agentleFS
agamaroraagamarora/second-brain/.claude/skills/capture/SKILL.md

capture

Skill2 starsChanged 7 months agoMITView on GitHub

Drop an in-conversation thought, link, quote, or observation into inbox/ as a timestamped note. Writes the file immediately — no triage, no processing. Use whenever the user says "capture this", "save this", "add to inbox", or describes something they want to keep but not act on right now.

57 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use weekly, brief and 8 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.
  • gaiaaiagentSkill

    weekly

    Generate a weekly digest rolling up dailies into higher-level pattern analysis

    Also in 4 projects that use this

  • AnthropicSkill

    brief

    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

  • QuixiAISkill

    weekly-review

    Review the past week across goals, tasks, calendar, journal, and commitments, then propose the next week

    Also in 5 projects that use this

  • dubwoahSkill

    ask

    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

  • termdockSkill

    recall

    Retrieves cross-session memories about past decisions, lessons, and patterns. Use when user asks about prior work, past decisions, or mentions a feature. Triggers include check memory, what did we decide, how did we solve.

    Also in 6 projects that use this

  • AlexPEClubSkill

    refine

    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

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 55 edited versions we read keep these.

  • 2

    Distinctive

    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
  1. Distinctive:

    If the content is ambiguous, ask one clarifying question: "Capture [A] or [B]?" Do not invent content.

    line 33
  2. Very specific:

    If a file with the same name exists, append -2, -3, etc.

    line 46
  3. Distinctive:

    Do not summarize the content back.

    line 75

“Common” is measured: kept by at least 6 in 10 of the 55 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Turn a conversation fragment into a raw capture in one shot. No editing, no synthesis, no triage. Processing happens later via /ingest.

Trigger phrases

Invoke this skill when the user says any of:

  • "capture this"
  • "save this"
  • "add to inbox"
  • "put this in my brain"
  • "jot this down"
  • "keep this for later"
  • "hold onto this"

Or when the user describes something valuable mid-conversation and asks Claude to remember it without acting on it.

Steps

1. Figure out the content

The content is whatever the user just said or referenced. Three cases:

  • Direct content — user pasted a quote, a link, a thought. Use verbatim.
  • Referenced content — user said "capture that thing Ravi said about pricing." Scroll back in the conversation, lift the exact passage, include attribution.
  • User instruction — user says "capture this: I want to try usage-based pricing." Use the instruction as the capture body.

If the content is ambiguous, ask one clarifying question: "Capture [A] or [B]?" Do not invent content.

2. Build the filename

inbox/<YYYY-MM-DD>-<slug>.md

Slug rules:

  • Lowercase, hyphen-separated, 3-6 words
  • Derived from the content itself — not the surrounding conversation
  • Examples: inbox/2026-04-23-ravi-on-hybrid-pricing.md, inbox/2026-04-23-karpathy-llm-wiki-gist.md

If a file with the same name exists, append -2, -3, etc.

3. Write the frontmatter + body

---
title: <one-line summary of what's being captured>
date: <YYYY-MM-DD>
status: raw
source: <where this came from — conversation, URL, person, meeting, etc.>
---

# <title>

<the captured content — verbatim where possible>

## Context

<1-2 sentences on why this was captured — what the user said or what triggered it>

4. Confirm succinctly

Return one line:

Captured → inbox/<YYYY-MM-DD>-<slug>.md

Do not summarize the content back. Do not suggest next steps. The capture is the whole action.

What NOT to do

  • Do not /ingest the file. Capture and ingest are separate phases. The user will run /quick-sync at session end (or /ingest explicitly) to process the inbox.
  • Do not overwrite an existing inbox file. Append -2 if collision.
  • Do not write a wiki page directly. Capture goes to inbox/ only. Wiki pages get enriched by /ingest later.
  • Do not edit the user's phrasing. Capture verbatim when possible.

Failure modes

  • No content clear → ask: "Capture what exactly? Paste the text or point me at the message."
  • File collision with different content → append -2 or -3. Never overwrite.
  • inbox/ missing → create inbox/.gitkeep first, then the capture.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.