capture
Skill4 starsChanged 4 months agoMITView on GitHub
Ingest one raw input — a URL, video, article, transcript, screenshot text, meeting note, or a thought — into your co-brain. Saves the raw material verbatim to `sources/` (+ a `_sources.md` row + content hash), then writes atomic, fully-sourced notes into `wiki/`. Anything worth keeping but not verbatim-sourceable lands in `inbox/` with `status: needs-source`; junk is dropped per the blocklist. This is the WRITE side of cite-or-refuse. Triggers - "capture this", "add to my brain", "remember this", "ingest", or pasting something worth keeping.
60 other projects use a version of this.
Adopted by
Most recently taken up by
- jakubtobiasz/second-brain-templatetheir own version, first seen Nov 15, 2026
- anurag-rivora/product-brain-startertheir own version, first seen Nov 15, 2026
- AndyMelnykov/obsidian-claudetheir own version, first seen Nov 15, 2026
- jzhao234/big-braintheir own version, first seen Nov 8, 2026
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use weekly, ingest and 9 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.
gaiaaiagentSkillweekly
Generate a weekly digest rolling up dailies into higher-level pattern analysis
Also in 4 projects that use this
JaimeGBASkillingest
Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base
Also in 8 projects that use this
AnthropicSkillbrief
Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.
Also in 6 projects that use this
QuixiAISkillweekly-review
Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week
Also in 5 projects that use this
dubwoahSkillask
Answer questions about the codebase without generating or modifying any code. Use when the user wants to understand how something works, find where something is defined, or explore the project structure. Invoked with /ask.
Also in 4 projects that use this
AlexPEClubSkillrefine
Always use when the user wants to discuss an exsiting feature or specification. Open an existing feature spec to improve, extend, or fundamentally challenge it. Pass the feature ID as argument (e.g. /refine PROJ-2).
Also in 3 projects that use this
Other versions60 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 60
- garrytan/gbrain★ 33ksame name
- andreaskelm/pm-brain★ 235same name
- manusco/resonance★ 38same name
- nimbalyst/nimbalyst-wiki★ 36same name
- Hassaan146/claude-skills★ 18same name
- ArcticFox2029/chamnan★ 10same name
- JaimeGBA/Ion★ 9same name
- sunitghub/canon-skills★ 9same name
- philippe-desplats/second-brain★ 6same name
- GavinGreenwood/agentic-workflow-template★ 5same name
50 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.
In this repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- agents-syncSkill
- call-agentSkill
- context-restoreSkill
- context-saveSkill
- curatorSkill
- learnSkill
- onboardSkill
- recallSkill
- reviewSkill
- skillifySkill
- wiki-doctorSkill
- worklog-audioSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 0 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 58 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Before anything else, check the input against references/blocklist.md.
- Very specific: line 25
Write the raw material to sources/<source-key>.md.
- Very specific: line 29
Add (or update) the row in sources/_sources.md: source-key | path | sha256[:12] | origin | captured | last_verified.
- Very specific: line 36
Write each new note to wiki/<id>.md per references/wiki-spec.md:
- Very specific: line 66
Never invent or guess a source: No verbatim quote → inbox/, not wiki/.
- Very specific: line 68
Provenance bottoms out in
sources/: Never cite a wiki/ note as a source. - Very specific: line 72
Blocklist is law: When in doubt, quarantine to inbox/.
“Common” is measured: kept by at least 6 in 10 of the 58 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
Inherits
references/kernel.md(the provenance contract). Readsreferences/wiki-spec.mdfor schema.
What this does
Turns one raw input into (a) one sources/ capture file — the bottom of the provenance chain — and (b) one or
more atomic, source-cited notes in wiki/. Anything that can't be sourced verbatim goes to inbox/. Anything
on the Do-NOT-capture blocklist is dropped, never written.
Execution
Step 0 — Triage against the blocklist
Before anything else, check the input against references/blocklist.md. Transient/env-specific errors, negative
tool-capability claims ("X doesn't work"), one-off chatter, secrets/PII not meant for canon, and speculation
stated as fact get dropped — they poison the brain if persisted. When in doubt → inbox/, not wiki/.
Step 1 — Land the raw source
- Identify the input and its real-world origin (a URL, a video link, "meeting {{date}}", a file path, etc.). If
the input is a URL, fetch it. If it's a thought with no external origin, origin =
self / {{you}}, <date>. - Write the raw material to
sources/<source-key>.md. Source-key = short kebab slug, date-suffixed if it could collide (e.g.ai-os-talk-2026-06-23). Preserve text verbatim — this is the load-bearing copy. Keep a one-line header with origin + captured date. Type-folders are allowed (sources/youtube/,sources/meetings/). - Compute the hash:
shasum -a 256 sources/<source-key>.md | cut -c1-12. - Add (or update) the row in
sources/_sources.md:source-key | path | sha256[:12] | origin | captured | last_verified.
Step 2 — Extract atomic notes
- Re-read the source file back from disk — never write a quote from memory.
- Break the content into atomic claims — one idea each. Split compound ideas ("X and Y" → two notes).
- For EACH claim, before creating a note:
grepINDEX.mdfor an existing note on the same idea. If one exists, refine it (add asrcblock) instead of forking a near-duplicate. - Write each new note to
wiki/<id>.mdperreferences/wiki-spec.md:- frontmatter —
id, title, type, tags, confidence, status, origin, pinned, created, source_verified_on, links; - a short interpretive body in your voice (see
references/voice.md); - inline
[[wikilinks]]to related notes, mirrored into thelinks:array (wikilinks are navigation only, never provenance); - one
srcblock per claim, eachquotea verbatim substring of the source file. Grep the source to confirm the quote resolves verbatim before saving.
- frontmatter —
- Set
confidence:stated(the source asserts it directly) |inferred(you concluded it across spans; then attach all the spans as multiplesrcblocks) |reported(the source is relaying a third party). - Set
origin:user-directedwhen a human directed this capture (the default for/capture). An autonomous loop setsagent-generated. Loops may later auto-manage onlyagent-generatednotes;user-directedandpinned: trueare immune.
Step 3 — Quarantine what you can't source
- A claim worth keeping but lacking a verbatim source → write
inbox/<slug>.mdwithstatus: needs-source, anorigin:line, and a note on what source would confirm it. Never smuggle it intowiki/.
Step 4 — Third-party claims (the attribution layer)
- A fact that belongs to another party enters your canon ONLY as an attributed, sourced claim — frame the body
as "per {{Acme}}, as of {{date}}", set
confidence: reported, and cite the source where they stated it. Their knowledge feeds your brain without becoming indistinguishable from your own.
Step 5 — Update the index
- Append the new notes to
INDEX.md(or run/wiki-doctorto rebuild it deterministically). Add any obvious natural-language query aliases to the ALIASES section. - Close with a one-screen summary: source-key created, N notes added, M drafts quarantined, J dropped, and any contradictions spotted vs. existing notes.
Guardrails (hard)
- Never invent or guess a source. No verbatim quote →
inbox/, notwiki/. - Quotes are verbatim substrings of the resolved source file. Grep to confirm before saving.
- Provenance bottoms out in
sources/. Never cite awiki/note as a source. - Cap quotes (~300 chars). Interpret in the body; don't paste transcripts into
wiki/. - Dedup first. Grep
INDEX.mdbefore creating; refine an existing note rather than fork it. - One idea per note. Compound titles get split.
- Blocklist is law. When in doubt, quarantine to
inbox/; never persist the forbidden classes.
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.

