Skip to content

All Skills

Every flow-next skill, grouped by where it sits in the pipeline. The pipeline is a menu, not a rail — use the smallest sufficient workflow: each skill runs standalone, and each stage can be skipped, reordered, or prompted into.

The Invocation column shows the canonical form. You do not have to type it — every skill is triggered by describing what you want, and every flag has a plain-language equivalent (the cookbook shows the pairs). Say “make a spec from what we discussed” and capture runs; the command is just the precise version.

SkillInvocationWhat it does
Strategy/flow-next:strategyCreate and maintain STRATEGY.md — the product anchor downstream skills read for grounding.
Prospect/flow-next:prospectGenerate ranked candidate ideas grounded in the repo, upstream of planning.
Capture/flow-next:captureSynthesize a conversation into a spec with source-tagged R-IDs and mandatory read-back.
Interview/flow-next:interviewRefine a spec via symmetric Q&A — business and technical passes, append-only R-IDs.
SkillInvocationWhat it does
Plan/flow-next:planResearch scouts in parallel; a structured plan with R-ID coverage; tasks sized for one work-loop iteration.
Plan Review/flow-next:plan-reviewCarmack-level adversarial review of a spec before any work starts.
Deps/flow-next:depsShow the spec dependency graph, execution order, and parallelizable phases.
Sync/flow-next:syncManually trigger plan-sync to update downstream task specs after implementation drift.
SkillInvocationWhat it does
Work/flow-next:workExecute a spec — worker subagent per task, re-anchor every iteration, plan-sync after each.
Impl Review/flow-next:impl-reviewCarmack-level cross-model review of the implementation diff, with a fix loop until SHIP.
QA/flow-next:qaLive-app QA pass that drives the running app and derives its scenarios from the spec.
SkillInvocationWhat it does
Make PR/flow-next:make-prRender a cognitive-aid PR body — R-ID coverage table, critical changes, decision context.
Resolve PR/flow-next:resolve-prResolve PR review feedback — fetch threads, triage, dispatch resolver agents, reply + resolve.
Spec Completion Review/flow-next:spec-completion-reviewVerify the combined implementation of all tasks satisfies the spec requirements.
SkillInvocationWhat it does
Pilot/flow-next:pilotThe build loop — one ready spec, one pipeline stage per tick, driven by your host’s /loop or /goal.
Land/flow-next:landThe ship loop — babysits the build loop’s draft PRs through CI, review convergence, merge, and release.
Ralph Init/flow-next:ralph-initScaffold the hardened Ralph harness — fresh session per iteration, hook-enforced guardrails.
SkillInvocationWhat it does
Tracker Sync/flow-next:tracker-syncProject a spec to Linear, GitHub, GitLab, or Jira and reconcile two-way — the spec stays the source of truth.
SkillInvocationWhat it does
Setup/flow-next:setupOptional local install of flowctl plus CLAUDE.md / AGENTS.md instructions.
Prime/flow-next:primeOpinionated agent-readiness assessment — verdict first, ranked next-actions.
Audit/flow-next:auditReview .flow/memory/ against the current codebase — Keep / Update / Consolidate / Replace / Delete per entry.
Map/flow-next:mapSemantic feature index of the repo (wraps clawpatch) — opt-in convenience consumed by scouts.
Memory Migrate/flow-next:memory-migrateLift legacy flat memory files into the categorized YAML schema.
SkillInvocationWhat it does
Worktree Kitdispatched on demandManage git worktrees for parallel feature work, isolated review, and clean workspaces.
Export Contextdispatched on demandExport a review prompt for external LLMs (ChatGPT Pro, Claude web, Gemini).
RP Explorerdispatched on demandToken-efficient codebase exploration using the RepoPrompt CLI.
Tasks & Inventoryconversational”Show me my tasks” — conversational access to specs and tasks in .flow/.
Drivedispatched by QASurface-aware UI automation — picks the best available driver per surface, degrading gracefully.

Skills are the judgment layer; the mechanical substrate is the flowctl CLI, which every skill calls for state, receipts, and validation.