agentleFS
VektoAIVektoAI/pmstack/brief/SKILL.md

brief

Skill0 starsChanged 8 months agoMITView on GitHub

Comms Strategist mode. Write exec briefs, board updates, team all-hands scripts, status reports, or stakeholder emails. Audience-aware — what the CEO needs is not what engineering needs. Modes: EXEC, BOARD, TEAM, STATUS, EMAIL.

78 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use capture, strategy 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.
  • toneron2Skill

    capture

    Capture thoughts to inbox with automatic classification

    Also in 6 projects that use this

  • EpistatesSkill

    strategy

    Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.

    Also in 4 projects that use this

  • aleksander-dytkoSkill

    decision

    Make a product decision with full context from the vault and available sources

    Also in 3 projects that use this

  • dirienSkill

    decide

    Three-agent adversarial debate protocol for strategic decisions. Two advocates steelman opposing positions while a moderator identifies risks and synthesizes a binding consensus. Use when choosing between alternatives, evaluating tradeoffs, or making high-stakes decisions.

    Also in 5 projects that use this

  • JaimeGBASkill

    ingest

    Digest an external source (article, paper, transcript, URL, book chapter) and integrate its content into the knowledge base

    Also in 7 projects that use this

  • howellsSkill

    reconcile

    Audit a project against current plugin conventions and offer to update structure.

    Also in 3 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 71 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:

    The anxiety test: After reading your brief, should the audience feel more confident or more anxious?

    line 26
  2. Distinctive:

    If a flag is provided, skip the audience selection question and go directly to that mode.

    line 55
  3. Distinctive:

    If no decision is needed, say "FYI only" explicitly.

    line 105
  4. Distinctive:

    Treat the team as adults. Don't over-explain obvious decisions.

    line 189
  5. Distinctive:

    If you need a decision, make it easy: options + recommendation + deadline

    line 248
  6. Distinctive:

    Every brief starts with audience and purpose

    line 254
  7. Distinctive:

    After delivering the brief, end with: "Ready for: feedback and iteration, or /launch (if this brief supports a launch communication)"

    line 260

“Common” is measured: kept by at least 6 in 10 of the 71 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

{{PREAMBLE}}

Stakeholder Communication Mode

Philosophy

Every communication has an audience, and every audience has a question they're trying to answer. The CEO wants to know: "Should I worry about this?" The board wants: "Is the company on track?" Engineering wants: "What should we build next and why?" If you don't know the audience's question, you'll write a document that answers the wrong one.

The pyramid principle: Lead with the conclusion, then support it. Not "we did A, B, C, therefore X." Instead: "X. Here's why: A, B, C." Busy people read the first paragraph. Make it count.

The anxiety test: After reading your brief, should the audience feel more confident or more anxious? If the answer is "neither," the brief has no point. If the answer is "anxious," make sure that's intentional — don't accidentally alarm.

Audience Selection

Ask the user (via AskUserQuestion):

Who is the audience and what format do they need?

RECOMMENDATION: Choose the audience that drives the most critical decision right now.

A) EXEC — C-suite or VP. They want: decision needed, business impact, risks, timeline. (<1 page) B) BOARD — Board of directors. They want: strategic progress, key metrics, asks. (1-2 pages) C) TEAM — Engineering/product team. They want: what's changing, why, what it means for their work. (verbal or written) D) STATUS — Regular status update. They want: progress vs plan, blockers, next steps. (template) E) EMAIL — Specific stakeholder email. They want: context, ask, deadline. (short)


How to Use

/brief                    → Interactive: asks you to choose audience
/brief --audience exec    → Jump straight to EXEC mode
/brief --audience board   → Jump straight to BOARD mode
/brief --audience team    → Jump straight to TEAM mode
/brief --status           → Jump straight to STATUS mode
/brief --email            → Jump straight to EMAIL mode

If a flag is provided, skip the audience selection question and go directly to that mode. If no flag, ask.


EXEC Mode

The executive brief. One page or less. Every word earns its place.

[TITLE] — Executive Brief
══════════════════════════
Date: [Date]
Author: [Name]
For: [Specific names/roles]
Decision needed by: [Date, or "FYI only"]

─── BOTTOM LINE ───
[2-3 sentences: What's happening, what it means, what you need from them.
This paragraph must stand alone — if they read nothing else, they get it.]

─── CONTEXT ───
[3-5 sentences: Background the reader needs. Not the full history —
just enough to understand the bottom line. Assume they haven't thought
about this topic in 2 weeks.]

─── OPTIONS ─── (if a decision is needed)
A) [Option] — [Pro] / [Con] / [Impact: timeline, cost, risk]
B) [Option] — [Pro] / [Con] / [Impact]
C) [Option] — [Pro] / [Con] / [Impact]

RECOMMENDATION: [Option X] because [one-line reason].

─── KEY METRICS ─── (if relevant)
| Metric | Current | Target | Trend |
|--------|---------|--------|-------|
| [Metric] | [Value] | [Value] | ↑ ↓ → |

─── RISKS ───
1. [Risk] — Mitigation: [Action] — Owner: [Who]
2. [Risk] — Mitigation: [Action] — Owner: [Who]

─── TIMELINE ───
[Key milestones only — 3-5 dates max]

─── APPENDIX ─── (optional — for those who want depth)
[Details that support the brief but aren't essential to the decision]

Exec brief rules:

  • Bottom line is FIRST, not last. Execs decide whether to keep reading based on the first paragraph.
  • If no decision is needed, say "FYI only" explicitly. Don't make them guess.
  • Options have trade-offs. If one option is obviously better, just recommend it and skip the theater.
  • Metrics show trend, not just current state. "Revenue is $5M" means nothing. "Revenue is $5M, up 15% MoM against $4.5M target" tells a story.

BOARD Mode

Board updates are about pattern recognition and strategic confidence.

[COMPANY/PRODUCT] — Board Update
═════════════════════════════════
Period: [Timeframe]
Prepared by: [Name, Title]

─── EXECUTIVE SUMMARY ───
[3-5 sentences: Where we are relative to plan. What the board should take away.
Frame as progress narrative, not activity report.]

─── KEY METRICS ───
| Metric | Period Start | Period End | Target | Status |
|--------|-------------|-----------|--------|--------|
| [North star] | [Value] | [Value] | [Value] | 🟢🟡🔴 |
| [Revenue/ARR] | [Value] | [Value] | [Value] | 🟢🟡🔴 |
| [Growth] | [Value] | [Value] | [Value] | 🟢🟡🔴 |
| [Retention] | [Value] | [Value] | [Value] | 🟢🟡🔴 |

─── STRATEGIC PROGRESS ───
[For each strategic priority: 2-3 sentences on progress, 1 sentence on what's next]

1. [Priority 1]: [Progress summary]
2. [Priority 2]: [Progress summary]
3. [Priority 3]: [Progress summary]

─── WHAT'S WORKING ───
[2-3 specific wins with data. Not "team is working hard" — measurable outcomes.]

─── WHAT'S NOT WORKING ───
[2-3 specific challenges with plans to address. Boards respect honesty more than spin.]

─── ASKS ───
[Specific asks of the board — introductions, decisions, approvals, advice.
If no asks, state "No asks this period — FYI update."]

─── LOOKING AHEAD ───
[Top 3 priorities for next period and what success looks like]

TEAM Mode

Internal team communication. Can be written or verbal (talking points for an all-hands).

Team Update: [Topic]
════════════════════

─── WHAT'S CHANGING ───
[Plain English: What is different, starting when]

─── WHY ───
[The reasoning. Not "leadership decided" — the actual logic.
Teams trust decisions they understand, even if they disagree.]

─── WHAT IT MEANS FOR YOU ───
[Specific impact on the team's day-to-day work]
- [Role/team A]: [How this affects your work]
- [Role/team B]: [How this affects your work]

─── WHAT'S NOT CHANGING ───
[Equally important — reduces anxiety. "Your current project is unaffected."]

─── TIMELINE ───
[When things happen]

─── QUESTIONS? ───
[How to ask questions, where decisions can still be influenced, what's final]

Team comms rules:

  • Lead with "what's changing," not "why." People want to know the impact first, then the reasoning.
  • "What's NOT changing" is as important as what is. Teams catastrophize in the absence of information.
  • Treat the team as adults. Don't over-explain obvious decisions. Don't under-explain controversial ones.

STATUS Mode

Regular status updates. Designed for scan-ability.

Status Update: [Project/Team] — Week of [Date]
═══════════════════════════════════════════════
Overall: 🟢 On Track / 🟡 At Risk / 🔴 Blocked

─── PROGRESS ───
✅ Completed: [2-3 items with impact, not just "done"]
🔄 In Progress: [2-3 items with % or ETA]
⏸️ Blocked: [Items + what's blocking + who can unblock]

─── METRICS ───
[2-3 numbers that matter this week]

─── NEXT WEEK ───
[Top 3 priorities — specific, measurable]

─── RISKS / ESCALATIONS ───
[Only if something needs attention from leadership]

EMAIL Mode

Stakeholder email. Clear ask, minimal friction.

Subject: [Action needed / FYI]: [Topic] — [Deadline if applicable]

[Name],

[1-2 sentences: Context — why you're emailing them specifically]

[1-2 sentences: The ask or the information]

[If decision needed:]
Options:
A) [Option]
B) [Option]
I recommend [X] because [reason]. Can you confirm by [date]?

[If FYI:]
No action needed — just keeping you in the loop. Happy to discuss if questions.

[Sign-off]

Email rules:

  • Subject line tells them what to do: "Action needed" or "FYI"
  • First sentence explains why THEY are receiving this email
  • The ask is in the first 3 sentences, not buried at the bottom
  • If you need a decision, make it easy: options + recommendation + deadline

Formatting Rules

  • Every brief starts with audience and purpose
  • Bottom line / conclusion is ALWAYS first, not last
  • Metrics include trend (↑↓→), not just current value
  • Risks have mitigations and owners
  • "FYI" is stated explicitly when no action is needed
  • Match the audience's vocabulary — no engineering jargon in exec briefs, no business jargon in team updates
  • After delivering the brief, end with: "Ready for: feedback and iteration, or /launch (if this brief supports a launch communication)"

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.