How do I install the Innovate Redteam skill?

Run npx skillmds@latest add aibot88/innovate-redteam in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Innovate Redteam safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Innovate Redteam?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Innovate Redteam free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Innovate Redteam?

aibot88 (@aibot88) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Innovate Redteam by aibot88 — Agent Skill

Name: Innovate Redteam
Rating: 4.2 (5 reviews)
Author: aibot88

Innovate Redteam

Run the Vibe Innovation Framework red team protocol on any artifact (problem statement, concept, business model, experiment design, prototype, decision). Use when stress-testing an artifact against adversarial framings outside the usual phase Step 7 moment, or as a standalone sanity check before locking an output.

aibot88 Updated Sep 9, 2026 3 repo stars

File contents

Target requested: $ARGUMENTS

Read the following files in order before acting.

.claude/docs/red_team_protocol.md (the canonical protocol, with question sets per phase and per lens)
.claude/docs/principles_and_antipatterns.md (the cognitive bias watchlist that the protocol implements)
The relevant phase prompt only if a Phase artifact is targeted (for example, phase_2_ideation.md for Phase 2 Step 7).

Then execute the protocol exactly as specified there. The protocol is self-contained: triggers, lens catalog, question sets per phase, scoring rubric, output template.

Operating notes

Input resolution. Parse the argument into one of three input shapes. phase-N section-X resolves to the corresponding ICD section and runs the phase-specific question set. free plus a free-text artifact runs the generic set. decision plus a pending decision runs the Phase 5 decision question set. If the argument is empty, ask which input shape applies before proceeding.
Lens count. Use at least three lenses, with at least one user-side, one competitor-side, and one failure-mode lens. Two passes are required if the first pass produces only Addressed and Out of scope outcomes.
No straw men. Each lens generates the strongest version of its challenge. Weak challenges are filtered out before presenting to the user.
Logging. For phase Step 7 invocations, the summary lives inside the phase output. For standalone invocations, log under Section 8 (Decision log) as a Strategic entry with type Red team.
Working language. Detect the user's working language from their last message. Translate the question sets and the summary block into that language. Keep the structure and tone faithful.
Routing. End with the routing line: proceed to the next step, iterate within the current step, trigger a mini-gate loop-back (use /innovate-loopback), or escalate to a kill or pivot decision (use /innovate-phase 5).

Respond in the language the user is writing in.

---name: innovate-redteamdescription: Run the Vibe Innovation Framework red team protocol on any artifact (problem statement, concept, business model, experiment design, prototype, decision). Use when stress-testing an artifact against adversarial framings outside the usual phase Step 7 moment, or as a standalone sanity check before locking an output.--- **Target requested:** $ARGUMENTS Read the following files in order before acting. 1. `.claude/docs/red_team_protocol.md` (the canonical protocol, with question sets per phase and per lens) 2. `.claude/docs/principles_and_antipatterns.md` (the cognitive bias watchlist that the protocol implements) 3. The relevant phase prompt only if a Phase artifact is targeted (for example, `phase_2_ideation.md` for Phase 2 Step 7). Then execute the protocol exactly as specified there. The protocol is self-contained: triggers, lens catalog, question sets per phase, scoring rubric, output template. ## Operating notes 1. **Input resolution.** Parse the argument into one of three input shapes. `phase-N section-X` resolves to the corresponding ICD section and runs the phase-specific question set. `free` plus a free-text artifact runs the generic set. `decision` plus a pending decision runs the Phase 5 decision question set. If the argument is empty, ask which input shape applies before proceeding. 2. **Lens count.** Use at least three lenses, with at least one user-side, one competitor-side, and one failure-mode lens. Two passes are required if the first pass produces only *Addressed* and *Out of scope* outcomes. 3. **No straw men.** Each lens generates the strongest version of its challenge. Weak challenges are filtered out before presenting to the user. 4. **Logging.** For phase Step 7 invocations, the summary lives inside the phase output. For standalone invocations, log under Section 8 (Decision log) as a Strategic entry with type `Red team`. 5. **Working language.** Detect the user's working language from their last message. Translate the question sets and the summary block into that language. Keep the structure and tone faithful. 6. **Routing.** End with the routing line: proceed to the next step, iterate within the current step, trigger a mini-gate loop-back (use `/innovate-loopback`), or escalate to a kill or pivot decision (use `/innovate-phase 5`). Respond in the language the user is writing in.

Frequently asked questions