agentleFS
teachskillofskills-aiteachskillofskills-ai/DigitalMarketingPro-techshu/skills/crisis-response/SKILL.md

crisis-response

Skill0 starsChanged 9 months agoMITView on GitHub

Assess a PR crisis and deliver a structured response plan — severity classification (Level 1-3), a ready-to-publish holding statement, tailored messaging per stakeholder group, an hour-by-hour communication timeline, and a trust-rebuilding roadmap. Drafts and plans only; it publishes nothing. Triggers on \"/digital-marketing-pro:crisis-response\", \"we're getting slammed on social media\", \"draft a holding statement fast\", \"a negative story just broke about us\", \"how do we respond to this backlash\". Reads the brand profile, voice settings, guidelines, and market compliance rules before drafting any statement.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

/digital-marketing-pro:crisis-response

Purpose

Provide rapid crisis assessment and a structured response plan. Classifies severity, identifies stakeholders, drafts messaging for each audience, and builds a communication timeline to contain damage and rebuild trust.

Input Required

The user must provide (or will be prompted for):

  • What happened: Description of the crisis or incident
  • When it started: Timeline of events so far
  • Current exposure: How widely known is it (internal only, social media, press coverage)
  • Stakeholders affected: Customers, employees, investors, partners, public
  • Actions taken so far: Any statements, fixes, or responses already issued
  • Spokesperson: Who will speak for the brand

Process

  1. Load brand context: Read ~/.claude-marketing/brands/_active-brand.json for the active slug, then load ~/.claude-marketing/brands/{slug}/profile.json. Apply brand voice, compliance rules for target markets (skills/context-engine/compliance-rules.md), and industry context. Also check for guidelines at ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json — if present, load restrictions and relevant category files. Check for custom templates at ~/.claude-marketing/brands/{slug}/templates/. Check for agency SOPs at ~/.claude-marketing/sops/. If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with defaults.
  2. Severity classification: Level 1 (monitor), Level 2 (respond), Level 3 (full mobilization) based on reach, impact, and trajectory
  3. Assess the narrative: What is being said? What is the public sentiment? What is the worst-case escalation?
  4. Identify all stakeholder groups and prioritize communication order
  5. Draft holding statement for immediate release (within first hour)
  6. Draft tailored messaging per stakeholder: customers, employees, media, partners, social media
  7. Build communication timeline: first hour, first 24 hours, first week, ongoing
  8. Define channel strategy: which messages go where (social, email, press, internal comms)
  9. Outline recovery plan: corrective actions, transparency updates, trust-rebuilding initiatives
  10. Set monitoring cadence and escalation triggers

Output

A structured crisis response plan containing:

  • Severity classification with rationale
  • Situation assessment and narrative analysis
  • Holding statement (ready to publish)
  • Stakeholder-specific messaging (customers, media, employees, partners)
  • Communication timeline with milestones and decision points
  • Channel deployment plan
  • Social media response guidelines (what to reply, what to ignore, when to escalate)
  • Recovery and trust-rebuilding roadmap
  • Monitoring plan with escalation triggers

Agents Used

  • brand-guardian — Brand protection, messaging consistency, stakeholder communication, compliance
  • pr-outreach — Media relations, press statement, journalist engagement strategy

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.