doc-coauthoring/SKILL.md
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
npx skillsauth add lidge-jun/cli-jaw-skills doc-coauthoringInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Three-stage workflow: Context Gathering → Refinement & Structure → Reader Testing.
Offer the workflow when user starts a writing task. If declined, work freeform.
Goal: Close the knowledge gap so you can guide effectively later.
Ask for meta-context:
Accept shorthand answers or info dumps.
If a template or existing doc is provided, read it. For docs with images lacking alt-text, offer to generate alt-text — images are invisible to future AI readers.
Encourage the user to share everything relevant:
Offer to pull context via available integrations (Slack, Drive, etc.). If none available, suggest enabling connectors or pasting content directly.
After the initial dump, generate 5–10 numbered questions targeting gaps.
Let users answer in shorthand (e.g., "1: yes, 2: see #channel, 3: no").
Track what's learned vs. what's still unclear. Address gaps immediately.
Exit condition: Questions show understanding of edge cases and trade-offs without needing basics explained.
Transition: ask if there's more to add, or if it's time to draft.
Goal: Build the document section by section through brainstorm → curate → draft → refine.
Per-section process:
If structure is clear: ask which section to start with. Suggest starting with the most uncertain section.
If structure is unclear: propose 3–5 sections based on doc type and adjust per feedback.
Create the scaffold (artifact or markdown file) with section headers and [To be written] placeholders.
Ask 5–10 questions specific to the section's purpose.
Generate 5–20 numbered options. Surface forgotten context and unconsidered angles. Offer to brainstorm more.
Ask which points to keep, remove, or combine. Accept numbered or freeform feedback — parse preferences and apply.
Ask if anything important is missing.
Replace placeholder with drafted content using str_replace.
On the first section, instruct: "Tell me what to change instead of editing directly — this helps me learn your style for later sections."
str_replace for edits — never reprint the whole docAt 80%+ sections done, re-read the full document checking for:
Provide feedback, then ask if ready for Reader Testing.
Goal: Test the document with a context-free reader to catch blind spots.
Generate 5–10 questions readers would realistically ask when discovering this document.
With sub-agents: For each question, invoke a sub-agent with only the document and the question (no conversation context). Summarize what it got right/wrong.
Without sub-agents: Instruct user to open a fresh conversation, paste the doc, and ask the generated questions. Have the reader report: answer, ambiguities, assumed knowledge.
Check (via sub-agent or fresh conversation) for:
If issues found, loop back to Stage 2 refinement for affected sections.
Exit condition: Reader consistently answers questions correctly with no new gaps.
When reader testing passes:
Tips: link this conversation in an appendix, use appendices for depth, update as real reader feedback arrives.
development
Goal execution guidelines with PABCD integration, verification tiers, documentation workflow, and AI-driven planning
tools
A CLI tool for making authenticated requests to the X (Twitter) API. Use this skill when you need to post tweets, reply, quote, search, read posts, manage followers, send DMs, upload media, or interact with any X API v2 endpoint.
development
Use this skill any time a spreadsheet file is the primary input or output (.xlsx, .xlsm, .csv, .tsv). This includes: creating, reading, editing, analyzing, or formatting spreadsheets; cleaning messy tabular data; converting between formats; and data visualization with charts. Also use for pandas-based data analysis when the deliverable is a spreadsheet. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration.
tools
Use this skill when the user wants to build a financial model, 3-statement model, DCF valuation, cap table, scenario analysis, or financial projections in Excel. Trigger on: 'financial model', '3-statement model', 'DCF', 'cap table', 'pro forma', 'projections', 'sensitivity analysis', 'waterfall', 'debt schedule', 'break-even', 'discounted cash flow', 'capitalization table', 'fundraising model', 'WACC calculation', 'scenario analysis model'. Input is a text prompt with assumptions. Output is a single .xlsx file with formula-driven, interconnected statement sheets.