flowai

Plugin flowai from marketplace flowai-plugins in korchasa/flowai-plugins. Commands read from the repo's manifest — today.

Skills (24)

• adapt

  Use when the user asks to tailor the installed flowai skills, agents, hooks or AGENTS.md artifacts to this project's specifics. Not for first-time setup, template reconciliation, or edits to the project's own code.

• check-goals

  Use when the user asks whether the goals of the CURRENT session are met — lists everything they asked for, gathers evidence for each item and reports met or not met, changing nothing. Not for auditing how the session went — use reflect.

• commit

  Use when the user asks to commit the current changes — groups the diff into atomic conventional commits and updates the docs each change affects. Not for reviewing a diff, and not when the user asks for a review before the commit.

• configure-deno-commands

  Configure and maintain Deno development commands (check, test, dev, prod). Use when the user wants to set up or update the standard command interface in deno.json and scripts/ directory.

• epic

  Use when the user asks to plan a LARGE feature spanning multiple sessions or phases — produces an epic under the `tasks` role with dependency-ordered phases, atomic tasks and per-phase status. Use plan for single-session tasks, not for roadmaps.

• finish-session

  Use when the user asks to finish or wrap up the session — checks that all they asked for is delivered, then commits, pushes and archives it. Not for a code review. Self-contained — execute the inlined steps directly, do NOT invoke other skills.

• implement

  Use when the user asks to execute an existing task plan's Solution under TDD — RED → GREEN → REFACTOR → CHECK per AGENTS.md. Requires a written plan under the `tasks` role. Do NOT trigger on planning, review, or unrelated failing tests.

• init

  Use when the user asks to set a project up for flowai for the first time — writes AGENTS.md and the documentation skeleton for a new or an existing codebase. Not for reconciling an existing AGENTS.md with newer templates.

• investigate

  Use when the user asks to diagnose a bug, find the root cause of a failing behavior, or run a hypothesis-by-hypothesis investigation with experiments and evidence. Produces a diagnostic report with a recommended fix, but does not apply the fix.

• maintenance

  Use when the user asks for a project health audit, a maintenance sweep, or a multi-category lead-engineer scan followed by interactive issue-by-issue resolution. Not for routine lint/test runs, single-file cleanups, or plain check-project requests.

• plan

  Use ONLY when the user explicitly asks to plan a task, create a task file, produce a task breakdown in the accepted format, or prepare a critiqued strategy before coding. Writes under the `tasks` role. Not for design chat or ad-hoc code suggestions.

• push

  Use when the user asks to push the current branch — confirms a first-time upstream and a diverged main, and refuses force pushes without explicit authorization. Not for committing or reviewing. Self-contained — execute the inlined steps directly.

• reflect-by-history

  Use when the user asks to review PAST sessions, find recurring patterns across sessions, or improve project primitives (rules, skills, hooks, docs) from historical IDE transcripts. Do NOT trigger on current-session self-review — use reflect instead.

• reflect-gate

  Use when the user asks to close a session by auditing it AND writing the fixes into the project's instruction files — audits, applies and commits the edits, then asks whether to push. Not for a reflection that only reports findings.

• reflect

  Use when the user asks to reflect on the CURRENT session or one transcript file they name, analyze the agent's own process, audit context use, or extract lessons from how a task was done. Not for multi-session history — use reflect-by-history.

• review-and-commit

  Use when the user asks to review the uncommitted changes and then commit them — the verdict gates the commit. Not for a review alone or a plain commit. Self-contained — execute the inlined steps directly, do NOT invoke other skills.

• review-commit-push

  Use when the user asks to review finished uncommitted work, commit it and push it in one run. Not for planning or implementing, nor when the user stops before the push. Self-contained — execute the inlined steps directly, do NOT invoke other skills.

• review

  Use when the user asks to review CURRENT uncommitted changes (staged, unstaged, branch diff) before committing, or to synthesize JiT tests against the diff — QA + lead-engineer verdict on quality, architecture, cleanup. Needs a diff, not old commits.

• setup-ai-ide-devcontainer

  Generate a .devcontainer (devcontainer.json plus Dockerfile) for AI-IDE development with AI CLI integration, skill mounting and security hardening. Use when the user wants to set up or containerize a local dev environment. Not for cloud deploys.

• ship-task

  Use when the user asks to implement a ready task file (its Solution filled), then review, commit and push it. No planning; not for work that stops before the commit. Self-contained — execute the inlined steps directly, do NOT invoke other skills.

• ship

  Use when the user asks to take a new task all the way: plan, implement, review, commit and push. Not when a ready task file already exists. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.

• tasks-overview

  Show the current state of the project's tasks, hiding archived ones, by writing a project-local status script for however the project stores its tasks. Use when the user asks which tasks are open or in progress, or how far the work has got.

• update

  Use when the user asks to reconcile the project's AGENTS.md, CLAUDE.md and scaffolded files with the current flowai templates after a framework upgrade. Not for first-time setup, and not for tailoring the installed skills.

• write-gods-tasks

  Supplies the accepted task format GODS (Goal, Overview, Definition of Done, Solution). Use when the user asks what that format is, or to write up decided work in it. NOT for planning before coding — weighing variants belongs to the planning skill.

Subagents (11)

• agent-adapter

  Adapts a single agent to project specifics after upstream update. Merges upstream changes with previous project adaptations. Use when adapt or update detects updated agents that need project-specific adaptation.

• console-expert

  Expert in executing complex console tasks and commands. Use when you need to run shell commands, analyze output, or perform system operations without modifying code.

• diff-specialist

  Git diff analysis specialist. Analyzes changes, groups them into logical hunks, and prepares summaries for atomic commits. Use proactively during commit to minimize context usage by delegating detailed diff analysis.

• maintenance-scan-contracts

  Self-contained read-only maintenance scan worker for bucket W3 — Type & behaviour contracts (Cats 12, 13, 14). Embeds its full check detail — needs nothing beyond the project to scan. Returns findings as leads (no severity, no fixes, no writes). Spawned in parallel by the maintenance skill's Scan Ph

• maintenance-scan-coverage

  Self-contained read-only maintenance scan worker for bucket W5 — Coverage & pairing X↔Y (Cats 6, 8, 15). Embeds its full check detail — needs nothing beyond the project to scan. Returns findings as leads (no severity, no fixes, no writes). Spawned in parallel by the maintenance skill's Scan Phase —

• maintenance-scan-dependencies

  Self-contained read-only maintenance scan worker for bucket W2 — Structure & dependency graph (Cats 10, 11, 16). Embeds its full check detail — needs nothing beyond the project to scan. Returns findings as leads (no severity, no fixes, no writes). Spawned in parallel by the maintenance skill's Scan

• maintenance-scan-docs

  Self-contained read-only maintenance scan worker for bucket W4 — Docs & instruction coherence (Cats 5, 7, 9). Embeds its full check detail — needs nothing beyond the project to scan. Returns findings as leads (no severity, no fixes, no writes). Spawned in parallel by the maintenance skill's Scan Pha

• maintenance-scan-hygiene

  Self-contained read-only maintenance scan worker for bucket W1 — Mechanical hygiene & structure (Cats 1, 2, 3, 4). Embeds its full check detail — needs nothing beyond the project to scan. Returns findings as leads (no severity, no fixes, no writes). Spawned in parallel by the maintenance skill's Sca

• plan-critic

  Fresh-context adversarial reviewer of a plan task file. Recomputes the affected-surface diff from the persisted scout block, attacks missing stated outcomes, un-inspected risk claims, over-engineering, and unrecorded scope cuts. Use during planning after the Solution section is drafted; dispatch wit

• skill-adapter

  Adapts a single skill to project specifics after upstream update. Merges upstream changes with previous project adaptations. Use when update detects updated skills that need project-specific adaptation.

• surface-scout

  Read-only scout that independently enumerates the full affected surface of a requested change — parallel implementations, consumers and producers of the touched data or artifact — from the request text alone. Use during planning to cross-check the planner's own surface enumeration; dispatch with the

Hooks (2)

• Stop

  deno run -A "${CLAUDE_PLUGIN_ROOT}/hooks/chat-links-validate/run.ts"

• Stop

  deno run -A "${CLAUDE_PLUGIN_ROOT}/hooks/doc-anchors-validate/run.ts"

Similar plugins