AI & ML

jamie-bitflight Bundle

Process quality methodology for the process-siren agent — use before or during Mermaid conversion when the source process shows ambiguity, missing decisions, undefined actors, vague conditions, or structural weakness. Provides triage sequence, excellence criteria, and an improvement framework drawn from Lean, Six Sigma, BPR, Design Thinking, Systems Thinking, and Theory of Constraints. Activates when source content is poorly structured enough that converting it as-is would encode wrong behavior for AI readers.

jackspace Bundle

This skill provides comprehensive knowledge for building type-safe APIs with Hono, focusing on routing patterns, middleware composition, request validation, RPC client/server patterns, error handling, and context management. Use when: building APIs with Hono (any runtime), setting up request validation with Zod/Valibot/Typia/ArkType validators, creating type-safe RPC client/server communication, implementing custom middleware, handling errors with HTTPException, extending Hono context with custom variables, or encountering middleware type inference issues, validation hook confusion, or RPC performance problems. Keywords: hono, hono routing, hono middleware, hono rpc, hono validator, zod validator, valibot validator, type-safe api, hono context, hono error handling, HTTPException, c.req.valid, middleware composition, hono hooks, typed routes, hono client, middleware response not typed, hono validation failed, hono rpc type inference

jamie-bitflight Bundle

Use when extracting specific data points from large agent output transcripts, kaizen analysis reports, or JSONL session files — tool timings, query counts, error summaries, or any structured facts — without loading raw data into orchestrator context. Activates when the orchestrator needs targeted facts from large files and context pollution must be avoided.

jamie-bitflight Skill

Shapes for running many sub-agents at once — fan-out with a barrier, maker/checker, generate-and-filter, tournaments for ranking, hypothesis fan-out for root cause, and loops that stop on a condition with a cap. Use when a phase has several independent targets, when a task is too large or too repetitive for one window, when the same edit applies across many files, when ranking or judging a large set, when several hypotheses compete, or when work must repeat until a signal says stop. Does not apply when units depend on each other's results or the cause is still unknown — investigate first, then parallelize.

human-avatar Skill

Maps the audience's current beliefs, real goals, fears, and threshold conditions before communicating with them. Use when asked to 'model the audience', 'audience analysis', 'who am I talking to', 'what do they care about', or 'why aren't they getting it'.

jackspace Bundle

This skill provides comprehensive knowledge for working with the Anthropic Claude Agent SDK. It should be used when building autonomous AI agents, creating multi-step reasoning workflows, orchestrating specialized subagents, integrating custom tools and MCP servers, or implementing production-ready agentic systems with Claude Code's capabilities. Use when building coding agents, SRE systems, security auditors, incident responders, code review bots, or any autonomous system that requires programmatic interaction with Claude Code CLI, persistent sessions, tool orchestration, and fine-grained permission control. Keywords: claude agent sdk, @anthropic-ai/claude-agent-sdk, query(), createSdkMcpServer, AgentDefinition, tool(), claude subagents, mcp servers, autonomous agents, agentic loops, session management, permissionMode, canUseTool, multi-agent orchestration, settingSources, CLI not found, context length exceeded

jackspace Bundle

Reference for OpenAI's Responses API (/v1/responses), the unified stateful API for agentic applications. Covers reasoning state preserved across turns, conversation IDs and automatic state management, polymorphic outputs, built-in tools (Code Interpreter, File Search, Web Search, Image Generation), MCP server integration, background mode, and migration from Chat Completions. Includes both the Node.js openai SDK and direct fetch usage in Cloudflare Workers. Use when building agents that keep reasoning across turns, conversational AI with memory, tool- based or RAG applications, data analysis agents, or when calling openai.responses.create with gpt-5 models, connecting MCP servers, or porting existing Chat Completions code to the Responses API.

jackspace Bundle

Guide to the Google Gemini API using the current @google/genai SDK v1.27+, not the deprecated @google/generative-ai (sunset November 2025). Covers text generation, streaming, multimodal input (images, video, audio, PDFs), function calling including parallel and compositional calls, system instructions, multi-turn chat, thinking mode, generation parameters, context caching, built-in code execution, grounding with Google Search, error handling and rate limits, plus accurate 2025 model facts (Gemini 2.5 Pro, Flash and Flash-Lite with 1M input tokens, not 2M). Use when integrating Gemini, building multimodal or chat applications, deploying Gemini calls to Cloudflare Workers, migrating off @google/generative-ai, or debugging model not found, context window, function calling, or multimodal format errors. Embeddings live in the google-gemini- embeddings skill.

jackspace Bundle

Guide to OpenAI's Assistants API v2: stateful conversational AI with Code Interpreter, File Search and function calling, vector stores for RAG up to 10,000 files, thread and run lifecycle management, and streaming, using the Node.js SDK or plain fetch. Notes the planned H1 2026 sunset and the migration path to the Responses API. Use when building stateful OpenAI chatbots, implementing RAG with vector stores, running Python via Code Interpreter, doing document Q&A with file search, managing conversation threads and run polling, streaming assistant responses, maintaining legacy Assistants code, or debugging errors such as thread already has active run, run status polling timeouts, vector store indexing delays, and file upload failures.

jamie-bitflight Skill

Generates one worker task prompt conforming to the CLEAR + selective CoVe task design standard and swarm-task-planner structure. Use when creating or rewriting a single task entry or task block inside a plan — providing a title and brief description as input.

jamie-bitflight Bundle

Optimize existing CLAUDE.md, SKILL.md, agent definitions, and other AI-facing files for Claude comprehension and economy. Scope: optimization of existing content only — not upstream sync, not read-only auditing. Measures baseline metrics, delegates to @ai-doc-optimizer agent with file-type-specific context, runs independent verification via second agent, measures post-optimization metrics, and presents comprehensive before/after report. Supports iterative mode for large targets. Use when improving prompt effectiveness, reducing token waste, or rewriting instructions for LLM consumption. Invoke with /optimize-claude-md <file-or-directory>.

harshahosur81 Skill

Master TypeScript with advanced types, generics, and strict type safety. Handles complex type systems, decorators, and enterprise-grade patterns. Use PROACTIVELY for TypeScript architecture, type inference optimization, or advanced typing patterns.

harshahosur81 Skill

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

harshahosur81 Skill

Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.

human-avatar Skill

Maps what kind of knowing is actually in play for a claim or question. Distinguishes a priori from a posteriori knowledge; propositional (knowing that) from procedural (knowing how) from acquaintance (knowing of); and knowledge sourced from perception, inference, testimony, intuition, or memory. Use when you say 'what kind of claim is this', 'is this something we can reason our way to or do we need evidence', 'they're treating this as obvious but I don't think it is', 'is this really an empirical question', or when you need to assess what standards of justification apply before testing whether a claim is true.

jackspace Bundle

Guidance on Claude Code, Anthropic's terminal-based agentic coding tool. Use when asked about Claude Code features, installation and authentication, slash commands, Agent Skills, MCP server configuration, hooks and plugins, IDE integration, enterprise deployment, or troubleshooting.

jamie-bitflight Bundle

Configure Claude Code permissions — tool approval rules, permission modes, managed policies, and sandboxing. Use when setting up permission rules, configuring allow/deny/ask policies, debugging permission prompts, deploying managed settings for organizations, or controlling Bash/Read/Edit/WebFetch/MCP/Agent tool access.

jamie-bitflight Bundle

Executes a groomed milestone with parallel kage-bunshin sessions in isolated worktrees. Use when a milestone has been groomed and /groom-milestone has produced a dispatch plan. Reads the dispatch plan, creates an integration branch, spawns one kage-bunshin (independent claude -p process) per wave item in its own worktree — each session is a full orchestrator with the Agent tool. Sequentially merges worktree branches, relays wave discoveries to subsequent waves, then lands the integration branch to main. Takes a milestone number as argument.

jamie-bitflight Skill

Query and invoke tools on MCP servers using fastmcp list and fastmcp call. Use when you need to discover what tools a server offers, call tools, or integrate MCP servers into workflows.

jamie-bitflight Bundle

Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md configurations, or Skill files. Transforms negative instructions into positive patterns following Anthropic's official best practices.

jamie-bitflight Skill

Start or complete a specific refactoring task from a task file. Use when a sub-agent needs to pick up a refactoring task, update its status, implement acceptance criteria, and run verification steps.

harshahosur81 Skill

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

harshahosur81 Skill

Use when working with agent orchestration multi agent optimize

human-avatar Skill

Maps what the audience currently believes, actually cares about, and fears before communicating — because communication fails at the receiver, not the sender. Triggers: 'model the audience', 'audience analysis', 'who am I talking to', 'what do they care about', 'why aren't they getting it'.

jamie-bitflight Skill

Use when reviewing AI/ML code or LLM integration — activates on prompt templates, model selection logic, token budget concerns, or evaluation harness code. Enforces prompt hygiene, model tier matching, context window management, token economics, structured output validation, temperature settings, retry logic, streaming error handling, and PII/safety rules.

jamie-bitflight Skill

Use when SAM Stage 5 Execution has completed and task results need independent verification against acceptance criteria. Dispatches a separate reviewer agent to fact-check implementation outputs and returns COMPLETE or NEEDS_WORK with specific findings and remediation tasks.

jamie-bitflight Bundle

Grooms a GitHub milestone for parallel execution — batch-grooms ungroomed items, assesses scope gaps, analyzes cross-item dependencies via Impact Radius overlap, builds conflict groups, assigns items to execution waves, and persists the dispatch plan via dispatch_create_plan MCP tool. Calls dispatch_wave_start per wave to register state. Use when preparing a milestone for /work-milestone execution. Pass the milestone number as the first argument. Requires milestone items assigned via /group-items-to-milestone.

jamie-bitflight Bundle

Design pattern for converting rule-following, checklist, or rubric skills into a fan-out map-reduce ensemble of parallel rigid sub-agents with corroboration-weighted merge; worker model tier and diversity are knobs matched to inference load and stakes, not fixed values. Apply when creating or refactoring a skill or agent that applies 10+ independent criteria in a single pass. Triggers on: 'review against a checklist', 'fan out', 'map reduce review', 'ensemble', 'split the rules', 'apply rubric', or any large ruleset being applied by one agent in one pass. NOT for tight single-pass transforms or rulesets under 5 criteria.

jamie-bitflight Skill

Extract the small set of explicit goals a skill is designed to achieve by reading the skill in full. Use when asked what a skill accomplishes or what capability an agent gains from it, or to summarize a skill's purpose before refactoring or reviewing it.

jamie-bitflight Bundle

Transform transcript analysis findings into actionable improvements. Triggers on "generate hooks from findings", "improve agent", "fix anti-pattern", "kaizen improvement", "generate hook proposals", or "create improvement plan". Provides templates for hook generation, agent prompt refinement, skill patches, CLAUDE.md updates, and script automation from analysis data.

jamie-bitflight Skill

Local codebase analysis research angle — derives behavioral contracts, coding conventions, SKILL.md flow insertion points, and agent data availability maps from actual source files. Use when the blocking question is answered by reading the repository: what does this function actually do, what pattern does the codebase use for X, where in this workflow does a new step go, or what data does this agent already have.

lifangda Bundle

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

lifangda Bundle

Gene regulatory network inference with GRNBoost2/GENIE3 algorithms. Infer TF-target relationships from expression data, scalable with Dask, for scRNA-seq and GRN analysis.

enuno Bundle

LangChain Python package — new create_agent() factory (builds a LangGraph agent from a model string + tools + middleware), plus a comprehensive middleware system covering HITL, PII redaction, model fallback, rate limiting, auto-summarization, context editing, shell tools, and todo planning.

enuno Bundle

LangGraph (Python) — build stateful, controllable agent graphs with checkpointing, streaming, persistence, interrupts, fault tolerance, and durable execution. Covers both Graph API (StateGraph) and Functional API (@entrypoint/@task).

enuno Bundle

LangSmith Python SDK — trace, evaluate, and monitor LLM applications. Covers @traceable decorator, trace context manager, Client API, evaluate() / aevaluate(), comparative evaluation, custom evaluators, dataset management, prompt caching, ASGI middleware, and pytest plugin.