agentleFS
DeepExtremaDeepExtrema/Tesseract/skills/recall/SKILL.md

recall

Skill4 starsChanged 14 days agoMITView on GitHub

Use when Taimoor asks what he or the vault knows about a topic, wants a researched answer from the mind database, or says "recall X" / "what do we know about X". Searches the Tesseract vault, synthesizes a cited answer, and files it into Claude/Answers/ so knowledge compounds.

150 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use addskill, apply-firmware 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.
  • ryanportfolioSkill

    addskill

    Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.

    Also in 6 projects that use this

  • ryanportfolioSkill

    apply-firmware

    Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.

    Also in 6 projects that use this

  • +10 more from ryanportfolio

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 137 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. Very specific:

    Citation-or-label: Every factual claim either cites its source note as a [[wikilink]], or is explicitly marked *(not from the vault)*.

    line 13
  2. Distinctive:

    Thin retrieval → say so: If the vault has little on the topic, report that honestly and STOP.

    line 15
  3. Distinctive:

    Always end with a "What the vault doesn't know" section.

    line 18

“Common” is measured: kept by at least 6 in 10 of the 137 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

Recall — researched Q&A over the Tesseract vault

Answer the question from the vault, cite every claim, file the answer. Requires the tesseract MCP server.

Contract (non-negotiable)

  1. Citation-or-label. Every factual claim either cites its source note as a [[wikilink]], or is explicitly marked (not from the vault).
  2. Thin retrieval → say so. If the vault has little on the topic, report that honestly and STOP. Never pad an answer with model knowledge dressed up as vault knowledge. No answer note is filed in that case.
  3. Always end with a "What the vault doesn't know" section.

Steps

  1. context_bundle(question, limit=10) — hybrid hits + graph entities + related notes in one call.
  2. Judge coverage: are at least 2 hits genuinely about the question? If not: tell Taimoor the vault has almost nothing on this, list the nearest misses, offer to capture the question or add_task a research follow-up, and stop here.
  3. read_note the top 3–5 relevant hits IN FULL — the bundle's excerpts locate notes, they are not enough to synthesize from. Follow one or two related_notes chains if they add real context.
  4. Compose the answer with exactly this structure:
    • ## Answer — synthesized, every claim carrying a [[wikilink]].
    • ## Sources — bullet list of every cited note.
    • ## What the vault doesn't know — gaps, contradictions, staleness.
  5. Offer to file each gap as a task (add_task) or a capture — the gaps are tomorrow's ingest queue.
  6. File the answer with write_note:
    • Path: Claude/Answers/YYYY-MM-DD <question slug>.md — slug is the question compressed to at most 6 words with the characters \ / : * ? " < > | [ ] # ^ stripped. If the path already exists, suffix 2, 3, … (same rule as session notes).
    • Frontmatter (YAML): created: YYYY-MM-DD HH:MM, agent: claude, project: <if obvious, else "">, tags: [answer], type: answer, question: "<the exact question asked>".
    • Body: the three sections from step 4.
  7. Show the full answer in chat as well — the note is for the vault, the chat reply is for now.

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.