Prompts
Prompt engineering and templates
instinct-system
by codewithmukesh
Confidence-scored instinct system for learning project-specific patterns through an observe-hypothesize-confirm cycle. Instincts start as low-confidence hypotheses and graduate to permanent rules in MEMORY.md once confirmed. Stored per-project in .claude/instincts.md. Load this skill when you notice a recurring pattern, want to track a project convention, encounter "learn this", "I think they always", "notice a pattern", "instinct", "hypothesis", "confidence", or when starting a session (to load existing instincts).
wrap-up-ritual
by codewithmukesh
Structured session ending ritual that captures completed work, pending tasks, and learnings before a session ends. Writes a handoff note to .claude/handoff.md so the next session (or a different developer) can pick up exactly where this session left off. Load this skill when the user signals they're wrapping up, says "let's stop here", "that's all for now", "end of session", "wrap up", "save progress", "handoff", or "I'm done for today".
convention-learner
by codewithmukesh
Detects and enforces project-specific coding conventions by analyzing existing codebase patterns. Learns naming conventions, folder structure, test organization, and coding style from the existing code. Load when: "conventions", "coding standards", "project patterns", "enforce style", "detect patterns", "learn conventions", "code consistency".
session-management
by codewithmukesh
End-to-end session lifecycle management for .NET projects. Handles session start (load handoff, MEMORY.md, instincts, detect .NET solution), session end (capture completed work, persist learnings, write handoff), and context preservation across sessions. Load this skill when starting a new session, ending a session, when the user says "new session", "pick up where we left off", "what were we working on", "session start", "session end", "handoff", "context", "resume", or when Claude needs to bootstrap itself in an unfamiliar project.
workflow-mastery
by codewithmukesh
Claude Code workflow mastery for .NET developers. Covers parallel execution with git worktrees, plan mode strategy, verification loops, auto-formatting hooks, permission setup for dotnet CLI, prompting techniques, and subagent patterns — all adapted for the .NET ecosystem. Load this skill when setting up Claude Code for a .NET project, optimizing workflows, running parallel sessions, or when the user mentions "productivity", "workflow", "parallel", "worktree", "plan mode", "permissions", "hooks", "10x", "setup Claude Code", or "speed up development". Inspired by tips from Boris Cherny (creator of Claude Code) and the Anthropic team.
split-memory
by codewithmukesh
Modular CLAUDE.md management strategy for projects that outgrow a single instruction file. Covers when and how to split a monolithic CLAUDE.md into multiple files, organizing by concern, module, or team. Includes precedence rules to prevent conflicting instructions. Load this skill when CLAUDE.md exceeds 300 lines, when multiple teams need different instructions, when the user mentions "split CLAUDE.md", "modular instructions", "too long", "organize instructions", or "multiple CLAUDE files".
youtube-srt
by BlackBeltTechnology
Download YouTube subtitles (SRT + timestamped TXT) for a channel, playlist or video via yt-dlp, no media download; optionally mine them into a categorized catalog (e.g. AI models by function, open weights, local runnability, hardware tier). Use on "download the srt of this video", "transcripts of channel X for the last N months", "catalog the models AI Search talked about", "update docs/models".
ctf-ai-ml
by ljagiello
Provides AI and machine learning techniques for CTF challenges. Use when attacking ML models, crafting adversarial examples, performing model extraction, prompt injection, membership inference, training data poisoning, fine-tuning manipulation, neural network analysis, LoRA adapter exploitation, LLM jailbreaking, or solving AI-related puzzles.
environmental-scanning-foresight
by lyndonkl
Use when scanning external trends for strategic planning, monitoring PESTLE forces (Political, Economic, Social, Technological, Legal, Environmental), detecting weak signals (early indicators of change), planning scenarios for multiple futures, setting signposts and indicators for early warning, or when user mentions environmental scanning, horizon scanning, trend analysis, scenario planning, strategic foresight, futures thinking, or emerging issues monitoring.
chain-spec-risk-metrics
by lyndonkl
Use when planning high-stakes initiatives (migrations, launches, strategic changes) that require clear specifications, proactive risk identification (premortem/register), and measurable success criteria. Invoke when user mentions "plan this migration", "launch strategy", "implementation roadmap", "what could go wrong", "how do we measure success", or when high-impact decisions need comprehensive planning with risk mitigation and instrumentation.
estimation-fermi
by lyndonkl
Use when making quick order-of-magnitude estimates under uncertainty (market sizing, resource planning, feasibility checks), decomposing complex quantities into estimable parts, bounding unknowns with upper/lower limits, sanity-checking strategic assumptions, or when user mentions Fermi estimation, back-of-envelope calculation, order of magnitude, ballpark estimate, triangulation, or needs to assess feasibility before detailed analysis.
edit-flow
by BlackBeltTechnology
Create and edit pi-flows flows and agents from the main session. Use when the user wants to create a new flow, add or change an agent, or edit an existing flow/agent. Covers agent frontmatter, flow YAML, step types, model references, the flow_agents and flow_write tools, write locations, and how to fix validation errors.
building-streamlit-chat-ui
by streamlit
Building chat interfaces in Streamlit. Use when creating conversational UIs, chatbots, or AI assistants. Covers st.chat_message, st.chat_input, message history, and streaming responses.
prompt-refiner-claude
by Factory-AI
Refine prompts for Claude models (Opus, Sonnet, Haiku) using Anthropic's best practices. Use when preparing complex tasks for Claude.
Claude-Mem OpenClaw Plugin — Setup Guide
by thedotmack
observationFeed.to string â Target chat/channel/user ID
code-review
by pipecat-ai
Automated code review for pull requests using multiple specialized agents
stakeholder-requirements-gathering
by nimrodfisher
Structured requirements elicitation for analysis requests. Use when scoping new analysis projects, clarifying ambiguous business questions, or documenting analysis acceptance criteria with stakeholders.
route
by ypollak2
Route a task to the best LLM based on task type and complexity
analysis-retrospective
by nimrodfisher
Post-analysis learning and process improvement. Use when completing major analysis projects, documenting lessons learned, or improving team analytical practices.
my-skill
by LukeRenton
What this skill does and when to use it. Claude reads this to decide relevance. Include keywords users would naturally say.
Short-Form Video Clip Pipeline — Skill
by ericosiu
Clip too long: Claude sometimes overshoots. The pipeline auto-trims clips >90s to 75s.
LLM Router — Savings Tracking Skill
by ypollak2
```
interrogate
by Sma1lboy
"Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Multiple LLM reviewers challenge changes from independent angles."
architect
by Sma1lboy
"Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape."