← all publishers

fockus

@fockus source repo

31 published skills

  1. Memory Bank · fockus bundle
    Agent-agnostic long-term project memory through `.memory-bank/` + RULES (TDD/SOLID/Clean Architecture/FSD/Mobile) + dev-toolkit commands. Use when working in a project with a `.memory-bank/` directory or when the user explicitly asks for memory-bank workflow, code rules, or dev-toolkit commands.
    0
    installs
  2. Writing Clearly · fockus bundle
    Use when writing or editing ANY prose for humans, in Russian or English — documentation, README, commit and PR descriptions, reports, business letters, posts, announcements, release notes, error messages, UI text, explanations, summaries, chat answers. Триггеры — «напиши текст/пост/письмо/статью/README/доку», «отредактируй», «упрости», «сократи», «объясни просто», «сделай понятнее», «инфостиль», «по Ильяхову»; and English "write", "rewrite", "simplify", "explain", "edit this text", "make it clearer". Apply even when the user asks for prose without naming a style — clear writing is the default. Based on Maxim Ilyakhov's «Пиши, сокращай» and «Ясно, понятно» — clarity first, then brevity. NOT for source code, identifiers, commit subjects under 50 chars, or literary fiction.
    0
    installs
  3. Breezing · fockus
    チーム実行モード — harness-work のチーム協調エイリアス。breezing, チーム実行, 全部やって でトリガー。
    0
    installs
  4. Sdd Plan · fockus bundle
    Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
    0
    installs
  5. Kaizen Why · fockus
    Iterative Five Whys root cause analysis drilling from symptoms to fundamentals
    0
    installs
  6. Sadd Judge · fockus
    Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
    0
    installs
  7. Harness Plan · fockus bundle
    Harness v3 統合プランニングスキル。タスク計画・Plans.md管理・進捗同期を担当。以下のフレーズで起動: 計画を作る、タスクを追加、Plans.md更新、完了マーク、進捗確認、harness-plan、harness-sync。実装・レビュー・リリースには使わない。
    0
    installs
  8. Harness Sync · fockus
    Plans.md と実装の進捗同期。差分検出・マーカー更新・レトロスペクティブを実行。以下で起動: harness-sync、sync-status、進捗確認、今どこ、どこまで終わった。--snapshot で進捗スナップショット保存にも対応。プランニング・実装・レビュー・リリースには使わない。
    0
    installs
  9. Harness Work · fockus
    Harness v3 統合実行スキル。Plans.md タスクを1件から全並列チーム実行まで担当。以下で起動: 実装して、実行して、harness-work、全部やって、breezing、チーム実行、parallel。プランニング・レビュー・リリース・セットアップには使わない。
    0
    installs
  10. Sdd Add Task · fockus
    creates draft task file in .memory-bank/specs/tasks/draft/ with original user intent
    0
    installs
  11. Harness Setup · fockus
    Harness v3 統合セットアップスキル。プロジェクト初期化・ツール設定・2エージェント構成・メモリ設定・公開 skill mirror 同期を担当。以下で起動: セットアップ、初期化、新規プロジェクト、CIセットアップ、codex CLIセットアップ、harness-mem、エージェント設定、symlink、mirror、harness-setup。実装・レビュー・リリース・プランニングには使わない。
    0
    installs
  12. Sdd Implement · fockus
    Implement a task with automated LLM-as-Judge verification for critical steps
    0
    installs
  13. Harness Review · fockus
    Harness v3 統合レビュースキル。コード・プラン・スコープを多角的にレビュー。以下で起動: レビュー、コードレビュー、プランレビュー、スコープ分析、セキュリティ、品質チェック、harness-review。実装・新機能・バグ修正・セットアップ・リリースには使わない。
    0
    installs
  14. Kaizen Analyse · fockus
    Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
    0
    installs
  15. Sdd Brainstorm · fockus
    Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes
    0
    installs
  16. Harness Release · fockus
    Harness v3 統合リリーススキル。CHANGELOG・バージョンバンプ・タグ・GitHub Release を自動化。以下で起動: リリース、バージョンバンプ、タグ作成、公開、/harness-release。実装・コードレビュー・プランニング・セットアップには使わない。
    0
    installs
  17. Sadd Do In Steps · fockus
    Execute complex tasks through sequential sub-agent orchestration with intelligent model selection, meta-judge → LLM-as-a-judge verification
    0
    installs
  18. Sdd Create Ideas · fockus
    Generate ideas in one shot using creative sampling
    0
    installs
  19. Reflexion Reflect · fockus
    Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
    0
    installs
  20. Sadd Do And Judge · fockus
    Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
    0
    installs
  21. Reflexion Critique · fockus
    Comprehensive multi-perspective review using specialized judges with debate and consensus building
    0
    installs
  22. Reflexion Memorize · fockus
    Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
    0
    installs
  23. Sadd Do In Parallel · fockus bundle
    Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection, quality-focused prompting, and meta-judge → LLM-as-a-judge verification
    0
    installs
  24. Sadd Do Competitively · fockus
    Execute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
    0
    installs
  25. Sadd Tree Of Thoughts · fockus
    Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
    0
    installs
  26. Kaizen Analyse Problem · fockus
    Comprehensive A3 one-page problem analysis with root cause and action plan
    0
    installs
  27. Sadd Judge With Debate · fockus
    Evaluate solutions through multi-round debate between independent judges until consensus
    0
    installs
  28. Kaizen Cause And Effect · fockus
    Systematic Fishbone analysis exploring problem causes across six categories
    0
    installs
  29. Kaizen Plan Do Check Act · fockus
    Iterative PDCA cycle for systematic experimentation and continuous improvement
    0
    installs
  30. Sadd Multi Agent Patterns · fockus
    Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
    0
    installs
  31. Sadd Subagent Driven Development · fockus
    Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates
    0
    installs