Skill Authoring Toolkit

Guides users through creating effective skills that extend AI coding agents with specialized knowledge, workflows, and tool integrations.

Guides the design and structuring of workflow-based Claude Code skills with multi-step phases, decision trees, subagent delegation, and progressive disclosure.

Provides a structured process for creating or updating skills that extend an AI agent's capabilities with specialized knowledge, workflows, and tool integrations.

Design a new PM skill through guided conversation, from raw idea to a structured, repo-compliant SKILL.md draft.

Turn rough notes, workshop content, or prompt dumps into compliant, publish-ready SKILL.md files that pass validation and integrate with repo documentation.

Decides when to delegate to compressed-output subagents (investigator, builder, reviewer) instead of using vanilla agents, saving main-context tokens across long sessions.

Drafts structured goal-loop prompts for long-running agent work with verifiable stop conditions, validation commands, and documentation requirements.

Coordinates a squad of specialized agents for software development, routing tasks and managing context across requirements, planning, architecture, implementation, review, testing, and deployment phases.

Guides the creation of MCP servers that enable LLMs to interact with external services through well-designed tools.

Scaffolds a per-task verification skill for a repo, including a dev-local launcher, a browser driver, and a verification SOP that spawns a sub-agent to drive the app and produce proof.

Audits a project's agent configuration files, establishes a source-of-truth skills directory, normalizes naming, and generates bridge files to make the workspace consistent across Claude Code, Codex, Grok, and generic Agents.

Analyzes past agent sessions to identify recurring failures and skill gaps, then automatically creates or patches skills and runs self-evolution to fix them, tracking improvement over time.

Provides cross-harness memory for agents by maintaining a local memex and offering commands to query, record, and check status across sessions.

Provides a structured template for creating new agent skills, including workflow steps, input/output schemas, and quality gates.

Manages persistent coding sessions across multiple AI coding engines including Claude Code, Codex, Antigravity, Cursor, and OpenCode, with support for multi-agent councils, cross-session messaging, deep planning, parallel code review, and autonomous workspace iteration.

Creates cross-platform agent skills from workflow descriptions, files, URLs, or screenshots. Supports single skills, multi-agent suites, template-based creation, cross-platform export, spec validation, and security auditing of third-party skills before install.

Consolidates 89 high-integrity SOPs for the Full department of the Galyarder Framework, covering adapter creation, execution protocols, and multi-agent hygiene.