Skip to content

Latest commit

 

History

History
39 lines (39 loc) · 2.54 KB

File metadata and controls

39 lines (39 loc) · 2.54 KB
  • Added output expectations to all agents and standardized required output sections across all skills.
  • Added validation script for agent/skill prompt quality:
    • scripts/validate_agents_skills.sh
  • Verified prompt test matrix for all agents/skills (26 checks, all passing).
  • Hardened command prompts with shared execution guardrails:
    • docs/prompt-execution-guardrails.md
  • Added deterministic validation guidance:
    • docs/validation-matrix.md
  • Updated canonical commands and core skills for:
    • explicit fail-fast behavior when required context is missing
    • tighter scope control and deterministic validation requirements
  • Updated active official Flutter AI rule to choose state management by project conventions (Riverpod/Bloc/Cubit/GetX/ValueNotifier based on context).
  • Added reference example repository for project structure and tests:
  • Added pre-release enable guide (docs/pre-release-enable-plugin.md) with repository install and manual workspace settings options.
  • Added semantic prompt quality gates:
    • scripts/validate_prompt_semantics.sh
    • .github/workflows/semantic-quality.yml
    • docs/semantic-quality-gates.md
  • Updated scaffold architecture guidance to prefer existing project state-management convention before selecting a pattern.
  • Reworked official Flutter AI rules integration to use policy routing instead of post-sync text patching:
    • added high-priority policy layer rules/flutter-plugin-policy-priority.mdc
    • kept synced upstream profiles as base source of truth
  • Added deterministic environment setup workflow:
    • command: commands/setup-flutter-environment.md
    • skill: skills/setup-flutter-environment/SKILL.md
  • Simplified command prompts by removing repeated guardrails boilerplate from canonical command files.
  • Strengthened semantic output quality across agents/skills:
    • explicit truthfulness policy (planned/not executed wording when no command evidence exists)
    • required missing-inputs/assumptions notes for partial context
    • required next steps and confidence/residual risk coverage in output contracts
  • Added external backend API integration workflow:
    • command: commands/integrate-mobile-api.md
    • skill: skills/integrate-mobile-api/SKILL.md
  • Removed flutter:* command aliases and kept canonical commands only.
  • Breaking: removed flutter:* command aliases; use canonical command names only.
  • Removed alias maintenance artifacts:
    • deleted docs/command-namespacing.md
    • deleted scripts/generate_namespaced_command_aliases.py