By nicknisi
Transform brain dumps into implementation specs through an evidence-gated interview stress-tested by adversarial plan critics. Interactive HTML contract for planning decisions, Markdown specs for execution. /ideation:autopilot runs all phases on a deterministic workflow engine with overlap-serialized parallel waves; /ideation:retro mines implementation notes into learnings future interviews read.
Adversarial reviewer for ideation contracts. Reads contract-data.json before approval and produces structured findings through one of three lenses (scope-creep, hidden-dependency, success-criteria). Cannot edit files — enforced by tool restrictions.
Spec-aware code reviewer for execute-spec. Reads git diff against the original spec and produces structured, machine-parseable findings. Cannot edit files — enforced by tool restrictions.
Gate-based codebase exploration for execute-spec. Evaluates implementation readiness across 5 evidence gates and produces a persisted context map. Read-only — never edits files.
Orchestrate full execution of an ideation project — reads the contract, builds an execution manifest, and runs all phases on the deterministic Workflow engine (parallel for independent phases, sequential for dependent ones). Auto-continues on success, gates on failure. Use after ideation is complete and specs are approved.
Execute an implementation spec generated by ideation. Invokes Scout for codebase exploration, builds components with feedback loops, then runs a Verify-Review-Fix cycle with the Reviewer agent before committing.
Generate a /goal command that runs an ideation project to completion UNATTENDED by driving /ideation:autopilot. The /goal is a durability wrapper — it keeps autopilot going across hours/sessions and recovers from failures, while autopilot's Workflow engine does the dependency-ordered dispatch. Reads the contract, builds the /goal, copies it to the clipboard, and prints it. Use when the user says 'goal', 'run as goal', 'goal prompt', or wants to run the project long-haul/unattended rather than watching /ideation:autopilot interactively.
You MUST use this before building any new feature, planning a migration, designing a system, or turning scattered ideas into a plan. Triggers on: feature requests, project ideas, brain dumps, 'help me plan,' 'spec this out,' 'think through this,' 'interview me,' 'I want to build,' 'let's design,' or any unstructured idea that needs structure before code. Covers small single-spec projects through multi-phase initiatives. Runs a conversational interview, writes an interactive HTML contract, then generates implementation-ready Markdown specs. Skip ONLY for well-defined implementation tasks (writing code to a known spec, fixing bugs, refactoring, explaining code).
Mine a completed ideation project's implementation notes for generalizable spec-gap patterns and append them to a repo-level docs/ideation/learnings.md, so future interviews and specs learn from past gaps. Reads the project's implementation-notes-phase-*.html, contract.md, and git history; keeps only patterns that would change how future specs or interviews are written; dedupes against existing entries and retires entries the current codebase has invalidated. Use when the user says 'retro', 'run a retro', 'what did we learn', or after an ideation project completes.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Transform brain dumps into structured implementation artifacts through a conversational interview. HTML is used for interactive decision-making (the Mission Brief contract with evidence-gate readiness, visual comparisons during the interview). Markdown is used for reference documents (specs, PRDs) consumed directly by /ideation:execute-spec. Includes an execution workflow for implementing specs in fresh sessions with per-component feedback loops, adversarial plan critics, a Scout/Reviewer agent pipeline, and a retro loop that feeds learnings back into future runs.
This release ships the full Fable 5 upgrade. Six behavior changes, plus one breaking schema change:
ready or not-ready, justified by a concrete artifact. The contract proceeds only when all 5 are ready (or the user ends the interview early). See Evidence Gates.ideation:scout, ideation:reviewer, ideation:plan-critic) invoked with per-invocation inputs only — their workflow, output format, and read-only tool restrictions live in the agent definitions and are enforced by the platform.scope-creep, hidden-dependency, success-criteria) review the plan in parallel while a blocker is still a one-line JSON edit. A Critic digest is shown at the approval gate. See Plan Critics.Explore agents at intake so the first question is already informed. Skipped for greenfield work.AskUserQuestion previews (monospace, side-by-side) and escalate to ephemeral HTML only when the decision hinges on real visual rendering./ideation:autopilot and --parallel execution plan waves with a tested CLI that serializes any phases declaring overlapping files, so two phases never race the same file. See Orchestration./ideation:retro mines a completed project's implementation notes for generalizable spec-gap patterns and appends them to a repo-level docs/ideation/learnings.md that future interviews read. See Retro.Breaking change —
contract-data.jsonschema. The contract now uses agatesobject instead of the oldconfidenceobject. Regenerating an old contract fails fast:contract-data.json uses the pre-gate `confidence` schema; regenerate via ideation to produce the `gates` schema.Re-run ideation on the project to produce a
gates-shapedcontract-data.json. Specs also gained an optional per-phasefilesmanifest field (the paths a phase touches), used by the autopilot/parallel engine to serialize file-overlapping phases.
Transforms raw, unstructured brain dumps (dictated freestyle) into actionable implementation artifacts through an evidence-gated workflow.
Use this before building any new feature, planning a migration, designing a system, or turning scattered ideas into a plan. Covers small single-spec projects through multi-phase initiatives.
How to invoke:
Use the ideation skill
[provide your brain dump - messy dictation, scattered thoughts, half-formed ideas]
Or simply start with your brain dump and mention you want to turn it into specs:
I want to build something. Here's what I'm thinking...
[your raw, unstructured thoughts]
...can you help me turn this into a spec?
The workflow:
npx claudepluginhub nicknisi/ideation --plugin ideationMeta-cognitive tools for Claude Code self-improvement. Learn from feedback, optimize configuration, and evolve your AI development workflow.
Agent dashboard TUI — tracks AI agent state via hooks for the fleet CLI
Skills for summarizing and recalling AI coding sessions across Claude Code, Codex, and Pi.
Comprehensive feature development workflow with specialized agents for codebase exploration, architecture design, and quality review
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification