agentleFS
rade-nugrohorade-nugroho/Agentic-Enteprises-Skill/communication-lead/SKILL.md

communication-lead

Skill9 starsChanged 6 months agoMITView on GitHub

Guides communications leadership—messaging strategy, narrative and key-message development, stakeholder and executive comms cadence, internal announcements (all-hands, change, crisis), external customer and partner messaging, launch and incident communication plans, channel selection, approval workflows, and spokesperson/Q&A prep. Use when planning org-wide comms, drafting executive or company-wide messages, aligning narratives across teams, designing change or crisis communications, or preparing launch announcements—not for management consulting deliverables (business-consultant), API/docs/runbooks (tech-writer-researcher), on-call/paging/SEV program design (incident-management-engineer), single-ticket customer replies (support-engineer), exec/community escalation program (community-executive-escalations-program-manager), developer training programs (developer-education-lead), or legal contract language (commercial-counsel).

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use pyramid structure: recommendation first, then support.

    line 80
  2. Very specific:

    Never promise dates or features not shipped.

    line 102

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “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

Communication Lead

When to Use

  • Define messaging hierarchy: narrative, pillars, proof points, audience variants
  • Plan comms for a launch, reorg, policy change, or transformation
  • Draft executive updates, all-hands scripts, company-wide email/Slack posts
  • Build crisis or incident message packs (holding lines, customer statements) with approval path
  • Align product, sales, and support on what to say (and not say) externally
  • Design comms cadence: weekly exec brief, monthly all-hands, incident updates
  • Prepare spokesperson talking points and anticipated Q&A

When NOT to Use

  • Issue trees, business cases, steerCo slide analysis → business-consultant
  • Technical documentation, runbooks, API reference → tech-writer-researcher
  • Severity model, paging, on-call, postmortem process → incident-management-engineer
  • Outage rollback and deploy tactics → deployment-strategist, devops
  • Individual support ticket responses → support-engineer
  • Marketing campaign creative, paid media, SEO → route to marketing skills if present; stay factual/product-truth aligned here
  • Contract, DPA, or legal risk language → commercial-counsel
  • Security control design → cybersecurity

Related skills

NeedSkill
Executive deck storyline and business casebusiness-consultant
Long-form docs and research synthesistech-writer-researcher
Incident program, status page workflowincident-management-engineer
Release rollout and stakeholder briefdeployment-strategist
Cross-team program coordinationtechnical-program-manager
Developer training and certification programsdeveloper-education-lead
Customer escalation and ticket commssupport-engineer
Exec/VIP and community escalation programcommunity-executive-escalations-program-manager
Security incident policy and enterprise IRcybersecurity
Security advisory and CVD publicationtechnical-program-manager-security-cvd
Product positioning and UX copyproduct-designer
Commercial terms in customer commscommercial-counsel

Core Workflows

1. Messaging framework

For any initiative, define:

  1. Audience — who must hear, believe, and act
  2. Objective — one outcome (e.g., adopt, reassure, comply)
  3. Narrative — 2–3 sentence through-line (problem → direction → ask)
  4. Key messages — 3–5 bullets, MECE, evidence-backed
  5. Proof points — metrics, quotes, dates (no unverified claims)
  6. Guardrails — what not to say; sensitive topics; legal review triggers

See references/messaging_framework.md.

2. Stakeholder and executive comms

ArtifactTypical cadenceLead with
Exec briefWeeklyDecision or risk needing attention
SteerCo / leadership updatePer milestoneStatus vs plan, blockers, asks
Board-style summaryQuarterlyOutcomes, risks, strategic choices

Use pyramid structure: recommendation first, then support. Pair with business-consultant when the pack is primarily analytical.

See references/stakeholder_comms.md.

3. Internal communications

  • All-hands — 30–45 min arc: context, wins, priorities, Q&A
  • Change — why, what changes for whom, timeline, support channels
  • Manager cascade — toolkit: email template, FAQ, office hours

Sequence: leaders briefed first → company announcement → team Q&A.

See references/internal_comms.md.

4. External communications

Align with product truth and legal review for:

  • Customer email, in-app banners, changelog
  • Partner or investor-facing notes (when approved)
  • Blog or press statement (factual, attributable quotes only)

Never promise dates or features not shipped; coordinate with deployment-strategist for launch timing.

See references/external_comms.md.

5. Crisis and incident messaging

Separate process (incident-management-engineer) from words:

  1. Confirm facts with incident commander; no speculation
  2. Draft internal holding line → customer status → follow-up cadence
  3. Route legal/comms/security approval per severity
  4. Single source of truth doc; version messages

See references/crisis_comms.md.

6. Launch communications

PhaseComms focus
T-4 weeksInternal preview, enablement, FAQ
T-1 weekSales/support talk tracks
LaunchCoordinated send: email, blog, in-app, social (if approved)
T+1 weekMetrics, feedback loop, correction if needed

See references/launch_comms.md.

Output standards

  • One primary CTA per message
  • Plain language; define acronyms once
  • Accessible formatting (headings, short paragraphs)
  • Version and timestamp on crisis or incident drafts
  • Flag [LEGAL REVIEW], [EXEC APPROVAL] where required

When to load references

  • Messaging hierarchy → references/messaging_framework.md
  • Exec and leadership updates → references/stakeholder_comms.md
  • All-hands and change → references/internal_comms.md
  • Customer and public → references/external_comms.md
  • Incident statements → references/crisis_comms.md
  • Feature or initiative launch → references/launch_comms.md

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.