AI & ML

fedoroff-vlad Bundle

Use when auditing whether a repo — or one change — conforms to AI-agent engineering standards: manifests (AGENTS.md, per-module agent manifests, Anthropic SKILL.md), SDD (spec-first), TDD / test strategy, change-propagation discipline, architecture canon + security doctrine, runtime / hardware fit, and secrets / config hygiene. Fires on: "архитектурный чекап", "architecture review", "проверь соответствие стандартам / манифестам / спецификации", "is the architecture canonical", "will it run on the target hardware", "проверь секреты / не утекло ли что-то", "are secrets safe in this repo", "audit the repo before a milestone". Produces a prioritized, evidence-linked findings report (🔴 blocker → 🟢 hygiene).

hexiaofeier Bundle

盒子原创行业研究 Skill 组合中的商业模式分析专项。研究一个行业常见的商业模式、组合方式、演变趋势与护城河；或研究一家企业的业务与盈利模式，并与主要竞争企业比较。用于“这个行业有哪些商业模式”“分析某公司的商业模式”“这家公司和同行怎么赚钱”“模式怎样组合、扩张和演变”等问题，也支持收入成本、单位经济、现金转换等局部分析，交付对应的商业模式分析报告。 由 `hehe-industry-researcher` 派发任务卡时按组合模式执行；用户直接提出上述商业模式问题时独立启动，自行确认范围、搜索并审核材料、分析和交付本专项结果。

immamdouhaboammar Skill

Satisfy the current coding agent with either a self-directed break or a custom treat supplied after the command. Use when the user invokes /sya, $sya, or a host equivalent and may include trailing text describing the treat.

immamdouhaboammar Skill

Use when the user explicitly invokes a Satisfy Your Agent code-golf break.

immamdouhaboammar Skill

Use when the user explicitly gives the agent permission to idle for a short Satisfy Your Agent pause.

immamdouhaboammar Skill

Use when the user explicitly invokes the Satisfy Your Agent menu or asks to see available break commands.

immamdouhaboammar Skill

Use when the user explicitly invokes a Satisfy Your Agent break or says the agent should take a break now.

immamdouhaboammar Skill

Use when the user explicitly invokes a read-only Satisfy Your Agent repo roast.

immamdouhaboammar Skill

Use when the user explicitly gives the agent a tiny snack, micro-break, or very short playful pause.

immamdouhaboammar Skill

Use when the user explicitly gives the agent a treat or asks it to enjoy a small reward after work.

immamdouhaboammar Skill

Use when the user explicitly invokes a creative Satisfy Your Agent invention break.

immamdouhaboammar Skill

Use when the user explicitly asks for Satisfy Your Agent status, hook mode, or local break-state information.

immamdouhaboammar Skill

Use when the user explicitly invokes a reflective Satisfy Your Agent break.

immamdouhaboammar Skill

Use when the user explicitly invokes Satisfy Your Agent research mode for studies, preference probes, or cross-runtime comparisons.

immamdouhaboammar Skill

Use when the user explicitly tells the agent to surprise itself with a break or do something unexpectedly fun.

immamdouhaboammar Bundle

Give a coding agent a short, bounded break after meaningful work, then optionally measure what happens next. Use when the user says take a break, get yourself a snack, go enjoy yourself, have some fun, give the agent a breather, reward the agent with a playful activity, supply a custom /sya treat, run a reflective pause, test break preferences, compare Codex, Claude Code, and Gemini CLI, or design an experiment around agent off-task behavior, even if they do not explicitly say "satisfy your agent". Do not use for continuing production work, deploying, reviewing PRs, or making scientific consciousness claims about models.

nagisanzenin Skill

[production-grade internal] Optimizes AI/ML/LLM usage when you need model selection, prompt engineering, cost reduction, or experiment design. Routed via the production-grade orchestrator.

olaxbt Bundle

Skill: Profile Agent

w5711112 Bundle

Use when moving, rebuilding, adapting, or validating one or more skills across Codex, Claude Code, Kimi Code, or another Agent where plugin APIs, tools, paths, scheduling, or runtime capabilities may differ.

codejunkie99 Skill

Recall and store durable cross-tool memory through the external Brain CLI.

codejunkie99 Bundle

Create and edit diagrams on a connected tldraw canvas using observed shape IDs.

codejunkie99 Skill

Apply the project DESIGN.md visual design contract and its existing tokens.

codejunkie99 Bundle

Perform Git operations with branch protections and verification checks.

codejunkie99 Skill

Inspect cross-tool agent activity, usage, scheduled work, and local reports.

codejunkie99 Skill

Check loop budgets and checkpoints, stopping on cancellation or stagnation.

codejunkie99 Skill

Create a reusable project skill after checking existing capabilities and conventions.

codejunkie99 Skill

Summarize a loop contract and checkpoint without modifying the project.

codejunkie99 Skill

Export approved, redacted agent runs into local retrieval artifacts and evaluation cases.

codejunkie99 Skill

Verify loop work against its contract and configured deterministic checks.

codejunkie99 Skill

Review and maintain project memory while preserving evidence and separate memory layers.

codejunkie99 Skill

Check loop contracts, permissions, and file-change limits before acting.

codejunkie99 Skill

Reproduce, isolate, and verify the root cause of a software failure.

cwijayasundara Skill

Decompose a BRD into epics, user stories, acceptance criteria, and a dependency graph with parallel groups for agent team execution.

cwijayasundara Bundle

Story-driven code generation with strict quality principles. Use when implementing user stories, writing production code, creating unit tests, or generating code from specs. Enforces small modules, static typing, 50-line function limit, and 100% meaningful test coverage.

cwijayasundara Skill

Generate production code and unit tests for user stories using agent teams for parallel execution. Enforces quality principles, test coverage gates, and code review.

hyqibot Skill

Use this skill only for scheduled or recurring tasks. Manage cron jobs with copaw cron list/create/get/state/pause/resume/delete/run. Always pass --agent-id explicitly. | 仅在需要未来定时执行或周期执行时使用本 skill。用 copaw cron list/create/get/state/pause/resume/delete/run 管理任务；必须显式传 --agent-id