AI & ML

dtsong Skill

System prompt design, chain-of-thought patterns, structured output, and prompt versioning

megastep Bundle

Generate and edit images with Google's Nano Banana 2 model through the official Python Google GenAI SDK. Use when a user asks to create an image, edit an existing image, restyle a photo, add or remove visual elements, create concept art, mockups, infographics, or product shots with Gemini / Nano Banana, especially when the result should be saved locally and the API key may come from the environment or a file.

overtimepog Skill

Define database models, schemas, and ORM mappings with proper relationships, constraints, and data integrity rules. Use this skill when creating or modifying ORM model classes, database schema definitions, model relationships, validators, or working with files like models.py, schema.prisma, entity classes, or Sequelize/TypeORM/ActiveRecord model definitions. Apply this skill when defining primary keys, foreign keys, indexes, unique constraints, timestamps, or when implementing model validation logic, serializers, and data type mappings. This skill ensures models follow naming conventions, include appropriate database constraints, define clear relationships with cascade behaviors, balance normalization with performance needs, and maintain data integrity at both the model and database levels.

dtsong Bundle

Use this skill when formalizing security properties into TLA+ specifications for model checking with TLC. Triggers on "formalize this security invariant", "TLA+ spec for this protocol", "model check this property", "write a TLA+ security spec". Translates threat findings and protocol behaviors into temporal logic. Do NOT use for threat identification (use threat-model-skill) or verification scaffolding without formal methods (use verification-scaffold-skill).

megastep Bundle

CoreML diagnostics - model load failures, slow inference, memory issues, compression accuracy loss, compute unit problems, conversion errors.

w95 Skill

Generate project status reports with RAG status, milestones, risks, blockers, resource utilization, and executive summaries

masumi-network Bundle

Drive the Sokosumi web app (and Core API) the way a user does — launch local web+core, doctor health, browser login via agent-browser, capture proof. Use when proving a UI/API change works, after feature work, or when a task needs end-to-end evidence beyond unit tests.

arabelatso Bundle

Generate targeted test inputs to reach specific code paths and hard-to-reach behaviors in Python code. Use when: (1) Targeting uncovered branches or specific execution paths, (2) Need coverage-guided test generation, (3) Want to leverage LLM understanding of code semantics for meaningful test inputs, (4) Testing boundary conditions and edge cases systematically, (5) Combining symbolic reasoning with fuzzing. Provides path analysis, constraint solving, coverage-guided strategies, and LLM-driven semantic generation for comprehensive test input creation.

broedkrummen Skill

Bridge skill to call NeuralMemory (nmem) from OpenClaw via the exec tool. Use to remember and recall associative memories without native MCP support.

madappgang Skill

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

madappgang Skill

YAML frontmatter schemas for Claude Code agents and commands. Use when creating or validating agent/command files.

madappgang Skill

Use BEFORE delegating any complex task to a subagent. Contains the routing table that maps task patterns to the correct specialized agent. MUST be consulted before using the Task tool for delegation decisions. Trigger keywords - "delegate", "subagent", "agent", "research", "implement", "investigate", "debug", "architect".

madappgang Skill

Common agent patterns and templates for Claude Code. Use when implementing agents to follow proven patterns for Tasks integration, quality checks, and external model invocation via claudish CLI.

arabelatso Bundle

Automatically generates executable test cases from model checking counterexample traces. Translates abstract counterexample states and transitions into concrete test inputs, execution steps, and assertions that reproduce property violations. Use when working with model checker outputs (SPIN, CBMC, NuSMV, TLA+, Java PathFinder, etc.) and needing to create regression tests, validate bug fixes, or reproduce verification failures in executable test suites.

masharratt Skill

Stage, commit, push changes via background github-commit-agent. Optional args for message override or push control. Use when committing/pushing work.

masharratt Skill

Operations-design phase. Design the production surface UP FRONT: threat model (STRIDE), observability (logs/metrics/traces), rollout (flags/canary), success metrics/KPIs, failure modes (FMEA), capacity/cost, rollback rehearsal, runbook. Use in cfn-megaplan for beta+ tiers so 'how it runs in prod and how we know it worked' is designed, not review-checkboxed.

rjmurillo Bundle

Collect agent usage metrics from git history and generate health reports. Use when measuring agent adoption, reviewing system health, or producing periodic dashboards. Collects Invocation Rate, Coverage, Infrastructure Review, and Usage Distribution. Use when you say "collect agent metrics", "generate metrics dashboard", or "weekly metrics report".

rjmurillo Skill

Route any request to the right skill, command, or agent chain with defaults, so nobody hand-picks from the full catalog. Use when you say `/autoplan`, `do it`, `handle it`, `figure this out`, or when a concrete request names no skill. Do NOT use when the user names a specific skill or lifecycle command; invoke that directly.

rjmurillo Bundle

Multi-agent debate orchestration for Architecture Decision Records. Automatically triggers on ADR create/edit/delete. Coordinates architect, critic, independent-thinker, security, analyst, and high-level-advisor agents in structured debate rounds until consensus. Use when you say "review this ADR", when an ADR is created/edited/deleted, or when reviewing, accepting, or updating a decision file under .agents/architecture/, docs/architecture/, docs/decisions/, docs/adr/, or architecture/decisions/, including intent like "review this decision record" or "check this rationale for future maintainers". Do NOT use to author a new ADR (use adr-generator).

rjmurillo Bundle

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression questioning, evolution lens, and multi-agent synthesis panel. Phase 0 triage ensures you never duplicate existing functionality. Use when you say "create a skill", "do I have a skill for", "which skill should I use", "improve the X skill", or "SkillForge: {goal}". Do NOT use to create a slash command (use slashcommandcreator).

arabelatso Bundle

Automatically derives TLA+ properties (invariants, safety, liveness) from natural-language requirements or structured requirement documents. Resolves ambiguities, asks clarifying questions for underspecified requirements, and outputs TLA+-compatible property definitions with semantic explanations. Use when translating system requirements, specifications, or behavioral constraints into formal TLA+ temporal logic properties for verification with TLC model checker.

clawdsolana Skill

Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5] [--notify-channel -1002381931352]

madappgang Skill

Unified patterns and templates for creating consistent Claude Code plugins. Use when creating new plugins, designing plugin architecture, implementing builder patterns, or standardizing plugin structure. Trigger keywords - "plugin SDK", "plugin template", "plugin pattern", "builder pattern", "plugin structure", "new plugin", "plugin architecture".

madappgang Skill

Comprehensive lifecycle hook patterns for Claude Code workflows. Use when configuring PreToolUse, PostToolUse, UserPromptSubmit, Stop, or SubagentStop hooks. Covers hook matchers, command hooks, prompt hooks, validation, metrics, auto-formatting, and security patterns. Trigger keywords - "hooks", "PreToolUse", "PostToolUse", "lifecycle", "tool matcher", "hook template", "auto-format", "security hook", "validation hook".

madappgang Skill

YAML format for Claude Code agent definitions as alternative to markdown. Use when creating agents with YAML, converting markdown agents to YAML, or validating YAML agent schemas. Trigger keywords - "YAML agent", "agent YAML", "YAML format", "agent schema", "YAML definition", "convert to YAML".

madappgang Skill

Collaborative ideation and planning with resilient multi-model exploration, consensus scoring, and adaptive confidence-based validation

clawdsolana Bundle

List and manage user feedback items from the agent inbox. Use when the user asks about feedback, bug reports, feature requests, or inbox items.

rjmurillo Bundle

Use when you say `run taste lints`, `check file size`, or `lint taste invariants`. Custom lints with agent-readable remediation instructions for file size, naming conventions, structured logging, and complexity.

rjmurillo Bundle

Input adapter that extracts a book's method into a structured payload and hands it off to SkillForge. Use when an operator wants to turn a methodology-bearing book (The Mom Test, Make It Stick, Influence, The Pragmatic Programmer, etc.) into one or more executable skills without hand-crafting the SkillForge prompt or bypassing SkillForge's triage and review gates. Use when you say "turn this book into a skill" or "extract method from TITLE".

rjmurillo Bundle

Use when you say `query agent logs`, `find slow tool calls`, or `show agent errors`. Query and analyze agent JSONL event logs for debugging, performance analysis, and decision tracing.

madappgang Skill

Audio/video transcription using OpenAI Whisper. Covers installation, model selection, transcript formats (SRT, VTT, JSON), timing synchronization, and speaker diarization. Use when transcribing media or generating subtitles.

madappgang Skill

Multi-agent orchestration enforcement for /team command. Provides claudish CLI validation, validates session directory paths, and ensures /team internal Tasks use dev:researcher. Use when debugging /team orchestration failures.

clawdsolana Skill

Convert PDF documents to clean structured Markdown for LLM context. Supports two modes: fast (PyMuPDF) and accurate (IBM Docling TableFormer AI). Features aggressive persistent caching, image extraction with metadata, table detection, and batch processing. Use when asked to convert PDFs, extract PDF content, parse documents, or prepare PDF data for AI/LLM consumption.

clawdsolana Bundle

Create reusable skills that extend agent capabilities. Use when the user asks to create a skill, teach you something reusable, or save instructions for future tasks.

clawdsolana Skill

Sign in with OpenRouter via OAuth PKCE — framework-agnostic, no client registration, no backend, no secrets. Produces an `sk-or-...` API key for any OpenClawd/solana-clawd agent that needs LLM inference.

rjmurillo Bundle

Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors. Use when you say "optimize this prompt", "improve this system prompt", or "review my agent prompt".