framework/core/commands/flowai-update/SKILL.md
Reconcile project-owned AGENTS.md, CLAUDE.md, and scaffolded artifacts with the current flowai framework templates.
npx skillsauth add korchasa/flowai flowai-updateInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Reconcile project-owned flowai artifacts with the currently installed framework templates. This command does not manage the flowai CLI, does not sync or rewrite installed primitives, and does not adapt skills or agents. CLI lifecycle belongs to the standalone flowai CLI repository. Primitive adaptation belongs to flowai-adapt.
Project-owned artifacts:
AGENTS.mdCLAUDE.md when it is a project compatibility file or symlinkRead-only framework sources:
.{ide}/assets/AGENTS.template.md.{ide}/skills/flowai-update/assets/AGENTS.template.md~/.claude/assets/AGENTS.template.md or ~/.codex/assets/AGENTS.template.mdIf project-local flowai primitives exist under .{ide}/skills/, .{ide}/agents/, hooks, or scripts, this command reports that they can be adapted with flowai-adapt. It must not rewrite them.
</context>
<step_by_step>
Detect scope and arguments
--all -> check instructions and scaffolded artifacts.--instructions -> check only AGENTS.md / CLAUDE.md.--scaffolds -> check only known scaffolded project artifacts..claude/, .cursor/, .opencode/, .codex/.Locate AGENTS template sources (for --instructions / --all)
.claude/skills/flowai-update/assets/AGENTS.template.md.cursor/skills/flowai-update/assets/AGENTS.template.md.opencode/skills/flowai-update/assets/AGENTS.template.md.codex/skills/flowai-update/assets/AGENTS.template.md*/skills/update/assets/AGENTS.template.md when visible in the project..claude/assets/AGENTS.template.md.cursor/assets/AGENTS.template.md.opencode/assets/AGENTS.template.md.codex/assets/AGENTS.template.md~/.claude/assets/AGENTS.template.md~/.cursor/assets/AGENTS.template.md~/.config/opencode/assets/AGENTS.template.md~/.codex/assets/AGENTS.template.mdRead project instructions artifacts
./AGENTS.md.AGENTS.md is missing, stop and tell the user to run flowai-init first. Do not create a new root file here../CLAUDE.md:
AGENTS.md, it is up to date.AGENTS.md.AGENTS.md; propose replacing it with a symlink only after showing the diff/risk.Compare template against project artifact
AGENTS.md.{{PROJECT_NAME}} and {{TOOLING_STACK}}.documents/AGENTS.md, scripts/AGENTS.md) -> propose collapsing them into root AGENTS.md.Proactive Resolution.Check scaffolded artifacts (for --scaffolds / --all)
documents/requirements.mddocuments/design.md.devcontainer/devcontainer.json.devcontainer/Dockerfile.devcontainer/init-firewall.sh.devcontainer/setup-container.shdeno.jsonscripts/check.tsDetect local primitives but do not adapt them
.{ide}/skills/flowai-*.{ide}/skills/* with name: flowai-*.{ide}/agents/flowai-*Propose changes
CHECK step, explain that skipping it leaves formatter, linter, and regression failures undetected after GREEN.Apply approved changes
Verify
git diff -- AGENTS.md CLAUDE.md documents/requirements.md documents/design.md .devcontainer deno.json scripts/check.ts limited to touched files.</step_by_step>
tools
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.
tools
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".
tools
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.
development
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.