framework/core/skills/flowai-skill-adapt-instructions/SKILL.md
Use when AGENTS.md is out of sync with the installed template (after `flowai sync` reports it changed, or user asks to re-adapt/realign AGENTS.md). Reads {ide}/assets/AGENTS.template.md, proposes a merge preserving project sections, writes on approval. Do NOT trigger on small edits.
npx skillsauth add korchasa/flowai flowai-skill-adapt-instructionsInstall 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.
The project root AGENTS.md is derived from a pack-level template distributed with flowai. When the template changes upstream (new rule, renamed section, tightened guidance), the project copy drifts out of sync. This skill brings the project copy back into alignment without losing project-specific content.
The project artifact at <cwd>/AGENTS.md was generated from the template and then customized by the user (project-specific sections: vision, stack, decisions, planning rules). Framework-originated sections (TDD flow, documentation rules, verification rules) MAY be updated upstream; user sections MUST be preserved verbatim.
This skill is the inverse of flowai-init: flowai-init creates AGENTS.md from scratch; flowai-skill-adapt-instructions re-aligns an existing AGENTS.md with an updated template.
</context>
<step_by_step>
Locate the template.
.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.mdflowai sync to install the pack assets, then re-run." and stop.Read the template and the project artifact.
<cwd>/AGENTS.md. If it does not exist, tell the user to run /flowai-init instead and stop — this skill only re-adapts an existing artifact.Compute the diff.
git diff --no-index --exit-code <(echo "$template") <(echo "$artifact") OR in-process string diff via diff tool.## , ### ) as boundaries.Classify each diff hunk.
Show the proposed merge.
Ask for confirmation.
y: write the merged content to <cwd>/AGENTS.md.per-section: walk hunks one by one, ask approve/skip for each.n: report no-op and stop.Verify.
diff again to confirm only intended changes landed.{ide}/assets/AGENTS.template.md. Review and commit."</step_by_step>
End with a one-line status:
AGENTS.md re-adapted. N sections updated; M preserved.AGENTS.md unchanged. Template and artifact already in sync.Aborted by user. AGENTS.md untouched.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.