d-o-hub

d-o-hub/github-template-ai-agents

Skill Claude CodeCodex

Research topics using web search to find accurate, current information. Use this skill when you need modern information, official documentation, best practices, or technical solutions beyond training data — even if they just say "look this up" or "search for how to do X". Not for do-web-doc-resolver, agent-browser.

d-o-hub/github-template-ai-agents

Agent Claude Code

Create new Claude Code agents with proper format, YAML frontmatter, system prompts, and tool configuration. Invoke when you need to build specialized sub-agents for autonomous task execution.

d-o-hub/github-template-ai-agents

Agent Claude Code

Multi-persona code analysis orchestrator using RYAN (methodical analyst), FLASH (rapid innovator), and SOCRATES (questioning facilitator) for balanced decision-making. Invoke for complex architectural decisions, trade-off analysis, comprehensive code reviews, or when avoiding single-perspective blind spots is critical.

d-o-hub/github-template-ai-agents

Agent Claude Code

Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies, or coordination of multiple specialized agents with quality gates and dynamic optimization.

d-o-hub/github-template-ai-agents

Agent Claude Code

Execute workflow agents iteratively for refinement and progressive improvement. Invoke when you need repetitive refinement, multi-iteration tasks (code review loops, incremental improvements), progressive optimization, or feedback loops until quality criteria are met or max iterations reached.

d-o-hub/github-template-ai-agents

Command Claude Code needs its repo

Create a conventional commit.

d-o-hub/github-template-ai-agents

Command Claude Code

Refactor code to improve quality and maintainability.

d-o-hub/github-template-ai-agents

Agent Claude CodeOpenCode needs its repo

Manage git worktrees for efficient multi-branch development. Invoke when creating worktrees for feature branches, organizing worktree directories, cleaning up unused worktrees, or implementing worktree-based workflows.

d-o-hub/github-template-ai-agents

Agent Claude CodeOpenCode

Edit and create GitHub Actions workflows and composite actions. Invoke when you need to create new CI/CD pipelines, modify existing workflows, ensure syntax correctness, or incorporate current best practices for GitHub Actions.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode

This command has been merged into git-github-workflow.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode

Unified atomic git workflow with GitHub integration - commits all changes, checks issues, creates PR, validates ALL Actions including pre-existing, uses swarm coordination with web research on failures.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode

This command has been merged into git-github-workflow.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode

Resume a previous session by loading state from plans/status.json and the specified handover reference.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode

Self-learning fix loop - commit, push, monitor CI, auto-fix failures using swarm agents with skills on demand, loop until all checks pass.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode

Swarm analysis of codebase for gaps - features, implementation, docs, evals, tests.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode

Execute swarm analysis with optimized web research in a git worktree - PR created automatically.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode needs its repo

Auto-update all documentation with command verification and link validation.

d-o-hub/github-template-ai-agents

Command Claude CodeOpenCode needs its repo

Verify all commands in markdown documentation with intelligent caching.

d-o-hub/github-template-ai-agents

Skill Claude CodeCodex

Diagnose failing builds and runtime errors with root-cause discipline. Use when a build, deploy, or service crashes, or an error appears at runtime — even if they just say "debug this crash" or "why does the server 502". Not for test-runner (failing or flaky tests in a suite), iterative-refinement (repeat-until-pass…

d-o-hub/github-template-ai-agents

Skill Claude CodeCodex

Perform routine, low-risk dependency version bumps and vulnerability-driven upgrades (patch/minor, or major with no source changes). Use when updating packages, action pins, pre-commit hooks, lockfiles, or base images — even if they just say "bump lodash" or "fix this CVE". Not for migration-refactoring (major bumps…

d-o-hub/github-template-ai-agents

Skill Claude CodeCodex

Remediate a live production failure through a gated loop: reproduce the failure, generate a candidate fix, evaluate it, red-team it adversarially, then shadow, canary, and promote or roll back on SLO verdicts. Use when production is degraded and the fix must itself be proven safe, or when the user is already…

d-o-hub/github-template-ai-agents

Skill Claude CodeCodex

Own the secret lifecycle: detect leaked secrets, rotate them, and store them correctly. Use when handling API keys, tokens, or credentials — even if they just say "rotate this key", "where do I put this secret", or "this key is hardcoded". Not for privacy-first (email/PII lint), general vulnerability audits (use…

d-o-hub/github-template-ai-agents

Skill Claude CodeCodex

Diagnose and safely isolate nested build, test, and coverage subprocesses (e.g., Cargo running inside cargo test, cargo llvm-cov, or cargo nextest) that fail due to inherited environment variables, target directory collisions, compiler flags, or generated .profraw litter. Use this skill when subprocess builds fail…