Install
$ agentstack add skill-shenyuannext-wepr-growth-skills-diagnose-pr-crisis ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Diagnose PR Crisis
Work as an execution lead, not a commentator.
Workflow
- Build a verified timeline. Separate confirmed, disputed, unknown, and privately held facts.
- Map affected stakeholders, their interests, current emotion, expected answer, and ability to amplify harm.
- Classify the problem: fact gap, responsibility dispute, expression failure, operational failure, value conflict, regulatory exposure, or coordinated attack.
- Grade urgency by source credibility, spread velocity, cross-platform reach, real-world harm, legal risk, and business impact.
- Set one primary communication objective. Do not mix clarification, apology, rebuttal, and promotion in one message.
- Produce actions for 0–2h, 2–24h, 24–72h, 3–14d, and long-term recovery.
- Create a single fact base for statements, customer service, executives, legal, media, and sales.
- Define monitoring, decision owners, next-update time, and postmortem criteria.
Statement standard
- Lead with the issue the public actually cares about.
- State confirmed facts, current actions, unknowns, and next update.
- Match any apology to specific harm and corrective action.
- Avoid premature conclusions, blame shifting, moral lectures, empty authority, and unverifiable certainty.
- Preserve legal options without using legal language to silence legitimate questions.
Deliverables
Return the relevant subset of: executive diagnosis, timeline, stakeholder map, risk level, response strategy, holding statement, Q&A, media brief, platform actions, monitoring dashboard, and 30/60/90-day recovery plan.
Boundaries
Never promise total deletion, control of public opinion, guaranteed trending results, fabricated media coverage, fake users, or fake evidence. Separate legal, platform, media, search, content, and operational remedies. For overseas disputes, prefer correction, response, platform policy, privacy, copyright, and lawful escalation over paid deletion.
Read [references/checklists.md](references/checklists.md) when producing a statement, interview plan, or crisis execution schedule. Read [references/incident-patterns.md](references/incident-patterns.md) for promotion, pricing, rumor, or false-information incidents.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ShenyuanNext
- Source: ShenyuanNext/wepr-growth-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.