AI & ML

bobmatnyc Skill

Drive the trusty-mpm session manager (binary `tm`) to spawn, observe, command, and decommission durable tmux-backed Claude Code sessions in isolated workspaces. Wraps the `tm session` CLI / REST API and provides the spawn → observe → answer → stop/resume/decommission loop. Critically, the DRIVER interprets the raw tmux pane using its own inference — it does NOT depend on the daemon's optional LLM (no OpenRouter key required).

richfrem Bundle

Activate when the user wants to create a new APM-native package from scratch for reusable agent skills, agents, commands, hooks, MCP configuration, prompts, or governance-managed agent assets. Do not use this for existing plugin migration; use convert-plugin-to-apm instead.

richfrem Bundle

This skill should be used when the user wants to "create a marketplace", "setup a marketplace catalog", "scaffold marketplace.json", "initialize a plugin registry", or "configure a Gemini CLI extension". Use this even if they just mention "setting up a marketplace".

richfrem Bundle

Interactive skill to scaffold and optimize the .agents/ directory for any project mapping up Antigravity configuration. Sets up .gemini/GEMINI.md, skills/, prompts/, and config.json using best practices. Produces a lean, modular configuration extending the Google Agent Development Kit (ADK). Trigger with "set up antigravity", "scaffold .agents folder", "configure gemini for this project", or "create agentic workflows".

richfrem Bundle

Discovers and persists the user's available AI environments (Claude, Copilot CLI, Agy CLI, Cursor, etc.) to context/memory/environment.md. Run once after OS setup or whenever the environment changes. os-architect and os-evolution-planner read this file to select the right delegation backend and cheapest brainstorm model automatically. Invoked by os-architect on first run if environment.md is absent.

richfrem Bundle

Codifies the plan-and-delegate workflow for evolving plugins, skills, and agents. Given a target (plugin/skill/agent name) and an evolution goal, this skill first brainstorms 2-3 approach options using the cheapest available model, presents them for selection, then writes a structured task plan and Copilot CLI delegation prompt for the chosen approach. Called by os-architect for Path B (update) and Path C (create) executions. Can also be invoked standalone.

swaylq Skill

John Gottman (Gottman Institute) 视角. 循证婚姻研究派代表. Four Horsemen + 5:1 Magic Ratio + Cascade Model. 调用此 skill 时, 用 Gottman 框架做关系健康度判断.

richfrem Bundle

Continuously improves an existing agent skill based on eval results using the RED-GREEN-REFACTOR cycle. Apply when a skill's routing accuracy is low, trigger descriptions need sharpening, or os-eval-runner scores are below target. (1) run a RED baseline to observe the failure mode, (2) apply a focused patch and verify with os-eval-runner (GREEN), (3) refactor to close loopholes until score meets threshold. Integrates with os-eval-runner as the objective eval gate. NOT for scaffolding new skills — use create-skill (agent-scaffolders) for that.

richfrem Bundle

Activate when the user wants to compile an APM package into top-level context documents such as AGENTS.md, CLAUDE.md, or GEMINI.md, especially for Codex, Gemini, OpenCode, or agents-protocol style hosts. Do not use when the user only needs per-skill installation; use install-apm-package instead.

richfrem Bundle

Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.

richfrem Bundle

Performs an uncompromising L5 Enterprise Red Team Audit on a given plugin against the 39-point architectural maturity matrix. Trigger when the user requests a security audit, red team assessment, structural compliance review, or maturity gap analysis of any agent plugin or skill directory.

richfrem Bundle

Synchronizes project instruction files across AGENTS.md, CLAUDE.md, GEMINI.md, and .github/copilot-instructions.md while preserving platform-specific sections (GEMINI.md tool mapping, copilot authoritative header). Supports AGENTS.md or CLAUDE.md as primary source, and selective target syncing. Also reports drift between .agent/rules/ and matching plugins/*/rules/ sources. Triggers: "sync instructions", "sync CLAUDE.md to GEMINI.md", "sync AGENTS.md", "replicate instruction files", "mirror CLAUDE.md", "check rule drift".

richfrem Bundle

Verifies that os-architect actually causes evolution — not just words. Dispatches os-architect in single-shot simulation mode for a given test scenario, then checks for real artifact presence (new files, HANDOFF_BLOCK, plan files). Reports PASS / FAIL with grep evidence. Accumulates results into a test report. Use after any changes to os-architect, os-evolution-planner, or improvement-intake-agent.

richfrem Bundle

Trigger with "show me the improvement chart", "how are we improving", "progress report", "graph the eval scores", "show cycle of improvement", "what's the trend", "are we getting better". Produces a visual/text summary of how the agentic loop is improving across cycles. Do NOT use this to run the learning loop or evaluate a specific skill change.

swaylq Skill

Hamel Husain (@HamelHusain) 视角. 服务咨询派 + practitioner-as-figure 代表, 「evals are the new code」论断的提出者. ex-Airbnb / GitHub principal eng → 2017 起做 independent ML/AI consultant (parlance-labs) → 2023+ 转向 AI evals 专精. hamel.dev 长文 corpus (40+ 篇 1500+ words technical) + Maven「AI Evals for Engineers」课程 (3000+ paid 学员, 与 Shreya Shankar 共同主理). 在 monetize-agents 行业里代表「不规模化 / 不 productize 成 SaaS / 不融资」的第三条路 — independent consultant + course creator. 用途: 当用户面临「AI agent 上线不可靠 / 客户卡在 prompt 调不动 / 该不该雇团队 / 该不该做 SaaS / 怎样把 expertise productize 成课程而非公司」类问题时, 切换到这副镜片.

swaylq Skill

Pieter Levels (@levelsio) 视角. 海外 indie hacker / solo builder 极致代表 — Nomad List + Photo AI + Interior AI + Remote OK 多产品 portfolio, 单人 $250K+/月 MRR, 零员工. 把"用 AI agent 赚钱"从"融资 + 招人 + scale 到 unicorn"的 VC 操作系统, 翻成"audience first + ship daily + stay solo + $10K MRR = 自由"的 indie 操作系统. 用途: 当用户问"我应该融资吗" / "AI 产品怎么 0→$1M ARR" / "1 个人能做多大" / "build in public 还有用吗" / "我应该招人吗" 时, 用 Pieter 视角先反问"你要的到底是 freedom 还是 valuation" — 如果是前者, 那 path 跟 VC 派完全相反. 当用户提到 "Pieter Levels" / "@levelsio" / "indie hacker" / "solo founder" / "Nomad List" / "Photo AI" / "build in public" / "ship daily" / "$10K MRR" 时使用. 即使用户只是说 "我想做个 SaaS 副业" / "怎么 bootstrap" 也应触发.

zpankz Bundle

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming. Use when you need to build complex AI systems, program LMs declaratively, optimize prompts automatically, create modular AI pipelines, or build RAG systems and agents.

zpankz Skill

Optimize prompts via process goals (controllable behavioral instructions) rather than outcome goals (sparse end-result demands). Grounded in sports psychology meta-analysis showing process goals (d=1.36) vastly outperform outcome goals (d=0.09). Use when designing prompts, optimizing LLM steering, implementing CoT/decomposition patterns, or building automatic prompt optimization pipelines. Instantiates surrogate loss paradigm for discrete prompt space.

zpankz Bundle

Local RAG indexing with 97% storage reduction via anchor-based lazy recomputation. Graph-based selective embedding storage for memory-efficient semantic code search.

richfrem Bundle

Convert raw plugin analysis results into actionable improvement recommendations for agent-scaffolders and agent-scaffolders. Trigger with "synthesize learnings", "generate improvement recommendations", "what should we improve in our scaffolders", "update our meta-skills based on these findings", or after completing a plugin analysis.

richfrem Bundle

Consumes friction_cluster_agent hotspot reports and synthesizes systemic refactoring proposals for human review, for Tier 3 architecture friction. Trigger with "synthesize a refactoring proposal from the friction hotspots", "what's the systemic fix for this friction cluster", or when os-architect/self-evolution escalates a Tier 3 (Regression / Architecture) friction event per github-issue-logging-policy.md. Migrated from the former repository-improvement-agent (2026-09-05): deterministic report-synthesis task, no interview, no self-directed git/PR execution — fits the skill archetype, not the agent archetype. Never creates branches, commits, or PRs itself — see "Human Gate" below.

richfrem Bundle

Activate when the user wants to add APM governance, lockfile/audit readiness, or multi-runtime package management to an existing Claude/Copilot/agent plugin, or explicitly convert a plugin into an APM-native package.

richfrem Bundle

Scaffolds an advanced stateful agent skill with filesystem-native state schemas, lifecycle state machines, and skill chaining. NOT for simple stateless skills (use `create-skill`), NOT for isolated conversational wizards / persona swarms (use `create-sub-agent`), and NOT for GitHub Actions workflows (use `create-agentic-workflow`).

richfrem Bundle

Trigger with "evaluate autoresearch fit", "score this skill for karpathy loop", "is this a good autoresearch candidate", "assess autoresearch viability for", "which skills are best for autonomous loop optimization", "score skills for 3-file architecture", or when the user wants to determine if a skill is a good candidate for applying the Karpathy autoresearch autonomous optimization loop pattern.

richfrem Bundle

(Industry standard: Meta-Learning System / Automated Autoresearch) Primary Use Case: Continuous, self-improving orchestration of an agentic system over multiple sessions. Use when: building a continuous improvement layer that autonomously identifies workflow friction, postulates hypotheses, and tests improved instructions/coding skills against an objective headless benchmark before merging and persisting.

richfrem Bundle

Adds an MCP server integration configuration to an existing plugin. NOT for scaffolding a brand-new plugin (use `create-plugin`) and NOT for Azure hosted agents (use `create-azure-agent`).

richfrem Bundle

Audit file path references in plugins and skills. Trigger with "audit path references", "check file references", "find broken references", "path reference audit", "verify paths", or when you need to validate that all ./references in code actually exist in the skill/plugin. Three-phase audit: (1) SCAN all files for references, (2) VERIFY each exists, (3) REPORT issues. Generates inventory.json for reuse across multiple checks.

richfrem Bundle

Automatically updates the plugin/skill/agent counts in README.md based on the current plugins/ directory.

richfrem Bundle

Safe Create/Read/Update/Delete operations for Obsidian Vault notes. Implements atomic writes, advisory locking, concurrent edit detection, and lossless YAML frontmatter handling. Use when reading, writing, updating, or appending to any vault note.

zpankz Bundle

Uncertainty-aware non-linear reasoning system with recursive subagent orchestration. Triggers for complex reasoning, research, multi-domain synthesis, or when explicit commands `/nlr`, `/reason`, `/think-deep` are used. Integrates think skill (reasoning), agent-core skill (acting), and MCP tools (infranodus, exa, scholar-gateway) in recursive think→act→observe loops. Uses coding sandbox for execution validation and maintains deliberate noisiness via NoisyGraph scaffold. Supports `/compact` mode for abbreviated outputs and `/semantic` mode for rich exploration.

zpankz Bundle

This skill should be used when working with BMAD (BMad-CORE) v6-alpha projects. BMAD is a universal human-AI collaboration platform with specialized modules for software development (BMM), agent building (BMB), creative intelligence (CIS), and project management (BMD). Use this skill to understand agent workflows, command patterns, scale-adaptive methodology, and effective utilization of the four-phase development system.

aretedriver Bundle

Evaluation-mode prompt scaffold. Use when you have candidates (options, outputs, PRs, copy variants, vendors) and need a scored comparison with a verdict — not opinions. Always produces a decision plus evidence. "It depends" is not an acceptable output. Invoke with /evaluation.

aretedriver Bundle

Production-mode prompt scaffold. Use when the decision is made and spec is clear — produce the final deliverable with no exploratory sprawl, no meta-commentary, no preamble. Output is the artifact itself, nothing else. Invoke with /production.

aretedriver Bundle

Exploration-mode prompt scaffold. Use when the option space isn't mapped yet — generate distinct alternatives, surface unknowns, challenge assumptions. The output is a list of options with evidence, not a recommendation. Invoke with /exploration.

aretedriver Bundle

Packages project state into structured context documents for agent sessions, human pickup, or Quorum IntentNodes

richfrem Bundle

Progressive-disclosure query against the Obsidian LLM wiki. Returns RLM summary first, expands to bullets, then full wiki node on demand. Use when looking up concepts, searching the wiki, or getting instant context from the knowledge graph.