All authors
Claude Skills by richfrem
github.com/richfrem381 skills4 installs475 views
- Create Docker SkillScaffolds an agent skill with a Docker runtime environment. NOT for normal local skills (use `create-skill`) and NOT for Azure hosted agents (use `create-azure-agent`).Votes: 0GitHub stars: 7
- Create Github ActionScaffolds a deterministic GitHub Actions CI/CD workflow YAML. NOT for scaffolding interactive agentic workflows (use `create-agentic-workflow`) and NOT for local event-driven hooks (use `create-hook`).Votes: 0GitHub stars: 7
- Create HookScaffolds a new event-driven hook in a plugin. NOT for creating skills (use `create-skill`) and NOT for GitHub Actions agentic workflows (use `create-agentic-workflow`).Votes: 0GitHub stars: 7
- Create Mcp IntegrationAdds 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`).Votes: 0GitHub stars: 7
- Create PluginScaffolds a new top-level agent plugin directory. NOT for scaffolding single skills (use `create-skill`) and NOT for adding MCP integrations to existing plugins (use `create-mcp-integration`).Votes: 0GitHub stars: 7
- Create SkillCreates a new skill in an existing plugin, with concise instructions, direct references and task evaluations. Use when scaffolding or authoring a skill; supports instructional and executable variants.Votes: 0GitHub stars: 7
- Create Stateful SkillScaffolds 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`).Votes: 0GitHub stars: 7
- Create Sub AgentScaffolds a new autonomous sub-agent with its own prompt, system instructions, and tool permissions. Enforces modern architectural guidance: sub-agents are reserved for isolated execution contexts, strict tool sandboxing, or adversarial personas. NOT for simple procedural skills (use `create-skill`) and NEVER for pointer-wrapper stubs that merely delegate to a skill.Votes: 0GitHub stars: 7
- Ecosystem Authoritative SourcesProvides information about how to create, structure, install, and audit Agent Skills, Plugins, Antigravity Workflows, and Sub-agents. Trigger this when specifications, rules, or best practices for the ecosystem are required.Votes: 0GitHub stars: 7
- Ecosystem StandardsProvides 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.Votes: 0GitHub stars: 7
- Install Apm PackageActivate when the user wants to install, deploy, test, or materialize an APM package into runtime directories such as .agents/, .github/, .claude/, .cursor/, .gemini/, .codex/, .opencode/, or .windsurf/. Use after creating or converting an APM package.Votes: 0GitHub stars: 7
- Manage MarketplaceThis 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".Votes: 0GitHub stars: 7
- Flawed SkillA deliberately broken skill that should trigger multiple anti-pattern detections during analysis.Votes: 0GitHub stars: 7
- Example SkillUse when demonstrating a correctly structured agent skill. Trigger when the user asks to "show a well-formed skill", "give me a skill template", or "what does a compliant SKILL.md look like". Also triggers for regression testing: this fixture MUST score maturity >= L2 with zero Critical or Error findings.Votes: 0GitHub stars: 7
- Compliant SkillThis skill does things.Votes: 0GitHub stars: 7
- Agent File SynchronizationMaintains AGENTS.md as the single canonical project instruction file and reports legacy CLAUDE.md, GEMINI.md, and .github/copilot-instructions.md mirrors without copying into them by default. Explicit target syncing remains an opt-in compatibility operation. Also reports drift between .agent/rules/ and matching plugins/*/rules/ sources. Triggers: "sync instructions", "sync AGENTS.md", "check instruction drift", "replicate instruction files", "check rule drift".Votes: 0GitHub stars: 7
- Agt SecurityProvides sandboxing validation, HMAC key rotation, and budget verification to manage security boundaries under Agentic Group Theory (AGT).Votes: 0GitHub stars: 7
- Agy Cli AgentDispatches authorized tasks through Antigravity (agy) to Gemini and other agy-hosted models. Use for agy execution, Gemini tasks, or an agy sub-agent.Votes: 0GitHub stars: 7
- Claude Cli AgentDispatches bounded tasks and persona-based analysis through Claude CLI. Use for authorized Claude reviews, audits, or work requiring a fresh model context.Votes: 0GitHub stars: 7
- Codex Cli AgentDispatches bounded coding tasks and analysis through the Codex CLI. Use for authorized Codex execution, code reviews, or tasks needing a fresh OpenAI model context.Votes: 0GitHub stars: 7
- Copilot Cli AgentDispatches bounded tasks and persona-based analysis through GitHub Copilot CLI. Use for authorized task delegation, security audits, code reviews, or fresh-context analysis.Votes: 0GitHub stars: 7
- Local Llm BridgeLocal Gemma 4 12B sub-agent. Routes bounded tasks directly to the optimized llama-server at localhost:8089 — no routing proxy, no cloud API, 2–5s typical response. Use for fast, private, cost-free subtask delegation from any cloud primary agent. Part of the run_agent.py multi-LLM task router — cli=llama target.Votes: 0GitHub stars: 7
- Local Llm SetupCross-platform setup wizard for the local Gemma 4 12B inference stack. Automates llama-server installation (binary download or Metal/CUDA/Vulkan/ROCm compile), model download, routing proxy daemon install (launchd/systemd/NSSM), and Mode A/B validation. Covers Day 1 bootstrap and Day 2+ reconfiguration.Votes: 0GitHub stars: 7
- Maf AdapterProvides validation, setup guidance, and a local test harness simulator to run skills within the Microsoft Agent Framework (MAF).Votes: 0GitHub stars: 7
- Project SetupConfigures agent runtimes for a project and establishes a reusable, non-secret provider capability profile. Use for project setup, agent configuration scaffolding, or refreshing provider access and model preferences.Votes: 0GitHub stars: 7
- Update Cli ModelsUpdates CLI model catalogs, capability tiers and cheapest-model references from official sources. Use when asked to refresh model IDs, availability or prices for Copilot, Agy, Claude, Codex or local models.Votes: 0GitHub stars: 7
- Dependency ManagementPython dependency and environment management for multi-service or monorepo python backends. Use when adding, upgrading, or removing packages, responding to CVE floor alerts, creating service requirements, debugging install failures, or running pip-compile. Enforces the pip-compile locked-file workflow and tiered dependency hierarchy.Votes: 0GitHub stars: 7
- Adr ManagementScaffolds, lists, searches, and manages Architecture Decision Records (ADRs) to record permanent institutional memory.Votes: 0GitHub stars: 7
- Coding Conventions AgentEnforces codebase coding conventions, file headers, type hints, Google docstrings, and naming standards across languages.Votes: 0GitHub stars: 7
- Context BundlerInteractively creates targeted code and documentation bundles (Markdown or ZIP) for review and sub-agent task delegation.Votes: 0GitHub stars: 7
- Convert MermaidTranslate .mmd diagram files into PNG images with configurable resolution, supporting binary linting and Puppeteer-based rendering.Votes: 0GitHub stars: 7
- Github Issue AgentAgent skill for safe, dry-run-first, deduplicated, root-cause-consolidated, evidence-validated, and secret-redacted logging of repository execution friction into GitHub Issues. USE ONLY for durable repository bugs, execution friction (T1-T3), map debt, and architectural improvements. DO NOT USE for managing git worktrees (use `github-issue-worktree-agent`) or full PR lifecycles (use `github-issue-pr-lifecycle-agent`).Votes: 0GitHub stars: 7
- Github Issue Backlog AgentBridge skill for escalating ephemeral local task scratchpad items (`tasks/*.md`) into durable, taxonomy-validated, evidence-rich GitHub Issues. USE ONLY when promoting a single-session local task into durable repository backlog. DO NOT USE for directly querying/commenting on issues (use `github-issue-agent` instead).Votes: 0GitHub stars: 7
- Github Issue PrioritizerAutomatically ranks GitHub issues (P0-P3) based on friction tier, frequency, and blockages, synchronizing priority labels and GitHub Projects v2 custom fields. USE ONLY when calculating issue priority ranks or generating Projects v2 payload mutations. DO NOT USE for logging issues (use `github-issue-agent`).Votes: 0GitHub stars: 7
- Hf DownloadDownload primitives for HuggingFace assets - files, folder snapshots, and model weights with exponential backoff on rate limits. Use when pulling models, datasets, or caches from HuggingFace to the local environment.Votes: 0GitHub stars: 7
- Hf InitInitialize HuggingFace integration - validates environment variables, tests API connectivity, and sets up dataset repository structure.Votes: 0GitHub stars: 7
- Hf UploadUpload primitives for HuggingFace Soul persistence - file, folder, snapshot, JSONL append, and dataset card management with exponential backoff. Use when persisting agent learnings, snapshots, or semantic caches to HuggingFace.Votes: 0GitHub stars: 7
- HumanizeTransforms synthetic, stiff, or AI-flavored text into natural writing with authentic human rhythm, tone, and personality.Votes: 0GitHub stars: 7
- Link Checker AgentSpecialized QA operator for documentation link integrity, auditing, and auto-repair across repository markdown files.Votes: 0GitHub stars: 7
- Optimize ContextReduces AI agent context bloat across three dimensions: duplicate skill deduplication, canonical AGENTS.md optimization, and session token efficiency. USE ONLY when trimming instruction files, diagnosing duplicate skill loading, or reducing agent token overhead.Votes: 0GitHub stars: 7
- Symlink ManagerCreate, audit, repair, and document cross-platform symlinks. Use when the user mentions symlinks, junctions, broken links after git pull, cross-platform path issues, or missing files after switching machines. Supports macOS/Linux and Windows; Windows users need Developer Mode or administrator rights before creating true symlinks.Votes: 0GitHub stars: 7
- Business Requirements CaptureCaptures and refines business requirements, including functional requirements, non-functional requirements, business rules, constraints, assumptions, and success measures. Produces structured BRD-style documents with [CONFIRMED] and [UNCONFIRMED] confidence markers. Trigger with "capture requirements", "generate a BRD", "document business rules", "list the constraints", or "create a requirements document".Votes: 0GitHub stars: 7
- Business Workflow DocGenerate Mermaid flowcharts documenting business processes, state machines, and workflow logic from session captures. Use when you need to map multi-step processes, approval flows, user journeys, or decision trees during exploration.Votes: 0GitHub stars: 7
- Discovery PlanningGuides a Subject Matter Expert through a structured discovery session to create and approve a Discovery Plan before any building begins. This is the HARD-GATE brainstorming skill — no prototype can be built until the SME explicitly approves the plan. Trigger phrases: "start a discovery session", "let's plan this out", "help me figure out what we're building", "I have an idea I want to explore", "let's start from scratch"Votes: 0GitHub stars: 7
- Exploration HandoffInteractive co-authoring skill for the narrow end of the exploration funnel. Synthesizes session briefs, BRDs, story sets, and prototype notes into a structured handoff package targeted at the correct downstream consumer.Votes: 0GitHub stars: 7
- Exploration OptimizerEvaluates and improves the exploration-cycle skills, prompts, routing, and artifact quality using baseline-first, one-hypothesis iteration loops with keep-discard decisions and experiment ledgers.Votes: 0GitHub stars: 7
- Exploration Session BriefCo-authors exploration session briefs at the wide end of the exploration funnel. Captures and refines core intent across software, business processes, or strategic roadmaps.Votes: 0GitHub stars: 7
- Exploration WorkflowOrchestrates the Business Exploration Loop across greenfield, brownfield, discovery-only, and spike sessions. Manages state via exploration-dashboard.md, enforces phase gates, and routes execution to child skills.Votes: 0GitHub stars: 7
- Prototype BuilderOrchestrates the prototype build cycle from approved discovery plans to working prototypes and SME walkthroughs. Coordinates layout confirmation and component assembly.Votes: 0GitHub stars: 7
- Subagent Driven PrototypingBuilds prototypes component by component, conducting self-reviews against the Discovery Plan before advancing. Handles greenfield, brownfield, and plugin prototyping slices.Votes: 0GitHub stars: 7