flowai-plugins

Create, maintain, and run evidence-based benchmarks for AI agents. Use when setting up testing infrastructure, writing new test scenarios, or evaluating agent performance.

Use when the user asks for a project health audit, maintenance sweep, or multi-category lead-engineer scan followed by interactive issue-by-issue resolution with user approval. Do NOT trigger on routine lint/test runs, single-file cleanups, or standard "check project" requests.

Guide for creating effective Agent Skills (SKILL.md packages). Use when users want to create a new skill, write a skill, author a SKILL.md, or ask about skill structure, best practices, or skill file format. Works across IDEs (Cursor, Claude Code, OpenCode).

Estimate total token usage and cost across conversation history, system prompts, and active rules. Use when the user asks how much context or how many tokens are in use, to audit context size, or to estimate session cost.

Design and build plugins for AI IDEs (skills, MCP tools, hooks, packaging, manifests, marketplaces, per-IDE validation). Use when the user wants to create, design, or package an AI-IDE plugin.

Build AI-IDE plugin hook elements - shared policies plus Claude Code/Codex/OpenCode/Cursor adapters for lifecycle events, blocking, audit, and context injection. Use when adding or configuring plugin hooks.

Design AI-IDE plugin marketplaces - requirements, host-specific payloads, local dogfood, release sync, and validation. Use when the user wants to create or publish a plugin marketplace.

Build AI-IDE plugin MCP elements - stdio JSON-RPC servers, tool schemas, host wiring for Claude Code/Codex, event-name mapping, and validation. Use when adding an MCP server to a plugin.

Guide to writing stable prompts for instant/fast models (Gemini Flash, GPT-4o Mini, Haiku). Use when the user is writing or tuning prompts for a fast or cheap model.

Guide to writing prompts for reasoning models (Gemini Pro, GPT-4o, Claude Sonnet), focused on structure and context. Use when the user is writing or tuning prompts for a reasoning or smart model.

Fix failing or broken tests by finding the root cause and correcting the source code (not the test). Use when tests fail, a suite is red, or the user asks to fix or repair tests or a CI test failure.

Write a Development Enhancement Proposal (DEP) for a technical improvement. Use when the user wants to propose, document, or formalize a technical change for review.

Author task files in the GODS framework (Goal, Overview, Definition of Done, Solution). Use when the user asks to write, structure, or break down a task or plan in GODS format.

Rewrite text in a dense, factual informational style with no fluff or marketing. Use when the user asks to write or rewrite docs or notes concisely or to apply a neutral informational tone.

Produce a comprehensive Product Requirements Document (PRD). Use when the user asks to write a PRD or formalize a feature's scope, goals, and success metrics.

Commit current changes as atomic, conventional commits with targeted documentation sync — groups the diff into logical commits and updates the docs each change affects.

User-invoked safe git push. Confirms before setting first-time upstream and before pushing a diverged main/master, and refuses force pushes without explicit authorization. Self-contained — execute the inlined steps directly.

Generate a .devcontainer (devcontainer.json plus optional 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 dev environment for Claude Code, OpenCode, or flowai.

Terminal full-cycle workflow: plan → implement → review → commit → push. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.

Continuation of the SDLC from a ready task file: implement → review → commit → push. No planning — the task file must already exist with `## Solution` filled. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.

Run prompts in Claude Code, OpenCode, Cursor, or Codex CLIs from the current session — pick one IDE, fan out across several, or compare models. You are a courier that relays the other runtime's stdout verbatim, do not synthesise your own answer. Use on "run in <ide>", "compare <ide> vs <ide>", "try on <model>", "which IDE handles X better", "run across models".

Delegate a task to another AI IDE's CLI (codex / claude / opencode / cursor-agent) through an isolated-context subagent. Triggers on "delegate to <ide>", "have <ide> do <task>", "execute <task> in <ide>", "offload to <ide>". For one-shot relay or fan-out comparison use `ai-ide-runner` instead.

Recommend which LLM model to use for a task. Use when asked "which model / best LLM for X", "pick a model for this task", or for a model shortlist ranked by live leaderboard evidence (coding, reasoning, agentic, tool-use, price, speed). Live-fetches public leaderboards and ranks models with per-axis rationale and citations.

Adapt project-local flowai primitives (skills, agents, AGENTS.md artifacts, hooks) to project specifics. Standalone adaptation — independent of update.

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 resolved through the `tasks` role in AGENTS.md. Do NOT trigger on planning, reviewing committed changes, or fixing pre-existing failing tests outside a plan.

Initialize project with AGENTS.md and rules, handling both Greenfield (new) and Brownfield (existing) projects.

Streamlined two-phase workflow: review, then commit. Verdict gate between phases. Self-contained — execute the inlined steps directly, do NOT invoke other skills via the Skill tool.

Use when the user asks to review CURRENT uncommitted changes (staged, unstaged, or branch diff) as QA + lead engineer before committing — verdict on task completion, code quality, architecture, cleanup, plus ephemeral regression probes (pass-on-parent / fail-on-diff). Requires an existing diff. Do NOT trigger without a diff or on post-merge review of historical commits.

Reconcile project-owned AGENTS.md, CLAUDE.md, and scaffolded artifacts with the current flowai framework templates.

Use ONLY when the user explicitly asks to plan a task, create a role-resolved task file, produce a GODS-format breakdown, or prepare a critiqued implementation strategy before coding. Writes tasks under the `tasks` role with extended frontmatter. Do NOT trigger on brief design discussion, ad-hoc code suggestions, or casual "how would you approach X?" questions.

Use when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, opens relevant pages, follows one SALP-REF hop, synthesises a cited answer, files it back. Do NOT trigger on source-code or live-session questions.

Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead SALP REFs, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.

Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.

Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces an epic under the `tasks` role from AGENTS.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.

Use when the user asks to reflect on the CURRENT session, analyze the agent's own process, audit context usage in this conversation, or extract lessons from how the current task was executed. Do NOT trigger for historical multi-session analysis — use reflect-by-history for that. Do NOT trigger on plain "what did you do?" style recaps.

Manage all Deno capabilities via CLI (run, test, fmt, lint, task, add, etc.). Use this skill when you need to execute Deno commands, manage dependencies, run tests, or handle local development workflows.

Manage Deno Deploy cloud services using both `deno deploy` and `deployctl`. Use this skill for deploying projects, managing cloud environments (Build/Dev/Prod contexts), monitoring logs, and troubleshooting deployment issues (like private npm dependencies).

Guide for creating effective flowai commands. This skill should be used when users want to create a new command (or update an existing command) that extends flowai's capabilities with specialized knowledge, workflows, or tool integrations. Works across IDEs (Cursor, Claude Code, OpenCode).

Creation and configuration of event hooks/plugins to manage agent behavior, command filtering, auditing, and automation. Works across IDEs (Cursor, Claude Code, OpenCode). Use when you need to: (1) Create a new hook (e.g., for formatting or security checks), (2) Configure hooks/plugins, (3) Implement logic for blocking or modifying agent actions via scripts.

Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, OpenCode).