Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku", "optimize for Haiku", "make this work on Haiku", "generate Haiku instructions", or needs to delegate a task to a smaller model with high reliability.
Discover and load skills on demand from /mnt/skills/user/. Use when you need a capability but don't know which skill provides it, when the boot-emitted skill list is names-only and you need a full description, or when you want to list the catalog. Verbs are list (names only), search (rank by name/description match against a query), and show (emit the full SKILL.md for a named skill).
Disciplined, validation-gated revision of an EXISTING skill so each edit is a measured improvement rather than a guess. Use when editing, revising, or tuning a skill that already exists and there is evidence it underperforms (observed failures, drift, complaints) — invoke by name, or have versioning-skills / creating-skill defer to it before applying edits. Not for authoring a brand-new skill from scratch (use creating-skill) or one-off prose.
Orchestrates parallel API instances, delegated sub-tasks, and multi-agent workflows with streaming and tool-enabled delegation patterns. Use for parallel analysis, multi-perspective reviews, or complex task decomposition.
Skill-aware orchestration with context routing. Decomposes complex tasks into skill-typed subtasks, extracts targeted context subsets, executes subagents in parallel, and synthesizes results. Self-answers trivial lookups inline. No SDK dependency — uses raw HTTP via httpx. Use when tasks require multiple analytical perspectives, when context is large and subtasks only need portions, or when orchestrating-agents spawns too many redundant subagents.
Creates new Margin Eval test suites from scratch. Use this skill whenever the user wants to author, build, or scaffold a new eval test suite, define test cases for evaluating coding agents, or create tasks with Dockerfiles, prompts, and grading scripts for the Margin Eval framework.
Use when removing installed skills from the central repository, especially when cleaning unused community skills, deleting a whole bundle group, or ensuring platform links and installed-skills indexes are cleaned up consistently.
Use IMMEDIATELY at session start, before responding to any user message about software development, feature additions, bug fixes, code reviews, or anything that could be done with SDDPro framework commands. Loads the canonical SDDPro pipeline overview, the 13 user-facing commands, and the agent ownership model so subsequent responses route through framework conventions instead of ad-hoc coding.
Write effective instructions for Claude: project instructions, standalone prompts, and skill content. Use when users need help writing prompts, setting up project instructions, choosing between instruction formats, or improving how they communicate with Claude. Covers writing principles, model-aware calibration, and format selection. For building and testing complete skills, use skill-creator instead.
Agent roles, safety rules, file ownership, and cross-package change protocol. Use when AI agents work on this codebase, plan multi-package changes, or need boundary guidance.