AI & ML

richfrem Bundle

Runs a semantic health check over the Obsidian LLM wiki using the cheapest available LLM CLI. Finds inconsistencies, missing concepts, stale articles, connection candidates, and new article suggestions. Writes a structured report to meta/lint-report.md. Use when the wiki is large enough to have quality drift, or as a periodic maintenance step.

richfrem Bundle

Audits closed GitHub issues to verify whether root causes were genuinely resolved, if follow-on execution friction appeared, or if systemic improvements were retained. Trigger with "audit closed issues", "review issue resolution quality", "was this issue actually fixed", or as a post-closure quality gate on issues labeled resolution:fixed or resolution:superseded. Migrated from the former issue-resolution-reviewer agent (2026-09-05): deterministic audit against fixed criteria, no interview, no code writes — fits the skill archetype, not the agent archetype.

richfrem Bundle

Transforms raw source files registered in wiki_sources.json into Karpathy-style LLM wiki nodes inside the wiki-root. Generates concept pages, cluster pages, index, and table of contents. Use when building or rebuilding the wiki from raw content.

richfrem Bundle

Read and manipulate Obsidian Bases (.base) files - YAML-based database views that render as tables, cards, and grids inside the vault. Use when reading, appending rows, or updating cells in a Base file.

richfrem Bundle

Distills wiki source files into the RLM summary layer (summary.md, bullets.md, deep.md) using the cheapest available LLM CLI. Routes to Copilot gpt-5-mini first, then Claude Haiku, then Gemini Flash. Never uses Ollama. Use when wiki nodes need RLM summaries generated or refreshed.

richfrem Bundle

Audits and rewrites AI agent instruction files (AGENTS.md, CLAUDE.md, GEMINI.md, .github/copilot-instructions.md) in any repo. Strips stale or foreign content, applies Karpathy's four behavioral principles, ensures platform-specific sections, and makes each file authoritative rather than a copy of another. 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 copilot instructions", "review my GEMINI.md", or "update my AI instruction files".

richfrem Bundle

Semantic link traversal for Obsidian Vaults. Builds an in-memory graph index from wikilinks and provides instant forward-link, backlink, and multi-degree connection queries. Use when exploring note relationships or finding orphaned notes.

aretedriver Bundle

Specification-mode prompt scaffold. Use when the decision is made and you need a buildable, testable, reviewable spec. Output is fixed-structure with measurable acceptance criteria. Never re-argues the premise. Invoke with /specification.

aretedriver Bundle

Pre-execution context mapping phase inspired by Blitzy — maps codebase structure, identifies dependencies, and builds execution context before any agent writes code. Use before complex multi-file changes, large refactors, or unfamiliar codebases.

zpankz Bundle

Consult official Claude Code documentation from docs.claude.com using selective fetching. Use this skill when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront.

richfrem Bundle

Programmatically create and manipulate Obsidian Canvas (.canvas) files using JSON Canvas Spec 1.0. Enables agents to generate visual flowcharts, architecture diagrams, and planning boards. Use when creating or editing visual canvas files.

richfrem Bundle

Core markdown syntax skill for Obsidian. Enforces strict parsing and authoring of Obsidian proprietary syntax (Wikilinks, Blocks, Headings, Aliases, Embeds, Callouts). Use when reading, writing, or validating Obsidian-flavored markdown.

richfrem Bundle

Provides 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.

aretedriver Bundle

End-to-end release workflow — preflight checks, code review, changelog generation, version bump, tagging, and publishing. Coordinates release-engineer agent, code-reviewer persona, and github-operations agent through the WHY/WHAT/HOW framework.

zpankz Bundle

Formal constraint theory unifying deontic logic (P/O/F/I operators), Juarrero's trichotomy (enabling/governing/constitutive), Hohfeldian rights (claim-duty, privilege-noright, power-liability, immunity-disability), and category-theoretic composition. Use when modelling permissions, obligations, prohibitions, rights structures, agent authority, governance systems, ontology validation, or any domain requiring formal constraint specification. Integrates with ontolog via λ-calculus mapping.

zpankz Bundle

Lindy is an AI agent creation and management platform focused on business process automation. It enables organizations to build sophisticated AI-powered assistants that can handle communication across...

zpankz Bundle

Unified router for all external tools: CLI binaries, MCP tools via lootbox, and data processing. Consolidates cli-router + tools-router + data-router.

zpankz Bundle

Routes tasks to appropriate Task tool agents (subagents). Triggers on complex multi-step tasks, research, code review, exploration, or any task benefiting from specialized agent execution. Matches intent to agent types.

richfrem Bundle

Use 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.

gonzalezpazmonica Bundle

Usar cuando se añade pr-agent como juez externo en el Code Review Court.

aretedriver Bundle

Diagnoses why Gorgon workflows fail — reads checkpoint state, agent logs, budget traces, and output contracts to produce root-cause analysis

zpankz Bundle

Use this skill whenever the user wants high-quality semantic retrieval, cross-textbook synthesis, reference verification, or authority-ranked question answering over the PageIndex corpus. Trigger on requests like "find which texts cover X", "compare sources", "retrieve semantically", "verify this claim from my textbooks", "build a reading list from the corpus", "cluster by topic", or any PageIndex question where naïve filename search would miss relevant material. This skill teaches a state-of-the-art hybrid retrieval workflow over the PageIndex catalog and live MCP extraction surface.

zpankz Bundle

Unified router for agent delegation and skill routing. Absorbs agents-router + skills-router. Triggers on complex tasks, multi-step operations, research, exploration, or specialized skill needs.

zpankz Bundle

Orchestrate reliable multi-agent reasoning using MAKER (Maximal Agentic Knowledge Engine for Reasoning). Implements three-pillar architecture for transforming probabilistic LLM outputs into deterministic, verifiable results. Use when tasks require high reliability, parallel consensus voting, or systematic error detection. Triggers include reliability-critical tasks, multi-step reasoning chains, consensus-based verification, parallel agent execution, or explicit MAKER invocation.

gonzalezpazmonica Bundle

Usar cuando un agente debe enviar un mensaje a otro agente con roles y receipts, sin pasar por el usuario. Triggers: mensaje a otro agente, agent-message, notify agent, inbox.

gonzalezpazmonica Bundle

Usar cuando se lanza, supervisa o consulta un run autónomo (overnight-sprint, code-improvement-loop, tech-research-agent, SDD) y se necesita el ledger operativo con estado derivado. Triggers: 'registra el run', 'board de runs', 'estado del run', 'savia-runs', '¿en qué columna está mi run?', 'ci_failed', 'needs_input', 'merge_conflict'.

gonzalezpazmonica Bundle

Usar cuando hay un modelo nuevo disponible y se quiere detectar prompt debt en el workspace.

gonzalezpazmonica Bundle

Usar cuando se necesita investigación técnica autónoma sobre un tema específico.

gonzalezpazmonica Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

fusengine Bundle

Use when implementing input/output guardrails, writing ethical guardrail templates, or auditing an agent/prompt for missing security controls.

aretedriver Bundle

SAST + OWASP audit with LLM-triaged findings. Runs semgrep/bandit/gitleaks/pip-audit, filters false-positives, drafts remediation patches, persists SECURITY_FINDINGS.md with --diff for regression tracking. Use for security reviews, vuln scans, hardening, pre-pen-test prep.

aretedriver Bundle

Builds Claude Code plugins — shareable packages that bundle skills, hooks, MCP server configs, and agent definitions into a single distributable unit with plugin.json manifest. Use when creating, scaffolding, packaging, or publishing Claude Code plugins.

aretedriver Bundle

Extract effective prompts from the current session and save them to a reusable library. Captures prompts that worked well for future reference. Invoke with /prompt-library or /prompts.

gonzalezpazmonica Bundle

Revisión de contratos con matriz de riesgos RAG, red flags y resumen ejecutivo. Jurisdicción española.

zpankz Bundle

Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.

aretedriver Bundle

Builds and configures Model Context Protocol (MCP) servers — tools that extend Claude Code with custom capabilities like database access, API integrations, semantic search, and UI components. Use when creating MCP servers, configuring existing ones, debugging MCP connections, or designing tool interfaces for Claude.