Total 50,527 skills, AI & Machine Learning has 8481 skills
Showing 12 of 8481 skills
Maintain a structured ledger of decisions, discovered bugs and fixes, user preferences, constraints, current status, and failed approaches throughout multi-step agentic tasks. Auto-update after every significant step. Triggers on "where were we", "continue", "summarize status", "remember", or when a new agent instance takes over a task.
Implement feature tasks using AI agents in logical batches, track completion status, identify blockers, and manage task handoffs. Use when you have an execution sequence and need AI agents to build tasks while maintaining progress tracking.
Controls InnerClaude instances on Sprites.dev VMs for testing workflows, install patterns, and Claude-to-Claude interaction. INVOKE BEFORE any 'sprite exec', 'inner Claude', 'test this workflow', 'Claude controlling Claude', or remote VM operations. Documents the critical tmux+pipe-pane pattern that makes OuterClaude/InnerClaude interaction work. Also covers checkpoint/restore and bootstrap. (user)
Reference guide for Agentica multi-agent infrastructure APIs
Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination
Parallel Agent Type Contracts
Use when about to ask the user a factual question, propose a solution, diagnose an error, or choose between approaches. Triggers on: 'Do you have X installed?', 'What version?', 'Is X configured?', 'We should...', 'The fix is...', 'Options: 1...', 'Based on my understanding...', 'I believe X supports...'. Before deciding anything, spin up parallel subagents to WebSearch for current docs, community solutions, framework best practices, and GitHub issues. Your memory is stale — verify everything.
Use when parameter values appear in multiple documents and consistency must be verified, especially for quantitative values that may differ due to measurement context or require reconciliation
MANDATORY before starting any task. Enforces the GPA execution loop that prevents tool call sprawl. G: GATHER phase combines discover queries + memory reads + file reads into one phase. P: Plan in text with zero tool calls. A: APPLY all writes/edits/verification in one phase. One call per tool type per phase — batch all same-type operations together. Covers dependency analysis, batch opportunities, scope estimation, and loop-back triggers.
Use when substantive documents (reviews, analyses, synthesis documents) need adversarial review to strengthen arguments, identify weak points, and challenge assumptions before editorial polish (mandatory for Writer → Devil's Advocate pairing protocol)
Create effective skills for OpenCode agents. Load FIRST before writing any SKILL.md. Provides required format, naming conventions, progressive disclosure patterns, and validation. Use when building, reviewing, or debugging skills.
Ensure AI agents work in an isolated Git worktree to prevent changes to the main working directory. Use when AI is about to make its first code modification in a session, or when the user requests isolated/safe editing. Triggers include starting to edit files, implementing features, or fixing bugs.