docgen
Skill2 starsChanged 3 months agoMITView on GitHub
Generate documentation with a local model drafting and the cloud only refining (0 cloud tokens for the draft), plus a local session review that summarises what a work session did. Use to write README/module docs/CHANGELOG/guides/ADRs cheaply, or to produce end-of-session notes/learnings from a transcript.
5 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- zedarvates/frugal-skillsedited, first seen Nov 8, 2026
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- AsiaOstrich/universal-dev-standardstheir own version, first seen Nov 1, 2026
- prsolans/claude-skillstheir own version, first seen Oct 15, 2026
- jnerytech/specdtheir own version, first seen Jul 28, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- zedarvates/frugal-skills★ 148% same
Wrote their own version · 4
- AsiaOstrich/universal-dev-standards★ 84same name
- AsiaOstrich/EngramGraph★ 4same name
- jnerytech/specd★ 0same name
- prsolans/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- clean-cacheSkill
- agent-cacheSkill
- app_testSkill
- asset-qualitySkill
- auto_distillSkill
- auto-memorySkill
- auto_routerSkill
- benchSkill
- bootstrapSkill
- botte-proxySkill
- cacheSkill
- capabilitiesSkill
- cardinalSkill
- cavemanSkill
- checkupSkill
- clarificationSkill
- clusterSkill
- code_fingerprintSkill
- completion_proofSkill
- conductorSkill
- context_budgetSkill
- context_profilerSkill
- context_slicerSkill
- context_windowsSkill
- control_loopSkill
- cost_estimatorSkill
- cwe_kbSkill
- dag_optimizerSkill
- dashboardSkill
- decision-ladderSkill
- demoSkill
- diff_languageSkill
- directives_auditSkill
- docs_stewardSkill
- eventsSkill
- fallow_likeSkill
- fast_contextSkill
- fixSkill
- harness_deltaSkill
- hermes-bridgeSkill
- hf_provenanceSkill
- infra_advisorSkill
- ingestSkill
- llm_backendsSkill
- llm_mcpSkill
- loaderSkill
- mcp_gatewaySkill
- meta_harnessSkill
- metricsSkill
- migration_auditSkill
- monte_cristoSkill
- mousquetairesSkill
- nlp_deterministicSkill
- nn_auditSkill
- prefix-prunerSkill
- prefix_treeSkill
- preflightSkill
- prompt_improverSkill
- reportSkill
- The first 60 shown.
The file
Files
docgen — local-drafted docs (cloud-refined) + session review
Documentation is verbose, so the LOCAL model writes the first draft and the cloud
model is spent only on a final polish — the video's "pre-write local, correct
with cloud" pattern, built on [[auto_router]]'s draft_refine fusion.
python -m skills.docgen.cli draft "deploy the service" --kind guide
python -m skills.docgen.cli draft "auth module" --kind module
python -m skills.docgen.cli session ~/.claude/projects/.../transcript.jsonl
python -m skills.docgen.cli session "user: did X\nassistant: built Y" --text- draft — local model drafts (
readme|module|changelog|guide|adr); cloud refines only if a key is set (otherwise you keep the local draft, marked un-refined). 0 cloud tokens for the draft itself. - session — reads a transcript (Claude Code
.jsonl, markdown, or raw text) and a LOCAL model returnsdone / decisions / learnings / next. 0 cloud tokens.
Exposed via [[llm_mcp]] as draft_doc and session_review. Pairs with
[[ingest]] (pull sources to document) and [[checkup]] (what changed this session).
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.