菜单
Activate when the turn's deliverable is substantial prose — docs, copy, proposals, feedback, commit/PR text, or UI strings. Provides copywriting frameworks, tone guidance, and editing workflow for clear, persuasive, polished output.
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。
| name | core-writing |
| description | Activate when the turn's deliverable is substantial prose — docs, copy, proposals, feedback, commit/PR text, or UI strings. Provides copywriting frameworks, tone guidance, and editing workflow for clear, persuasive, polished output. |
| user-invocable | false |
Follow Brief → Structure → Draft → Polish for every writing task.
When the current task matches a trigger below, Read the named companion from this skill's directory (path provided in the activation header). Companions are not pre-loaded — pull them on demand.
| Trigger | Companion |
|---|---|
| Writing or rewriting a project README | templates/readme.md |
| Drafting a git commit message | templates/commit-message.md |
| Documenting a function, endpoint, or CLI command | templates/api-doc.md |
| Formula | When to Use | Structure |
|---|---|---|
| AIDA | Marketing, proposals, feature announcements | Attention → Interest → Desire → Action |
| PAS | Bug reports, problem-solving docs | Problem → Agitate → Solution |
| Inverted Pyramid | News, announcements, summaries | Conclusion → Key details → Background |
| Before-After-Bridge | Change proposals, migration guides | Current → Desired → How to get there |
| FEBC | Technical decisions | Fact → Explanation → Benefit → Conclusion |
| Audience | Tone | Characteristics |
|---|---|---|
| Developers | Technical, precise | Specific terms, code examples, no fluff |
| Product managers | Outcome-oriented | Problem → impact → timeline → trade-offs |
| End users | Friendly, clear | Simple language, concrete examples, next steps |
| Executives | Concise, strategic | Recommendation first, TL;DR, business impact |
Before finalizing:
Ensure this skill is active before every journal write — new entry, edit, restructure, or activity log append. Provides the graph protocol (bidirectional links, indexes), the directory layout, and the activity log format that keep the journal consistent.
Activate when the turn's deliverable is source, test, code analysis, or config files — editing or creating code. Provides the Research → Strategy → Execution workflow, the complexity budget, and specialised deep-dive companions (testing, debug, refactor, review).
Activate when the turn's deliverable is a design — system architecture, API contract, data model, component decomposition, or trade-off analysis. Provides the Constraints → Explore → Decide → Specify → Plan workflow for sound, well-reasoned designs.
Activate when the turn's deliverable is findings, comparisons, recommendations, or an investigation-backed plan — answering questions, analyzing unfamiliar code, exploring new domains. Provides the systematic Scope → Discover → Synthesize → Plan workflow.
Force explicit research mode — Scope → Discover → Synthesize → Plan — with the approval gate before any implementation.
Prepare high-quality git commit messages or comprehensive Pull Request (PR) descriptions based on recent changes.
