agentleFS
jpantsjohajpantsjoha/ai-native-developer-experience/skills/sitrep/SKILL.md

sitrep

Skill13 starsChanged 27 days agoApache-2.0View on GitHub

Synthesise a status, standup, or situation-report from current work state. Trigger when a team member needs a concise summary of where things stand, what is blocked, and what is next.

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

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

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 3

    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:

    When a stakeholder asks "where are we?" and the honest answer is "it's complicated"

    line 18
  2. Distinctive:

    Keep current status separate from historical receipts.

    line 61
  3. Distinctive:

    Blocked means blocked: If something is moving slowly but not actually blocked, it belongs in "Next" with a note, not "Blocked."

    line 72

“Common” is measured: kept by at least 6 in 10 of the 12 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

Sitrep

Situation reports are for the person who was not in the room. Write for them.

A sitrep is not a diary of activity. It is a compressed, actionable picture of current state. Three questions: what is done, what is blocked, what is next. Anything that does not answer one of those three questions does not belong in the sitrep.

When to use

  • Daily standup synthesis from work logs, commits, or ticket state
  • End-of-sprint summary for stakeholders
  • Incident situation report during or after an active incident
  • Handoff summary when switching context or handing work to another agent or person
  • When a stakeholder asks "where are we?" and the honest answer is "it's complicated"

Procedure

  1. Gather the current work state — read from available sources:
    • Open and recently closed issues / tickets
    • Recent commits (last 24-48 hours for a standup; last sprint for a sprint summary)
    • Project status and roadmap documents (e.g. docs/operating-model/PROJECT-OPERATING-PROFILE.md, docs/ROADMAP.md, or equivalent per project structure)
    • Any blocking flags, risk register entries, or escalation notes
  2. Classify items into three buckets:
    • Done — the task's full acceptance and completion contract is evidenced; a passing test, closed ticket or deployment alone is insufficient
    • Blocked — work that cannot progress without a specific unresolved dependency (name the blocker precisely)
    • Next — the highest-priority items that will be worked next (ordered by priority)
  3. Write the sitrep — structure:
    ## Sitrep — <date> [<scope: sprint / incident / handoff>]
    
    **Done**
    - <item> — <one sentence on what was delivered and its evidence>
    
    **Blocked**
    - <item> — blocked on <specific dependency / owner / ETA if known>
    
    **Next**
    - <item> — <priority order, most important first>
    
    **Risks / flags** (optional — only if material)
    - <risk> — <impact if unresolved> — <owner>
  4. Apply the compression test — for each line: if removing it changes nothing that the reader needs to act on, remove it.
  5. Name blockers precisely — "blocked on backend" is not a blocker entry. "Blocked on API contract for /v2/orders — waiting on @owner, ETA unknown" is.
  6. Do not editorialise progress — "made good progress" is noise. "Delivered X, which unblocks Y" is signal.

Outputs

On milestone or release transitions, reconcile the current-fact matrix in workflow-audit.md. Keep current status separate from historical receipts. Report maturity dimensions, candidate/environment identity and unresolved evidence; never derive readiness from issue counts or version labels. Update generated dashboards only through their declared generator, and distinguish offline results from live tracker reconciliation.

  • A sitrep in the format above
  • Optional: a one-paragraph executive summary for stakeholders who need even less

Guardrails

  • No activity reporting. "Worked on the auth module" is not a sitrep entry. "Auth module: JWT validation complete, token refresh failing under load — investigating" is.
  • Blocked means blocked. If something is moving slowly but not actually blocked, it belongs in "Next" with a note, not "Blocked."
  • Done means done. "95% done" is not done. If it is not verifiably complete, it is "Next."
  • Length is not quality. A five-line sitrep that answers the three questions is better than a twenty-line one that does not.

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.