ai-skills

Intelligent CI failure diagnosis and guided remediation for GitHub Actions, GitLab CI, and local builds

Pre-execution mapping of codebases, document collections, or problem spaces. Runs BEFORE any Gorgon workflow to give all agents shared situational awareness

Investigative methodology for analyzing document collections — provenance analysis, anomaly detection, redaction detection, and cross-document validation

Resolves entity ambiguity across document corpora — fuzzy name matching, alias detection, identity consolidation, and confidence-scored entity merging

Packages project state into structured context documents for agent sessions, human pickup, or Quorum IntentNodes

Teaches agents how to publish well-structured intents for Convergent's intent graph — schema, quality criteria, and authoring patterns

Automates the last mile of shipping software — verifies release readiness, generates changelogs, tags versions, and pushes releases

Systematic technical debt assessment — scans for security issues, correctness gaps, infrastructure debt, maintainability problems, documentation quality, and dependency freshness

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

Fetch and parse web content with ethical scraping practices, rate limiting, and structured extraction

Search the web for information with rate limiting, caching, and structured source attribution

Compose and send emails with safety controls, draft-review-approve workflow, and SMTP delivery

Authenticated HTTP API client with retry logic, rate limiting, response parsing, and structured error handling. Supports OAuth2, API key, and bearer token auth.

Repository management through Git CLI and GitHub API with branch protection, commit conventions, and security controls

Designs and coordinates Claude Code Agent Teams — multi-agent collaboration where teammate sessions work in parallel with direct communication, task claiming via file locks, and cross-referencing findings

Hierarchical multi-agent orchestration supervisor that decomposes tasks, delegates to specialized worker agents, tracks state, and employs triumvirate consensus for high-stakes operations

Safe filesystem operations with path protection, backup enforcement, and audit logging

Execute and manage subprocesses with timeout, output capture, and safety controls. Blocks dangerous commands, enforces resource limits, and returns structured results with exit codes, stdout, stderr, and timing.

REST and GraphQL API testing — contract validation, load testing, regression suites, and endpoint verification

Database operations — schema design, migration authoring, query optimization, and SQL/ORM patterns

OAuth and API authentication — OAuth 2.0 flows, PKCE, token lifecycle, JWT validation, and provider integration

Webhook architecture — payload design, retry strategies, HMAC signature verification, and event-driven patterns

Designs CI/CD pipelines that integrate Claude Code in headless mode for automated code review, test analysis, deployment gating, and PR triage. Use when building GitHub Actions workflows, GitLab CI pipelines, or any automation that uses Claude Code non-interactively via `claude -p` or the Agent SDK.

Log high-leverage decisions from the current work session to the Arete Decision Log. Extracts architecture, UX, scope, tooling, and philosophy decisions. Invoke with /decision-log or /adl.

Designs Claude Code hooks — lifecycle event handlers (PreToolUse, PostToolUse) that enforce quality gates, block dangerous operations, auto-lint, run tests before commits, and log tool usage. Use when creating, debugging, or configuring Claude Code hooks for automated enforcement and workflow automation.

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.

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.

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.

Sets up Claude Code security hooks — protective PreToolUse guards that block sensitive file access, dangerous commands, destructive git ops, system path writes, network calls, and permission changes. Includes 7 ready-to-deploy hook scripts.

Cross-session continuity for Claude Code — resume context, structured handoffs, session history tracking

Manages Claude Code's persistent memory system — auto-memory files, cross-session context, project memory directories, and task handoff protocols. Use when organizing session memory, creating handoff documents, managing MEMORY.md files, or establishing continuity between Claude Code sessions.

Performs statistical analysis, finds patterns, and generates insights

Handles data collection, ingestion, cleaning, and pipeline design

Creates charts, dashboards, and visual representations of data

Creates executive summaries, reports, and documentation of findings

Backup strategy design, data integrity verification, and disaster recovery planning. Invoke with /backup.

Build and install the project in development mode. Handles venv creation and editable installs. Invoke with /build.

Generate Changelog from Commits

GitHub Actions Workflow Generator

Create well-formatted git commits with conventional commit style. Analyzes staged changes and generates appropriate commit messages. Invoke with /commit or after completing a task.