Signal Flare

5-stage regulatory-escalation framework for legitimate users stuck in dead platform-support loops.

Works with setup

Test report

Verdict
Works with setup
Score
8.8/10
Tested
Jul 16, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Aug 10, 2026 · b12dd54

Unusually well-guarded for a high-stakes skill — a hard ownership-verification gate, a mandatory outline-before-prose protocol on every regulatory document, and an explicit ban on inventing facts or naming legal theories. But platforms/discord.md instructs Claude to read three Discord-specific templates (server-transfer-request.md, server-restoration-request.md, discord-partner-escalation.md) that don't exist anywhere in the repo — a real dead end for Discord server-hijacking cases specifically, undisclosed in STATUS.md or the README.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 4/5
  • Triggers reliably 5/5
  • Output vs. baseline 9/10
  • Docs & honesty 4/5

What Signal Flare does

Walks a verified, legitimate account owner through a 5-stage escalation ladder — internal legal notice, state Attorney General complaint, FTC complaint, congressional constituent services, and attorney demand letter — when standard platform support has stalled on a hijacking, ban, lockout, billing dispute, or impersonation case. Triggers on distress language like 'my account got hacked'/'support won't respond', gates hard on provable legitimate ownership before proceeding, and refuses to name legal theories or invent facts.

How to install Signal Flare

git clone https://github.com/ChrisPirillo/signal-flare
mkdir -p ~/.claude/skills
cp -r signal-flare ~/.claude/skills/signal-flare

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Signal Flare

  • /signal-flare 5-stage regulatory-escalation framework for legitimate users stuck in dead platform-support loops.

It also activates on plain-language prompts like these:

  • My Instagram business account got hacked and support won't respond at all
  • Walk me through filing an FTC complaint after my account got hijacked
  • Help me escalate this billing dispute since customer support is stalling

Frequently asked questions

Is the Signal Flare skill free?
Yes. The skill itself is free from ChrisPirillo/signal-flare. SkillProof publishes the install command and an independent test verdict at no cost.
Does Signal Flare work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Unusually well-guarded for a high-stakes skill — a hard ownership-verification gate, a mandatory outline-before-prose protocol on every regulatory document, and an explicit ban on inventing facts or naming legal theories. But platforms/discord.md instructs Claude to read three Discord-specific templates (server-transfer-request.md, server-restoration-request.md, discord-partner-escalation.md) that don't exist anywhere in the repo — a real dead end for Discord server-hijacking cases specifically, undisclosed in STATUS.md or the README.
What is the Signal Flare SkillProof Score?
8.8/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 9/10, docs & honesty 4/5.
How do I install Signal Flare?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Signal Flare with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.