis, character appearances, memorable quotes, and streaming links."
Analysis:
/episodes/:id/full endpoint with joined data (Medium)Overall: Large (1-2 weeks) Confidence: High (similar to Character Detail) Story Points: 21-34 Risks:
Feature: "Users want to search for anything - characters, quotes, episodes - from a single search box."
Analysis:
Overall: Extra Large (> 2 weeks, break down required) Confidence: Medium (depends on search technology choice) Story Points: 55-89 Recommendations:
When confidence is Low, recommend a spike or research phase before committing to timeline.