← all publishers

anyoneanderson

@anyoneanderson source repo

Report this profile Claim this profile

• 27 skills
• 0 followers
• 7 hours ago last updated

1. ▌
   Note Draft · anyoneanderson bundle

   Markdownファイルをnote.comに下書き投稿するスキル
   0
   installs
2. ▌
   Note Publish · anyoneanderson bundle

   note.comの下書き記事にハッシュタグを設定し公開するスキル
   0
   installs
3. ▌
   Note Automation · anyoneanderson bundle

   Markdownの下書き投稿からハッシュタグ設定・公開までを一気通貫で実行するオーケストレーションスキル
   0
   installs
4. ▌
   Magi · anyoneanderson bundle

   Put a hard question to three independent LLM CLIs from different vendors and return a tallied verdict (decision mode) or a cross-checked research report (research mode), always with a matrix showing who said what. The three sages are MELCHIOR (Claude), BALTHASAR (Codex) and CASPER (Grok); they are configurable. Use it when one model's blind spot would be expensive: choosing between options, or checking whether a "current" fact is still true. English triggers: "ask the MAGI council", "put this to the MAGI", "three-model council", "get three independent opinions", "cross-check this with three models" 日本語トリガー: 「MAGI に諮って」「3賢者で合議」「3体で合議」「3モデルで多数決」「3つのモデルで裏取りして」
   0
   installs
5. ▌
   Handover · anyoneanderson bundle

   Create, install, inspect, and boot from local session handover files for AI agent continuity. Writes structured handover.md notes, keeps them private by default with .gitignore guards, installs AGENTS.md / CLAUDE.md startup guidance, and configures Claude Code / Codex session-start hooks. English triggers: "handover", "create handover", "boot from handover", "resume from handover", "install handover" 日本語トリガー: 「handover」「引き継ぎを作成」「handoverを見て開始」「引き継ぎから再開」「handoverをインストール」
   0
   installs
6. ▌
   Cmux Fork · anyoneanderson bundle

   Fork the current Claude Code conversation into a new cmux pane or workspace. Default: split right. Supports down and new workspace via natural language. Requires cmux session (CMUX_SOCKET_PATH must be set). English triggers: "fork session", "fork conversation", "split and fork" 日本語トリガー: 「フォークして」「会話をフォーク」「ターミナルをフォークして」「もう一個ターミナル立ち上げて」 Slash command: /cmux-fork
   0
   installs
7. ▌
   Spec Code · anyoneanderson bundle

   Implement a single task from spec documents autonomously. Reads requirement.md, design.md, and tasks.md to understand the full project context, then implements the specified task following coding rules and project conventions. Supports --feedback mode to address review or test findings. English triggers: "Implement task", "Code this task", "Run spec-code" 日本語トリガー: 「タスクを実装」「このタスクをコーディング」「spec-codeを実行」
   0
   installs
8. ▌
   Spec Test · anyoneanderson bundle

   Create and run tests for a spec task implementation. Reads task completion criteria from tasks.md, detects existing test patterns, creates test cases, runs them, and outputs a structured test result file. Works standalone or as part of the spec-implement pipeline. English triggers: "Test this task", "Run spec-test", "Create tests for task" 日本語トリガー: 「このタスクをテスト」「spec-testを実行」「タスクのテストを作成」
   0
   installs
9. ▌
   MCP Convert · anyoneanderson bundle

   MCP config converter for agent CLIs. Converts Claude Code MCP settings into Codex CLI MCP configuration, copying env values directly into Codex config. Use this when the user wants to: - migrate MCP servers from Claude Code to Codex CLI - sync Claude Code MCP settings into Codex - export Claude MCP settings as Codex config - copy MCP definitions while preserving commands and env behavior English triggers: - "convert Claude MCP to Codex" - "sync MCP settings from Claude Code" - "migrate MCP config to Codex CLI" - "copy Claude mcpServers into Codex" 日本語トリガー: - 「Claude CodeのMCPをCodexに変換」 - 「ClaudeのMCP設定をCodex CLIに同期」 - 「MCP設定を移行」 - 「claudeのmcpServersをcodexに持っていく」
   0
   installs
10. ▌
    Spec Review · anyoneanderson bundle

    Structured code review against review_rules.md and coding-rules.md. Performs rule-by-rule, file-by-file matrix review of code changes. Outputs findings to a structured review file for use by spec-code --feedback. Works standalone for manual reviews or as part of spec-implement pipeline. English triggers: "Review code", "Run spec-review", "Check against rules" 日本語トリガー: 「コードレビュー」「spec-reviewを実行」「ルールに照合」
    0
    installs
11. ▌
    Harness Init · anyoneanderson bundle

    Install a Harness Engineering control loop into the current project. Hears environment settings once, then generates Planner/Generator/Evaluator sub-agents, hooks, guard scripts, and resilience files (.harness/, .claude/). Use this when you want to switch a project to autonomous-sprint development driven by the /harness series (autonomous, auto-patrol, or scheduled modes). Not for spec-driven workflows — for that use /spec-workflow-init. English triggers: "Initialize harness", "Set up /harness", "Install harness engineering" 日本語トリガー: 「harness を導入」「ハーネスを初期化」「harness-init を実行」
    0
    installs
12. ▌
    Harness Loop · anyoneanderson bundle

    Run the GAN control loop for one epic: for each sprint, negotiate the contract, iterate Generator ⇄ Evaluator to rubric convergence (or Principal Skinner stop), checkpoint to progress.md + _state.json + git + metrics.jsonl every iteration, and open the PR. Handles interactive / continuous / autonomous-ralph / scheduled execution modes. Prerequisite: /harness-init and /harness-plan must have completed. _state.json.phase must be "ready-for-loop" (fresh) or one of the in-sprint phases (resume). English triggers: "Run harness-loop", "Start the sprint loop", "Execute sprints" 日本語トリガー: 「harness-loop を実行」「sprint ループを開始」「自律実装を開始」
    0
    installs
13. ▌
    Harness Plan · anyoneanderson bundle

    Plan an epic for /harness: draft product-spec.md interactively, derive roadmap.md with sprint decomposition and bundling, then emit one tracker Issue per sprint. The last human-in-the-loop step before autonomous sprints begin in /harness-loop. Prerequisite: /harness-init must have already initialised .harness/ and .claude/agents/ in this project. This skill is not for spec-driven (/spec-generator) workflows. English triggers: "Plan the epic", "Run harness-plan", "Create product-spec" 日本語トリガー: 「epic を計画」「harness-plan を実行」「product-spec を作成」
    0
    installs
14. ▌
    Ja Humanizer · anyoneanderson bundle

    Write, rewrite and check Japanese prose so it reads like the writer, not a language model. Removes Japanese-specific AI tells (metaphorical verbs, stiff predicates, staging, cushion phrases, thin claims) in tiers, follows a built-in Japanese writing norm when drafting, matches the writer's voice samples, and never invents facts: a missing fact comes back as a question. Use for explanatory articles, PR and Issue bodies, design documents, blogs, business mail and chat. Structure borrowed from blader/humanizer; patterns rebuilt for Japanese. English triggers: "humanize this Japanese", "remove AI tells from this Japanese text", "write this PR body in Japanese", "check this Japanese for AI smell", "rewrite this mail in Japanese" 日本語トリガー: 「AI 臭を消して」「人間らしい日本語に直して」「日本語で PR 本文を書いて」「この文章を自然な日本語にして」「AI っぽさをチェックして」「メールを直して」
    0
    installs
15. ▌
    Spec Inspect · anyoneanderson bundle

    Specification quality checker for spec-generator documents. Validates requirement.md, design.md, tasks.md for consistency, completeness, and quality. Detects requirement ID mismatches, missing sections, contradictions, and ambiguous expressions. English triggers: "inspect specs", "check specification quality", "validate requirements" 日本語トリガー: 「仕様書を検査」「品質チェック」「仕様を検証」「spec-inspect実行」
    0
    installs
16. ▌
    Spec Writing · anyoneanderson bundle

    Write and revise requirements, designs, task plans, and test plans with concrete process descriptions, traceable reasoning, and audience-appropriate detail. Provides a stable abstract-verb vocabulary for specification checks. English triggers: "write a clear specification", "revise this design", "apply spec-writing" 日本語トリガー: 「読みやすい仕様書を書く」「設計書を推敲」「spec-writingを適用」
    0
    installs
17. ▌
    Cmux Delegate · anyoneanderson bundle

    Delegate a task to another AI agent in a separate cmux pane or workspace. Supports Claude Code, Codex, Gemini CLI, and custom agents. Handles agent launch, task submission, completion detection, and result collection. Requires cmux session (CMUX_SOCKET_PATH must be set). English triggers: "delegate task", "run this in another pane", "have another agent do this" 日本語トリガー: 「別ペインでやらせて」「委任して」「別のエージェントにやらせて」「このタスクを投げて」 Slash command: /cmux-delegate
    0
    installs
18. ▌
    Skill Suggest · anyoneanderson bundle

    Auto-detect project tech stack and suggest optimal skills from skills.sh registry. Analyzes manifest files (package.json, Cargo.toml, go.mod, etc.), searches the skills.sh API, scores results by install count, and installs selected skills with agent-targeted installation to prevent unwanted directory creation. English triggers: "Suggest skills", "Find best practice skills", "What skills should I install" 日本語トリガー: 「スキルを提案」「ベストプラクティススキルを検索」「おすすめスキルを教えて」
    0
    installs
19. ▌
    Spec Evaluate · anyoneanderson bundle

    Run a black-box acceptance test plan (test.md) against a finished implementation and produce a structured pass/fail result. Executes each test case by its verification method (playwright / command / file-check), launches the app from a project recipe, saves screenshots and logs as evidence, and writes a spec-review-compatible findings file that spec-code --feedback can consume. Runs standalone or inside the spec-orchestrate pipeline, on a host-native subagent or a delegated peer LLM. English triggers: "Acceptance test this feature", "Run spec-evaluate", "Verify against test.md", "Run the acceptance test plan" 日本語トリガー: 「この機能を受け入れ試験して」「spec-evaluateを実行」 「test.md を実行」「受け入れテストを回して」
    0
    installs
20. ▌
    Spec To Issue · anyoneanderson bundle

    Create GitHub Issue from spec documents — Auto-generate structured Feature Issues from specifications. Analyzes spec documents (requirement.md, design.md, tasks.md) in .specs/{feature}/ and generates a structured Feature Issue via gh issue create. Best used with specs created by spec-generator. English triggers: - "Create issue from spec", "Register spec as issue" - "Convert spec to GitHub issue", "Publish spec to issue" - After spec-generator: "Turn this into an issue" 日本語トリガー: - 「仕様書をIssueにして」「Issueに登録して」「specからIssue作成」 - 「仕様書からIssue生成」「specをIssueに変換」 - spec-generator完了後に「これをIssueにして」「Issueにして」
    0
    installs
21. ▌
    Agent Delegate · anyoneanderson bundle

    Delegate a task to, or get an adversarial review from, the other AI agent (Codex from Claude Code, or Claude Code from Codex) via a headless CLI call — no cmux required. Returns a normalized report.json the caller can parse. Use for task hand-off, code/spec review, and second opinions in environments without cmux. English triggers: "delegate to Codex", "have Codex review this", "second opinion without cmux", "run this on the other agent" 日本語トリガー: 「Codex に投げて」「Codex にレビューさせて」「セカンドオピニオン」「もう一方のエージェントで実行して」 Slash command: /agent-delegate
    0
    installs
22. ▌
    Spec Generator · anyoneanderson bundle

    Specification Generator — Generate project requirements, design documents, and task lists. A skill for generating structured project specifications through interactive dialogue or quick generation. English triggers: - "Create requirements", "Generate requirements doc", "Summarize as requirements" - "Create design document", "Design the architecture", "Generate technical spec" - "Create task list", "Break down into tasks", "Generate tasks.md" - "Create full spec", "Generate all specs", "Create the complete specification" - After discussion: "Turn this into requirements", "Document this as spec" 日本語トリガー: - 「要件定義を作って」「要件をまとめて」「仕様書を作成して」 - 「設計書を作って」「技術設計をして」「アーキテクチャを設計して」 - 「タスクリストを作って」「実装タスクに分解して」「tasks.mdを生成して」 - 「仕様を全部まとめて」「フル仕様を作成」「3点セットを作って」 - 会話で仕様が固まった後に「これを要件定義書にして」
    0
    installs
23. ▌
    Spec Implement · anyoneanderson bundle

    Specification-driven implementation orchestrator — Coordinate spec-code, spec-review, and spec-test to implement from specs to PR. Reads issue-to-pr-workflow.md as playbook, delegates implementation to spec-code, review to spec-review, testing to spec-test. Manages fix loops, task progression, and PR creation. Does NOT write implementation code or perform reviews itself. English triggers: "Implement from spec", "Start implementation", "Execute spec tasks" 日本語トリガー: 「仕様書から実装」「実装を開始」「specタスクを実行」
    0
    installs
24. ▌
    Spec Rules Init · anyoneanderson bundle

    Coding rules generator — Extract and generate coding-rules.md from project conventions. Scans CLAUDE.md, AGENTS.md, config files, existing source code, and installed skills to produce a unified coding-rules.md that spec-implement uses as a quality gate. English triggers: "Generate coding rules", "Create coding-rules.md", "Extract project rules" 日本語トリガー: 「コーディングルールを生成」「coding-rules.mdを作成」「プロジェクトルールを抽出」
    0
    installs
25. ▌
    Spec Orchestrate · anyoneanderson bundle

    End-to-end pipeline orchestrator — drive a GitHub Issue or a human request from specification through adversarial review, implementation, acceptance testing, and pull request, as a thin state machine that delegates every unit of work to a worker skill. Runs in manual mode (human sets the request and approves the spec once) or auto mode (an Issue number goes in, a PR comes out with no human gate). Never writes code, specs, tests, or reviews itself. English triggers: "Run the spec pipeline", "Orchestrate this issue to PR", "spec-orchestrate", "Take this feature from spec to PR" 日本語トリガー: 「パイプラインを回して」「Issue から PR まで自動で」 「spec-orchestrate を実行」「仕様から PR まで通して」
    0
    installs
26. ▌
    Spec Workflow Init · anyoneanderson bundle

    Development workflow generator — Generate issue-to-pr-workflow.md for your project. Creates a project-specific development workflow through interactive dialogue, covering branch strategy, quality gates, development style, and optional sub-agent definitions. English triggers: "Generate workflow", "Create development workflow", "Setup issue-to-PR flow" 日本語トリガー: 「ワークフローを生成」「開発フローを作成」「Issue-to-PRフローを設定」
    0
    installs
27. ▌
    Cmux Second Opinion · anyoneanderson bundle

    Get a second opinion on code or specifications from a different AI agent via cmux. Default reviewer: Codex (or Claude Code if parent is Codex). Supports custom agents. Uses review_rules.md as review criteria when available. Requires cmux session (CMUX_SOCKET_PATH must be set). English triggers: "second opinion", "get another review", "have Codex review this" 日本語トリガー: 「セカンドオピニオン」「別のAIにレビューしてもらって」「Codexにレビューさせて」 Slash command: /cmux-second-opinion
    0
    installs