Flywheel Nudge — Testing skill for Claude Code
Apply the agent-flywheel first-turn maturity nudge (spec-first, delegate, verify-before-done) plus active guardrails to the current task now.
How to install Flywheel Nudge
Installs to ~/.claude/skills/abhishekgarg18-agent-flywheel-flywheel-nudge/SKILL.md
mkdir -p ~/.claude/skills/abhishekgarg18-agent-flywheel-flywheel-nudge && curl -fsSL https://raw.githubusercontent.com/abhishekgarg18/agent-flywheel/HEAD/commands/flywheel-nudge.md -o ~/.claude/skills/abhishekgarg18-agent-flywheel-flywheel-nudge/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Flywheel Nudge does
description: Apply the agent-flywheel first-turn maturity nudge (spec-first, delegate, verify-before-done) plus active guardrails to the current task now
Before continuing, apply the agent-flywheel maturity nudge to the task in front of you. Use your file-read tool on this exact path and follow it:
`${CLAUDE_PLUGIN_ROOT}/core/prompts/maturity-nudge.txt`
Then also surface any binding corrections from past sessions: read `~/.agent-flywheel/GUARDRAILS.md` if it exists and treat the entri
Alternatives in Testing
- #29 — #52, #103) 92.5k ★
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Spec Draft PR — Turn a feature idea or GitHub issue into a one-page spec saved to Documentation/specs/ and opened as a draft P 324 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Add
ADD — Agent Driven Development. Coordinated AI agent teams that ship verified software. Spec-driven TDD, trust
Proofpunk
Proofpunk — execution-first delivery plugin for Claude Code, oh-my-pi (OMP), and OpenCode. 18 skills where don
Myflow Controller
A controller for AI coding agents that takes 'done' away from the model: a Claude Code skill plus a stdlib-onl
Spec Rebase
Reconcile an active change's deltas with the current living spec when /ai-sdlc:spec-archive aborted on slug co
Code Max
Agent skill that makes a coding agent verify before it claims done — no stubs, no fabricated test results, evi
Al Plan
Turn an approved spec (or a described task) into an ordered, single-track implementation plan
Related Agents
Character Simulator
Run one character's turn in a simulated world. Given who the character is (persona, values, drives, current st
AI Readiness Reporter.Agent
Runs the AgentRC readiness assessment on the current repository and produces a self-contained, static HTML das
Blueprint Scout
Read-only research scout for recognition wins. Given an active Lean blueprint project, pulls its lemma depende