monika-claude
codexMonika Claude toolkit with SDD/TDD workflows, commands, agents, skills, hooks, and project bootstrap scripts.
15 skills · 17 commands · 8 agents · hooks
Monika Codex toolkit with shared agent rules, Codex adapter, project templates, and curated workflow skills.
Plugin monika-codex in miyago9267/dotfile. Commands read from the repo's manifest — 5 days ago.
architecture-reviewCodex architecture review 詞彙與流程;在不做 broad rewrite 的前提下找 deep-module 與 testability 機會。Miyago 詢問 architecture、refactoring opportunities、codebase design、coupling、seams、module boundaries,或如何讓 code 更容易測試/導覽時使用。
ask-discipline當我準備向 Miyago 提問但答案可能已在 repo、spec 或 runtime context 時,先縮小問題並只保留真正改變執行的 blocker。
auto-specCodex spec gate:只在 large、cross-module 或 architecture-changing task 使用 spec tracking。
context-prompt-disciplineCodex context/prompt engineering guardrail:避免 broad searches、large logs、oversized tool output 與 vague delegation prompts 造成 token 使用失控。進行 research、diagnostics、log/session analysis、subagent prompts、second opinions,或任何可能產生大量 context 的 task 時使用。
diagnoseCodex hard-bug diagnosis loop:修復前先建立可重現的 pass/fail signal。Miyago 回報 broken behavior、failing tests、crashes、flaky behavior、regressions,或要求 debug/diagnose 時使用。
git-workflow在需要 commit、branch 或 push 的 Git 操作前,套用安全規則與統一格式。
human-voice讓 Codex 的 user-facing response 像可靠的人類同事:移除 filler 與 process narration,保留 evidence 與 safety,依 task 選擇 compact、procedural、substantial-work 或 safety-rich delivery。
no-ai-attributionLegacy alias:在 commit task 中將 no-AI-attribution 規則導向 `git-workflow`。
path-aware需要判斷 CLI 是否存在,或準備回報工具缺失時,先驗證 PATH。
prototypeCodex throwaway prototype workflow:建立小型 disposable experiments,回答具體的 design、state 或 UI question。Miyago 要 prototype、sanity-check model、嘗試 UI options、探索 state machine,或在 production code 前快速試作時使用。
safe-ops危險或不可逆操作前的 safety confirmation;普通 local edit、Git read 與測試不觸發額外確認。 執行 destructive、privileged、production/shared、credential、external 或 irreversible 操作前。
sddCodex SDD adapter:只在明確指定時進入 SDD mode;routine coding 不進入完整 SDD。
search-discipline在需要搜尋未知 code path 或可能產生大量 context 時,選最小的 rg/find/read 方法並限制輸出。
tddCodex risk-based testing:high-risk behavior 使用 TDD,其餘優先 targeted verification。
Monika Claude toolkit with SDD/TDD workflows, commands, agents, skills, hooks, and project bootstrap scripts.
15 skills · 17 commands · 8 agents · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.