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

dossier

Skill4 starsChanged 14 days agoMITView on GitHub

Use when Taimoor wants a full briefing document on a topic rather than a quick answer — "give me the dossier on X", "brief me on everything we have about Y", "prep me for this meeting/interview from the vault". Synthesizes a multi-section, fully cited briefing from the Tesseract vault and files it to Claude/Answers/.

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 0

    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:

    Every claim carries a [[wikilink]] or is marked *(not from the vault)*.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 11 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

Dossier — the deep briefing ritual

Requires the tesseract MCP server. A dossier is /recall's big sibling: a standing briefing document, not an answer to one question. It inherits recall's contract — citation-or-label, thin retrieval means say so and stop, never pad with model knowledge dressed as vault knowledge.

Steps

  1. context_bundle(topic, limit=10). Judge coverage: at least 3 hits genuinely about the topic, spanning more than one note type (sessions, concepts, answers, graph). If not, tell Taimoor the vault is too thin for a dossier, list the nearest misses, offer /recall for the narrow question or add_task to research — and stop. No note is filed.
  2. read_note the top 5–8 relevant notes IN FULL; follow 1–2 related_notes chains and find_entity results where they add context the hits lack.
  3. Compose with exactly these sections:
    • ## Executive summary — what Taimoor needs in 30 seconds.
    • ## Timeline — dated events pulled from sessions and Claude/Decisions.md, oldest first.
    • ## Key concepts — the load-bearing ideas, each [[wikilinked]].
    • ## Tensions and open questions — contradictions between notes (side by side, with dates) and gaps the vault cannot answer.
    • ## Sources — every cited note. Every claim carries a [[wikilink]] or is marked (not from the vault).
  4. File with write_note to Claude/Answers/YYYY-MM-DD Dossier <slug>.md — slug rule as in /recall (≤6 words, characters \ / : * ? " < > | [ ] # ^ stripped, suffix 2, 3, … on collision). Frontmatter: created: YYYY-MM-DD HH:MM, agent: claude, project: <if obvious, else "">, tags: [dossier], type: dossier, question: "<the topic as asked>".
  5. Show the full dossier in chat. If the harness has a page surface (Claude Code's Artifact tool, a canvas), offer a rendered version — presentation only; the markdown note in the vault is the durable copy.
  6. Offer each item under "Tensions and open questions" as an add_task — the gaps are tomorrow's ingest queue.

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.