document-intake
Skill2 starsChanged 7 months agoMITView on GitHub
Normalize user-provided specs in any format into .ohc/doc-sources.md plus a traced plan. Triggers: from my docs, existing spec, external spec, /ohc-document-intake.
In this repository32 other files it gives its agents.
- skills/coding/redis-agent-skills/AGENTS.mdAGENTS.md
- skills/coding/redis-agent-skills/CLAUDE.mdCLAUDE.md
- agent-browserSkill
- autopilotSkill
- book-studySkill
- brainstormingSkill
- browser-useSkill
- cavemanSkill
- androidSkill
- brand-guidelinesSkill
- canvas-designSkill
- frontend-designSkill
- supabase-postgres-best-practicesSkill
- theme-factorySkill
- vercel-react-best-practicesSkill
- web-design-guidelinesSkill
- context7-aware-codingSkill
- explore-codebaseSkill
- find-skillsSkill
- finishing-a-branchSkill
- ohc-coding-disciplineSkill
- pdfSkill
- ralphSkill
- requesting-code-reviewSkill
- retrospectiveSkill
- seo-auditSkill
- skill-creatorSkill
- subagent-driven-developmentSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- writing-plansSkill
- writing-skillsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Use when stakeholders reference PRDs, RFCs, diagrams, or wiki exports in whichever structure they already use.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Document Intake — externally authored specifications
Use when stakeholders reference PRDs, RFCs, diagrams, or wiki exports in whichever structure they already use. Do not require re-hosting copy in oh-my-colab formats unless the team asks for it; register sources and derive an executable plan under .ohc/.
Steps
- Inventory — List every path, URL, or paste block the user gives. Assign each a role:
product,architecture,api,data_flow,design,testing,security,unknown. - Read — Load
.ohc/PROJECT.mdfirst. Read cited sources (text-first; see references for binary limits). - Reconcile — Compare claims to the repo: note conflicts, stale sections, missing code for specified behavior. Do not hide gaps.
- Internal notes (ephemeral) — Draft bullets: goal, out of scope, constraints, acceptance signals, APIs, data flow. Use for the plan only; do not duplicate entire foreign specs into repo files.
- Write
.ohc/doc-sources.md— Merge withassets/doc-sources.template.md: table columns Path or URL | Role | Version or date | Notes. Single index for this initiative; update in place on later intakes. - Handoff to writing-plans — Narrow Step 1 of writing-plans to unresolved questions and conflicts only. Produce
.ohc/plans/{kebab}.mdusing the plan template (Sources, Traceability table: source ref → task). - Gate — Same as writing-plans: no BUILD until user confirms the plan.
See references/external-doc-protocol.md for edge cases and reconciliation format.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

