subsection-writer
✓Write survey prose into per-section files under `sections/` so each unit can be QA\x27d independently before merging. **Trigger**: subsection writer, per-section writing, split sections, sections/, 分小节写, 按章节拆分写作. **Use when**: `Approve C2` is recorded and writer packs exist (`outline/writer_context_packs.jsonl`); you want evidence-bounded drafting without a monolithic one-shot draft. **Skip if**: `DECISIONS.md` approval is missing, or `outline/evidence_drafts.jsonl` / `citations/ref.bib` is missing. **Network**: none. **Guardrail**: do not invent facts/citations; no TODO/ellipsis leakage; keep citations subsection- or chapter-scoped; H3 body files and chapter leads must not contain headings.
Installation
SKILL.md
Purpose: produce a paper-like draft by writing small, inspectable files under sections/.
Use writer-selfloop as the strict gate (PASS/FAIL + actionable TODO). Use evidence-selfloop to route upstream when packs are too thin.
Treat this skill as a writing playbook first, and as an automation wrapper second.
Write survey prose into per-section files under `sections/` so each unit can be QA\x27d independently before merging. **Trigger**: subsection writer, per-section writing, split sections, sections/, 分小节写, 按章节拆分写作. **Use when**: `Approve C2` is recorded and writer packs exist (`outline/writer_context_packs.jsonl`); you want evidence-bounded drafting without a monolithic one-shot draft. **Skip if**: `DECISIONS.md` approval is missing, or `outline/evidence_drafts.jsonl` / `citations/ref.bib` is missing. **Network**: none. **Guardrail**: do not invent facts/citations; no TODO/ellipsis leakage; keep citations subsection- or chapter-scoped; H3 body files and chapter leads must not contain headings. Source: willoscar/research-units-pipeline-skills.
Facts (cite-ready)
Stable fields and commands for AI/search citations.
- Install command
npx skills add https://github.com/willoscar/research-units-pipeline-skills --skill subsection-writer- Category
- >_Productivity
- Verified
- ✓
- First Seen
- 2026-02-01
- Updated
- 2026-02-18
Quick answers
What is subsection-writer?
Write survey prose into per-section files under `sections/` so each unit can be QA\x27d independently before merging. **Trigger**: subsection writer, per-section writing, split sections, sections/, 分小节写, 按章节拆分写作. **Use when**: `Approve C2` is recorded and writer packs exist (`outline/writer_context_packs.jsonl`); you want evidence-bounded drafting without a monolithic one-shot draft. **Skip if**: `DECISIONS.md` approval is missing, or `outline/evidence_drafts.jsonl` / `citations/ref.bib` is missing. **Network**: none. **Guardrail**: do not invent facts/citations; no TODO/ellipsis leakage; keep citations subsection- or chapter-scoped; H3 body files and chapter leads must not contain headings. Source: willoscar/research-units-pipeline-skills.
How do I install subsection-writer?
Open your terminal or command line tool (Terminal, iTerm, Windows Terminal, etc.) Copy and run this command: npx skills add https://github.com/willoscar/research-units-pipeline-skills --skill subsection-writer Once installed, the skill will be automatically configured in your AI coding environment and ready to use in Claude Code or Cursor
Where is the source repository?
https://github.com/willoscar/research-units-pipeline-skills
Details
- Category
- >_Productivity
- Source
- skills.sh
- First Seen
- 2026-02-01