Build a phased reputation recovery plan after a crisis — from damage assessment through stakeholder communication, trust-rebuilding actions, and sentiment tracking. Use when: rebuilding brand reputation post-crisis, designing a public apology and accountability strategy, creating stakeholder-specific recovery communications, tracking sentiment recovery metrics, planning a PR damage-control roadmap, or recovering from a data breach, product recall, or public backlash.
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill reputation-recovery
> Build a phased reputation recovery plan after a crisis — from damage assessment through stakeholder communication, trust-rebuilding actions, and sentiment tracking.
| Aspect | Details |
|--------|---------|
| Source | Edelman Trust Barometer, Burson reputation recovery frameworks |
| Core Principle | Trust rebuilds through actions, not words — transparency, accountability, competence, then character, in that order |
| Recovery Phases | Stabilize → Acknowledge → Act → Communicate → Measure |
| Claude Does | You Decide |
|-------------|------------|
| Designs phased recovery roadmap with timelines | Investment level and resource allocation |
| Drafts stakeholder communications and apology frameworks | Spokesperson selection and timing |
| Creates measurement dashboards and recovery criteria | Acceptable recovery timeline |
| Prioritizes stakeholder groups and actions | Which initiatives to fund |
Build a damage baseline across key dimensions:
| Dimension | Pre-Crisis | Post-Crisis | Gap |
|-----------|------------|-------------|-----|
| Trust score | — | — | — |
| NPS | — | — | — |
| Brand sentiment (% positive) | — | — | — |
| Media tone | — | — | — |
| Customer retention | — | — | — |
Validation checkpoint: If you lack pre-crisis baselines, estimate from industry benchmarks before proceeding.
| Phase | Duration | Focus | Exit Criteria |
|-------|----------|-------|---------------|
| Stabilize | Weeks 1-2 | Stop the bleeding, full accountability | Crisis chapter closed, compensation launched |
| Rebuild | Months 1-3 | Demonstrate concrete structural changes | New processes in place, advisory board active |
| Demonstrate | Months 3-6 | Build track record, earn positive coverage | 3 months positive media, trust at 80% baseline |
| Sustain | Month 6+ | Long-term reputation building | Meet all recovery completion criteria |
| Stakeholder | Priority | Key Concern | Approach |
|-------------|----------|-------------|----------|
| Customers | P1 | Trust, safety | Transparency + compensation |
| Employees | P1 | Job security, pride | Internal comms + involvement |
| Investors | P2 | Financial impact | Recovery plan + milestones |
| Partners | P2 | Association risk | Assurance + collaboration |
| Regulators | P2 | Compliance | Cooperation + prevention |
| Public | P3 | Values alignment | Actions over words |
Apply the trust-rebuilding sequence (order matters):
| Action Type | Examples | Timeline |
|-------------|----------|----------|
| Transparency | Full incident report, public updates, data access | Immediate |
| Accountability | CEO apology, personnel changes, compensation | Week 1-2 |
| Competence | New processes, third-party audits, team expansion | Month 1-3 |
| Character | Values-aligned initiatives, sustained behavior change | Ongoing |
CEO apology framework: Direct acknowledgment → What went wrong → What we've done → What we're doing → Personal accountability → How to reach us.
| Metric | Frequency | Target |
|--------|-----------|--------|
| Brand sentiment | Weekly | Return to baseline |
| Trust score | Monthly | 80% of pre-crisis |
| NPS | Monthly | Return to positive |
| Media tone | Weekly | Neutral → positive |
| Customer retention | Monthly | Pre-crisis rate |
Recovery completion criteria:
Input: Product safety incident, 3 weeks in crisis mode, 30% trust drop, 15% churn, issue resolved.
Recovery roadmap:
| Month | Phase | Key Actions |
|-------|-------|-------------|
| 1 | Stabilize | CEO video apology, full incident report, compensation program, employee town hall |
| 1-3 | Rebuild | Safety team +3 hires, external advisory board, quarterly third-party audits |
| 3-6 | Demonstrate | Public safety reports, customer testimonials, thought leadership content |
| 6+ | Sustain | Ongoing transparency reports, industry standards participation |
Projected timeline: 6-9 months to full recovery with aggressive action.
See TEMPLATES.md for communication templates (CEO apology script, milestone update emails, stakeholder briefing outlines).
crisis-detector — Prevention and early warningresponse-coordinator — During active crisissocial-listening — Monitoring recovery sentimentExpert startup business analyst specializing in market sizing, financial modeling, competitive analysis, and strategic planning for early-stage companies. Use PROACTIVELY when the user asks about market opportunity, TAM/SAM/SOM, financial projections, unit economics, competitive landscape, team planning, startup metrics, or business strategy for pre-seed through Series A startups.
This skill should be used when the user asks to "plan team structure", "determine hiring needs", "design org chart", "calculate compensation", "plan equity allocation", or requests organizational design and headcount planning for a startup.
End-to-end bulk RNA-seq orchestrator — takes raw FASTQ reads through QC and trimming (FastQC, fastp/Trim Galore), alignment and quantification (STAR, Salmon, featureCounts), assembles a gene-level counts matrix, then hands off to differential expression (pydeseq2), pathway/GSEA enrichment (pathway-enrichment), and publication figures (scientific-visualization). Use whenever the user has bulk RNA-seq reads or quant output and wants a complete, reproducible differential-expression workflow — e.g. "analyze my RNA-seq", "FASTQ to DESeq2", "run nf-core/rnaseq", "STAR/Salmon quantification", "build a counts matrix for DESeq2", or "go from reads to differentially expressed genes and enriched pathways". Routes between an nf-core/rnaseq (Nextflow) path and a standalone STAR/Salmon path, and covers experimental design, strandedness, and QC gates. For single-cell RNA-seq use the scanpy skill instead.
Generate project status reports from Jira issues and publish to Confluence. When an agent needs to: (1) Create a status report for a project, (2) Summarize project progress or updates, (3) Generate weekly/daily reports from Jira, (4) Publish status summaries to Confluence, or (5) Analyze project blockers and completion. Queries Jira issues, categorizes by status/priority, and creates formatted reports for delivery managers and executives.
Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.
Google Workflow: Today's meetings + open tasks as a standup summary.
Read event data from a Google Sheets spreadsheet and create Google Calendar entries for each row.
Create professional, dark-themed SVG diagrams of any type — architecture diagrams, flowcharts, sequence diagrams, structural diagrams, mind maps, timelines, illustrative/conceptual diagrams, and more. Use this skill whenever the user asks for any kind of technical or conceptual diagram, visualization of a system, process flow, data flow, component relationship, network topology, decision tree, org chart, state machine, or any visual representation of structure/logic/process. Also trigger when the user says "画个图" "画一个架构图" "diagram" "flowchart" "sequence diagram" "draw me a ..." or uploads content and asks to visualize it. Output is always a standalone .svg file.
Take guia-matthieu/reputation-recovery from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.