Agent skills

The judgment layer for operating as a principal's trusted agent — how to think and behave, not which rule applies.

Meta-skill that orchestrates all agents of the ecosystem.

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

Agent skill for performance-optimizer - invoke with $agent-performance-optimizer

Audit and sync agent instruction files across all coding agent formats.

Create, edit, validate, and run Agent QA tests, suites, and hooks through MCP or CLI while preserving canonical IDs and schema contracts.

Debug, patch, and verify failed Agent QA runs from MCP evidence, artifacts, logs, and local code without hiding product or infrastructure…

Establishes and audits agent-first repository architectures using minimal AGENTS.md routers, nested rules, and single-source-of-truth…

Aggregates, reconciles, and finalizes multi-agent engineering task results into comprehensive project-level integration reports.

Agent skill for safla-neural - invoke with $agent-safla-neural

Agent skill for scout-explorer - invoke with $agent-scout-explorer

Use when: (1) Starting a long-running experiment that may span multiple sessions/disconnects, (2) Resuming work after a break and needing…

Concludes AI development sessions by updating status docs, generating devlogs, and making a final local Git commit.

Shared workflow for editing Langfuse's repo-owned agent setup under `.agents/`.

How to write effective agent skills — what to do, what not to do, anatomy, progressive disclosure, design patterns, anti-patterns…

Reference for the Agent Skills format specification (agentskills.io)

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY…

Verify supply chain integrity for AI agent plugins, tools, and dependencies.

Download a small corpus of open-access arXiv survey/review PDFs about agentic systems and extract text for style learning.

Agent skill for swarm - invoke with $agent-swarm

Tracks per-agent token usage and flags waste in parallel dispatch.