Repeatable agentic engineering. The workflow layer that turns AI coding agents into a disciplined factory: durable specs, fresh-context workers, adversarial cross-model reviews, receipts. Everything in your repo, zero dependencies. Claude Code · Codex · Cursor · Droid.
Skill Claude CodeCodex
Audit .flow/memory/ entries against the current codebase and decide Keep / Update / Consolidate / Replace / Delete per entry. Triggers on /flow-next:audit, "audit memory", "review memory", "refresh learnings", "sweep stale memory", "consolidate overlapping memory entries". Optional mode:autofix token in arguments runs…
Skill Claude CodeCodex
You are running inside a disposable eval arena.
Skill Claude CodeCodex
Audit .flow/memory/ entries against current code and keep, update, consolidate, replace, delete, or harden each. Use when asked to audit memory or graduate a recurring lesson into a gate.
Skill Claude CodeCodex
Synthesize the current conversation into a flow-next spec with read-back gating. Use when asked to capture this as a spec.
Skill Claude CodeCodex
Decision-map discovery for one oversized unclear idea before capture. Resolve one decision per invocation, brief for capture. Use when asked to chart an idea or work a chart decision.
Skill Claude CodeCodex
Show spec dependency graph and execution order. Use when asking 'what's blocking what', 'execution order', 'dependency graph', 'what order should specs run', 'critical path', 'which specs can run in parallel'.
Skill Claude CodeCodex
Drive any UI surface like a real user - a web app, a Chromium-backed desktop app (Electron / WebView2, reached over CDP), or a genuinely native app (macOS AppKit/SwiftUI, or a non-CDP webview) reached via the Cua Driver / Computer Use. Detects the surface, picks the best available driver, degrades gracefully. Use to…
Skill Claude CodeCodex
Export RepoPrompt context to a markdown file for review with an external LLM (ChatGPT, Claude web, etc.). Use when you want Carmack-level review but prefer an external model. Triggers on "export context", "export for external review", "export plan for ChatGPT", "export impl review context", "review with an external…
Skill Claude CodeCodex
Seed or maintain the committed user-POV drive map at .flow/features/ so QA and drive reuse how a user reaches each feature.
Skill Claude CodeCodex
Recommend the smallest sufficient flow-next workflow from the starting state. Stateless router. Use when unsure which command or stage applies next.
Skill Claude CodeCodex
Carmack-level implementation review of changes via the configured backend. Use when asked to review code or a diff in a flow-next repo.
Skill Claude CodeCodex
In-depth Q&A to refine a spec, task, or spec file before building. Use when asked to flesh out, refine, or interrogate requirements.
Skill Claude CodeCodex
Autonomous PR babysitter tick. Fixes CI, resolves feedback, merges when converged, closes the spec, releases. Emits LANDVERDICT. Use when asked to land PRs.
Skill Claude CodeCodex
Open a PR with a cognitive-aid body rendered from flow-next spec state via gh. Use whenever asked to make or open a PR in a flow-next repo.
Skill Claude CodeCodex
Build a semantic feature index of the repo via clawpatch map (opt-in). Use when asked to map the repo.
Skill Claude CodeCodex
Migrate legacy flat .flow/memory files to the categorized YAML schema. One-time ceremony. Use when asked to migrate flow memory.
Skill Claude CodeCodex
Single-tick autonomous build-loop conductor. Advances one ready spec one stage per tick, emits PILOTVERDICT. Use when asked to pilot a spec or backlog.
Skill Claude CodeCodex
Carmack-level review of a flow-next spec or plan via the configured backend. Use when asked to review a plan or spec.
Skill Claude CodeCodex
Plan a feature into a flow-next spec with tasks in .flow/. Use when asked to plan, spec out, or break down work (fn-N ids).
Skill Claude CodeCodex
Assess codebase agent and production readiness. Classifies the project, verifies commands run, leads with a verdict and ranked next actions.
Skill Claude CodeCodex
Use while drafting a substantial reply, report, or summary for the user - read the prose contract before writing and draft under its rules. Not for short turns or file/PR output.
Skill Claude CodeCodex
Generate ranked candidate ideas grounded in the repo. Use when asked what to build next.
Skill Claude CodeCodex
Live-app QA pass derived from the spec. Drives the running app, files P0/P1/P2 findings with evidence, emits a YES or NO qaverdict receipt.
Skill Claude CodeCodex
Scaffold the repo-local Ralph autonomous harness and project hooks. Use when asked to set up Ralph.