All authors
Claude Skills by richfrem
github.com/richfrem381 skills4 installs475 views
- Domain PatternsSkills evaluated primarily on routing accuracy (correct trigger/no-trigger given a user prompt). Use when `--primary-metric` is `quality_score`, `f1`, `precision`, or `recall`.Votes: 0GitHub stars: 7
- Evo SmoketestConverts temperatures between Celsius and Fahrenheit for the evolution end-to-end smoke test harness.Votes: 0GitHub stars: 7
- Optimize Agent InstructionsAudits and rewrites the canonical AGENTS.md instruction file in any repo. Strips stale or foreign content and applies Karpathy's four behavioral principles. It reports legacy CLAUDE.md, GEMINI.md, and .github/copilot-instructions.md mirrors but does not rewrite them by default, preventing instruction duplication and context bloat. Trigger when the user says "optimize my CLAUDE.md", "audit agent instructions", "improve my AGENTS.md", "apply Karpathy principles to my agent files", "clean up my ...Votes: 0GitHub stars: 7
- Os ArchitectSME-facing front-door skill for Agentic OS ecosystem evolution. Invokes the os-architect interview flow: classifies intent, audits existing capabilities, proposes evolution path (orchestrate / update / create), and dispatches work. Use when evolving plugins, skills, or agents — whether applying a new pattern, setting up an improvement lab, filling a capability gap, or coordinating multiple loops.Votes: 0GitHub stars: 7
- Os Clean LocksSafely removes all agent lock files from the context/.locks/ directory to resolve deadlocks caused by crashed agents leaving stale locks behind. Use when the user says "/os-clean-locks", "clear all locks", "reset agent locks", or when an agent is deadlocked and cannot acquire a lock because a previous agent crashed and left a stale lock behind in context/.locks/. Verifies lock existence, discovers and removes stale lock directories, updates OS state via kernel.py, and emits event bus notifica...Votes: 0GitHub stars: 7
- Os Environment ProbeDiscovers 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.Votes: 0GitHub stars: 7
- Os Eval BackportReviews a completed os-eval-runner lab run and backports approved changes to master plugin sources. Trigger with "backport the eval results", "review the lab run", "apply eval improvements to master", "check what the eval agent changed".Votes: 0GitHub stars: 7
- Os Eval Lab SetupBootstraps a skill evaluation lab repo for an autoresearch improvement run. Trigger with "set up an eval lab", "bootstrap the eval repo", "prepare the test repo for skill evaluation", "create an eval environment for this skill", "set up the lab space for this skill", or when starting a new skill optimization run that needs a standalone test environment.Votes: 0GitHub stars: 7
- Os Eval RunnerStateless evaluation engine that scores and gates skill improvement iterations using headless Python evaluation scripts. Use when the user says "evaluate this skill", "run autoresearch loop on", "optimize this skill", "run the eval loop", or when another agent proposes a change and needs validation.Votes: 0GitHub stars: 7
- Os Evolution PlannerCodifies 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.Votes: 0GitHub stars: 7
- Os Evolution VerifierVerifies 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.Votes: 0GitHub stars: 7
- Os Experiment LogMaintains a persistent, folder-based log of all agentic-os experiment runs. Each run writes one dated file to context/experiment-log/ and updates index.md. Supports five source types: verifier (qualitative), tester (qualitative), orchestrator (numeric), planner (qualitative), survey (mixed). Handles both numeric results (eval scores, KEEP/DISCARD, delta) and qualitative results (PASS/FAIL/PARTIAL, gap analysis). Use after any experiment run to persist findings before temp/ is cleared.Votes: 0GitHub stars: 7
- Os GuideTrigger with "explain agentic os", "how do I set up a persistent agent environment", "what is the CLAUDE.md hierarchy", "explain the context folder structure", "how does session memory work", "what is soul.md or user.md", "explain auto-memory or MEMORY.md", "what is a loop scheduler or heartbeat", or when the user asks for the canonical guide.Votes: 0GitHub stars: 7
- Os Improvement LoopPattern 5: Concurrent Event-Driven Multi-Agent Loop. Coordinates multiple Claude sessions as OS threads sharing a common event bus and memory address space. Every loop cycle is a full improvement cycle: execute, eval against benchmark (KEEP/DISCARD), emit friction events, and close with surveys, metrics, memory persistence, and Triple-Loop triggers.Votes: 0GitHub stars: 7
- Os Improvement ReportTrigger 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.Votes: 0GitHub stars: 7
- Os InitTrigger: "set up agentic OS", "initialize agent harness", "init my project for AI agents", "retrofit repository", "upgrade project for evolution", "sync instruction files", "where do I put CLAUDE.md", "create my agent environment", "set up persistent memory". Guides users through discovery, initializes/retrofits 3-Layer Memory, keeps AGENTS.md as the sole canonical instruction file, and guides plugin installation.Votes: 0GitHub stars: 7
- Os Memory ManagerTrigger with "remember this", "update memory", "what should we record from this session", "capture learnings", "write a session log", or when closing a session. Guides agents on managing memory hygiene across sessions, deciding what to write to dated memory logs, what to promote to long-term memory.md, and when to archive.Votes: 0GitHub stars: 7
- Os Skill ImprovementContinuously 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 skil...Votes: 0GitHub stars: 7
- Self EvolutionDeterministic graph-planned self-evolution engine. Enforces 6-node state transitions, worktree isolation, verifier sovereignty, and asymmetric Layer 2 knowledge persistence.Votes: 0GitHub stars: 7
- Todo CheckAudit a file for TODO comments, pending work items, or technical debt markers. Useful for checking code readiness before a commit or reviewing task status. Trigger with "check for todos", "audit for debt", "list pending work", or "scan for TODOs".Votes: 0GitHub stars: 7
- Memory ManagementZero-dependency, filesystem-native 3-Layer Memory Engine based on Google WikiSkill and Stanford graph-planning principles.Votes: 0GitHub stars: 7
- Rlm AuditAudit RLM cache coverage - compare manifest against filesystemVotes: 0GitHub stars: 7
- Rlm Cleanup AgentRemoves stale and orphaned entries from the RLM Summary Ledger when files are deleted, renamed, or moved.Votes: 0GitHub stars: 7
- Rlm CuratorKnowledge Curator agent skill for maintaining RLM semantic ledger hygiene, batch distillation, coverage auditing, and cache cleanup.Votes: 0GitHub stars: 7
- Rlm Distill AgentDistills uncached files into the Recursive Language Model (RLM) Summary cache Ledger by reading files deeply and injecting high-quality 1-sentence summaries via inject_summary.py.Votes: 0GitHub stars: 7
- Rlm InitInteractive RLM cache initialization for setting up a project semantic cache or adding a profile.Votes: 0GitHub stars: 7
- Rlm Search3-Phase Knowledge Search strategy enforcing optimal lookup order - RLM Summary Scan -> Vector DB Semantic Search -> Grep/Exact Match.Votes: 0GitHub stars: 7
- Vector Db AuditAudit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.Votes: 0GitHub stars: 7
- Vector Db CleanupRemoves stale and orphaned chunks from the ChromaDB vector store when source files have been deleted or renamed.Votes: 0GitHub stars: 7
- Vector Db IngestIngests repository files into the ChromaDB vector store, building or updating the vector index using ingest.py.Votes: 0GitHub stars: 7
- Vector Db InitInteractively initializes the Vector DB plugin, configuring source manifests and vector_profiles.json for In-Process or Server mode.Votes: 0GitHub stars: 7
- Vector Db LaunchStart the Native Python ChromaDB background server when concurrent multi-agent read/writes are required.Votes: 0GitHub stars: 7
- Vector Db SearchSemantic search skill for retrieving code and documentation from the ChromaDB vector store. Use when you need concept-based search across the repository (Phase 2 of the 3-phase search protocol). V2 includes L4/L5 retrieval constraints.Votes: 0GitHub stars: 7
- Agent Swarm(Industry standard: Parallel Agent) Parallel multi-agent execution pattern for independent sub-tasks running concurrently across isolated worktrees.Votes: 0GitHub stars: 7
- Co Pilot LoopCooperative Multi-Agent Coordination Loop. Spawns a lightweight companion sub-agent to perform spec discovery, planning, and implementation while the primary agent acts as QA Director.Votes: 0GitHub stars: 7
- Dual Loop(Industry standard: Sequential Agent / Agent as a Tool) Inner/outer agent delegation pattern via strategy packets, with verification and correction loops.Votes: 0GitHub stars: 7
- Graph ExecutionExecutes complex workflows using deterministic graph-state machines, explicit transition guards, transactional worktrees, and receipt gates.Votes: 0GitHub stars: 7
- Learning Loop(Industry standard: Loop Agent / Single Agent) Self-directed research and cognitive continuity loop across Orientation, Synthesis, Strategic Gate, and Completion.Votes: 0GitHub stars: 7
- Orchestrator(Industry standard: Routing Agent / Orchestrator Pattern) Analyzes incoming triggers to select loop patterns and manage shared session closure.Votes: 0GitHub stars: 7
- Red Team Review(Industry standard: Review and Critique Pattern) Primary Use Case: Iterative generation paired with adversarial review, continuing until an 'Approved' verdict is reached. Orchestrated adversarial review loop. Use when: research, designs, architectures, or decisions need to be reviewed by red team agents (human, browser, or CLI). Iterates in rounds of research → bundle → review → feedback until approved.Votes: 0GitHub stars: 7
- Select Loop StrategySelects the optimal agent orchestration topology using a deterministic 6-gate decision tree.Votes: 0GitHub stars: 7
- Triple Loop Learning(Industry standard: Meta-Learning System / Automated Autoresearch) Autonomous improvement loop evaluating friction and validating mutations against headless benchmarks.Votes: 0GitHub stars: 7
- Patterns**Use Case:** Complex domains where the agent needs to generate its own contextual reference files or even scaffold out entirely new skills dynamically.Votes: 0GitHub stars: 7
- Audit PluginUse when the user asks to audit or validate a plugin, check its structure or .claude-plugin/plugin.json, review components, or confirm compliance. Also trigger after plugin components change. Audit the whole plugin here; use audit-skill for one skill.Votes: 0GitHub stars: 7
- Audit SkillAudits and aligns individual skills or a repository skill inventory against authoring standards. Provides deterministic structural checks and optional AI review of language efficiency. Use audit-plugin for whole-plugin structure.Votes: 0GitHub stars: 7
- Compile Apm PackageActivate 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.Votes: 0GitHub stars: 7
- Convert Plugin To ApmActivate 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.Votes: 0GitHub stars: 7
- Create Agentic WorkflowScaffolds a Copilot GitHub agent, an agent that runs in GitHub Actions, a GitHub workflow agent, or a GitHub Agentic Workflow (gh-aw) from an existing skill. Supports three target configurations: Target A (Custom Copilot agent), Target B (GitHub Agentic Workflow), and Target C (CI/CD Smart Failure agent).Votes: 0GitHub stars: 7
- Create Apm PackageActivate 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.Votes: 0GitHub stars: 7
- Create Azure AgentDeploys a skill as an Azure AI Foundry hosted agent. NOT for Docker runtime skills (use `create-docker-skill`) and NOT for MCP server integrations (use `create-mcp-integration`).Votes: 0GitHub stars: 7