agentleFS
ErionisErionis/Jarvis-Lite/skills/briefing/SKILL.md

briefing

Skill3 starsChanged 3 months agoMITView on GitHub

Use when a user asks for a session briefing or a start-of-session overview.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use grill-me.

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.
  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 7 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 17 edited versions we read keep these.

  • 7

    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
  1. Distinctive:

    Use the latest relevant entry.

    line 22
  2. Distinctive:

    Use only rituals declared in the local profile.

    line 36
  3. Distinctive:

    If candidates remain materially equivalent, no unique priority is grounded.

    line 50
  4. Distinctive:

    Do not invent a ranking. Request one decision under the canonical interaction rule with at most three concrete candidates and next steps.

    line 51
  5. Distinctive:

    Use only the useful parts:

    line 61
  6. Distinctive:

    Use declared local sources.

    line 78
  7. Distinctive:

    Do not edit, create, rename, move, delete, stage, commit, configure Git, or process Inbox items.

    line 80

“Common” is measured: kept by at least 6 in 10 of the 17 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

Briefing — Quick Start

Give a local, read-only, dependency-free briefing grounded in evidence.

What to do

Step 1 — Gather context

Resolve through the local capability map:

  1. Identity supplies preferences.
  2. Durable memory supplies retained commitments. Stable preferences, references, and facts are not work candidates.
  3. Future work supplies current work and next actions. Ignore empty placeholders such as - [ ].
  4. Daily history supplies recent unfinished work or an explicit next action. Use the latest relevant entry.
  5. Handoff supplies continuation. Its source must be a readable directory; otherwise mark the role unresolved. A Handoff is active only when its frontmatter contains status: active. A missing or unknown status is not active; report it as a discrepancy. Treat each distinct active Handoff with an unfinished next action as a candidate. Do not select between multiple active Handoffs by recency alone. Exclude archive/ from ordinary briefing and ignore type: document-pointer redirects when counting handoffs or reporting missing lifecycle fields.
  6. Inbox supplies untriaged item names plus explicit deadlines, dependencies, constraints, or waiting states. Inbox is attention-only and never a priority candidate. An unresolved Inbox limits only attention and triage coverage. Do not process it.

Use only rituals declared in the local profile. If a role's declaration is missing, ambiguous, or points to a missing source, mark it unresolved and continue from verified sources. Do not discover or substitute another path.

Step 2 — Select the focus

Deduplicate the same semantic focus across sources. Recommend one candidate only when direct evidence distinguishes it: an explicit priority, an explicit deadline, a dependency or unblock, or an unequivocal continuation with a stated next action.

Give one concrete next step and why it matters now. Do not rank by guessed impact, age, counts, source order, or assumed urgency.

If candidates remain materially equivalent, no unique priority is grounded. Do not invent a ranking. Request one decision under the canonical interaction rule with at most three concrete candidates and next steps. If more exist, say so without demoting omitted items.

Durable memory, Future work, Daily history, and Handoff are candidate-bearing roles. If any candidate-bearing role is unresolved, do not claim a unique priority; show resolved candidates as partial evidence.

Step 3 — Generate the briefing

Use only the useful parts:

  • Priority: one recommendation, concrete next step, and why it matters now; or the bounded choice.
  • Continuity: At most one visible Continuity line from relevant Daily history or Handoff evidence. Do not repeat the same focus.
  • Attention: Include Attention only for verified deadlines, blockers, Inbox material, or other explicit friction.
  • Context incomplete: one compact Context incomplete line naming unresolved roles and the practical limitation.

Omit empty sections. Use about five lines when signal is low and normally no more than 10–12 lines. With no work or friction, say so and ask what to work on.

Rules

  • Be direct and friendly.
  • Use declared local sources; require no remote service, network, script, or Git state.
  • Do not edit, create, rename, move, delete, stage, commit, configure Git, or process Inbox items. The entire workflow remains read-only.

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.