learn
Skill5 starsChanged 6 days agoMITView on GitHub
Research an unfamiliar domain from primary sources into notes or a publish-ready draft, keeping contradictions visible. Use for deep dives. Not for one-URL lookups (use read).
195 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- HughYau/AcademicForgetheir own version, first seen Nov 8, 2026
- dimsedra/skillstheir own version, first seen Nov 8, 2026
- rajanrx/skillstheir own version, first seen Nov 8, 2026
- edwinidrus/dragonhoardtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-anydoc, add-clidash and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TomGranotSkilladd-anydoc
Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.
Also in 5 projects that use this
- TomGranotSkill
add-clidash
Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.
Also in 5 projects that use this
seek888Skillopen-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Also in 11 projects that use this
Saqlain-811Skillios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Also in 6 projects that use this
MicrosoftSkilladd-codex
Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
Also in 6 projects that use this
- MicrosoftSkill
add-deltachat
Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.
Also in 6 projects that use this
- +5 more from TomGranot
- +1 more from microsoft
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- garrytan/gstack★ 141ksame name
- rohitg00/ai-engineering-from-scratch★ 78ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- tigerless-labs/autoharness★ 11ksame name
- tw93/claude-health★ 7.5ksame name
- tw93/Waza★ 7.5ksame name
- nykooi1/vibe-wise★ 3.5ksame name
- HughYau/AcademicForge★ 2.6ksame name
185 more not listed
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.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
Ask only when two modes would change the deliverable.
- Distinctive: line 37
No Fill in before every outline section has a source.
- Distinctive: line 39
Every factual claim cites a fetched source URL or file.
- Distinctive: line 40
Stop at publish readiness.
“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Support the user's thinking; do not replace it.
Mode
| Mode | Entry | Exit |
| Quick Reference (default when unsure) | Collect | Digest: notes only |
| Deep Research | Collect | Self-review: publish-ready draft |
| Write to Learn (materials supplied) | Outline | Self-review |
| Canonical Article ("one page is enough") | Collect | Self-review, plus worked examples, common mistakes and 3–5 Further Reading picks |
Ask only when two modes would change the deliverable.
Phases
- Collect — primary sources only: papers, official docs and blogs, builders' posts, reference repos. Three ordered steps:
- Discover:
readsearch maps the landscape, then 2–3 deep searches on the best sub-topics. Output is a URL list. - Fetch: every URL through
read, which owns the cascade, privacy and paywall checks. - File: pass
readthe source directory (default: scratchpadlearn/<topic>/sources/); move, never refetch. Target 5–10 sources for a post, 15–20 for a survey.
- Discover:
- Digest — read each source fully; keep a claim only if it recurs in the source, predicts new cases, or is specific to that source rather than generic wisdom. Summarizing is not digesting.
- Outline — every section names its sources; a section without one is cut or sent back to Collect.
- Fill in — section by section; a section that resists writing goes back to Digest for that sub-topic only.
- Refine — edits only: cut repetition, flag broken flow and unexplained terms, then run
mono-writeto strip AI patterns. - Self-review — the user reads the draft linearly, twice; fix what they mark.
Hard Rules
- No Fill in before every outline section has a source.
- Contradictions stay visible: state both positions and each one's evidence.
- Every factual claim cites a fetched source URL or file.
- Stop at publish readiness; never post, upload or publish unless asked.
Output
The mode's exit artifact, its saved path, and a Sources list (URL, tier, one-line why). Prose for conclusions, a diagram only when relationships carry the point.
Defer to: read for every search and fetch; mono-write for prose polish; think when the question is a decision, not a domain.
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.