fockus
- 31 skills
- 0 followers
- 1 day ago last updated
- ▌ Memory Bank · fockus bundleAgent-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.
- ▌ Writing Clearly · fockus bundleUse 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.
- ▌
- ▌ Sdd Plan · fockus bundleRefine, parallelize, and verify a draft task specification into a fully planned implementation-ready task
- ▌
- ▌ Sadd Judge · fockusLaunch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation
- ▌ Harness Plan · fockus bundleHarness 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。
- ▌ Harness Sync · fockusPlans.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。
- ▌ Harness Work · fockusHarness 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。
- ▌ Sdd Add Task · fockuscreates draft task file in .memory-bank/specs/tasks/draft/ with original user intent
- ▌ Harness Setup · fockusHarness 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。
- ▌
- ▌ Harness Review · fockusHarness 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。
- ▌ Kaizen Analyse · fockusAuto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target
- ▌ Sdd Brainstorm · fockusUse 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
- ▌ Harness Release · fockusHarness 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。
- ▌ Sadd Do In Steps · fockusExecute complex tasks through sequential sub-agent orchestration with intelligent model selection, meta-judge → LLM-as-a-judge verification
- ▌
- ▌ Reflexion Reflect · fockusReflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
- ▌ Sadd Do And Judge · fockusExecute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop
- ▌ Reflexion Critique · fockusComprehensive multi-perspective review using specialized judges with debate and consensus building
- ▌ Reflexion Memorize · fockusCurates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
- ▌ Sadd Do In Parallel · fockus bundleLaunch 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
- ▌ Sadd Do Competitively · fockusExecute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesis
- ▌ Sadd Tree Of Thoughts · fockusExecute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluation
- ▌ Kaizen Analyse Problem · fockusComprehensive A3 one-page problem analysis with root cause and action plan
- ▌ Sadd Judge With Debate · fockusEvaluate solutions through multi-round debate between independent judges until consensus
- ▌ Kaizen Cause And Effect · fockusSystematic Fishbone analysis exploring problem causes across six categories
- ▌ Kaizen Plan Do Check Act · fockusIterative PDCA cycle for systematic experimentation and continuous improvement
- ▌ Sadd Multi Agent Patterns · fockusDesign 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.
- ▌ Sadd Subagent Driven Development · fockusUse 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