d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Orchestrates the full git-to-merge lifecycle: validate → commit → check issues → create PR → monitor ALL GitHub Actions (including pre-existing failures) → fix via swarm/web research → merge with strategy selection → post-merge validate. Use this skill when the user asks to ship changes end-to-end, manage a PR through…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Monitor a GitHub pull request until it's merged, green, or blocked. Polls CI checks, review comments, and mergeability state continuously. Use this skill when the user asks to monitor a PR, watch CI, handle review comments, sentinel a PR, babysit a PR, or keep an eye on failures and feedback — even if they just say…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Orchestrates complex multi-step tasks with intelligent planning: analyze the problem, decompose into sub-goals, select execution strategy, assign agents, and coordinate with quality gates. Use this skill when the user asks to plan a large change, break down a complex problem, coordinate multiple agents, or…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Execution agent skill focused on implementing changes based on an approved Blueprint. Use this skill when implementing targeted, atomic code changes once the plan is solid — even if they just say "implement this" or "make the changes". Gated by human or primary agent approval of the implementation strategy.
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Classify user intents and route to appropriate skills, commands, or workflows. Use when determining which skill to invoke, routing requests to specialized agents, or building skill selection logic. Trigger on 'which skill should I use', 'route this to', 'classify this request', 'skill selection', or when multiple…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Execute iterative refinement workflows with validation loops until quality criteria are met. Use this skill when running test-fix cycles, code quality improvement, performance optimization, or any task requiring repeated action-validate-improve cycles — even if they just say "keep improving until it passes" or…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Use this skill to delegate complex coding tasks by creating Jules sessions via the Jules CLI. Use this skill when the user asks to delegate a coding task to Jules, create a Jules session, or hand off implementation work — even if they just say "send this to Jules" or "let Jules handle it". Jules is an AI coding agent…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Extract non-obvious session learnings, patterns, and discoveries into scoped AGENTS.md files. Use this skill when the user wants to extract learnings after completing non-trivial tasks, or when they say "extract learnings", "save patterns", "update AGENTS.md", or whenever the session has produced insights that should…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Manage application lifecycle, error handling, and resource cleanup to prevent memory leaks and ensure stability. Use this skill when handling startup/shutdown sequences, managing resource pools, implementing error boundaries, preventing memory leaks, or ensuring graceful degradation — even if they just say "clean up…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Retrieve semantically relevant past learnings, analysis outputs, and project context using the csm CLI (HDC encoder with hybrid BM25 retrieval). Use this skill when the user needs context retrieval, past session memory, learning recall, or wants to query the memory system for relevant documents or patterns — even if…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Automate complex code migrations and refactorings with safety patterns. Use this skill when upgrading dependencies, migrating frameworks (React class→hooks, Flask→FastAPI), modernizing languages (Python 2→3), or performing large-scale refactories — even if they just say "migrate this" or "refactor the whole thing".…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Prevent email addresses and personal data from entering the codebase. Use this skill when the user asks to prevent emails, remove personal data, run a privacy check, scan for PII, or ensure no email addresses leak into source code or documentation — even if they just say "no email" or "check for personal data". Not…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Design Cache Storage + IndexedDB strategy and sync queue. Use this skill when building service workers, implementing caching strategies, or investigating offline bugs — even if they just say "make it work offline" or "add caching". Generic pattern for any offline-first application. Not for lifecycle-management.
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Build localized, accessible reader/admin UI with responsive layouts, telemetry, and state management. Use this skill when building React screens, polishing UX, or implementing responsive layouts for reader or admin interfaces — even if they just say "fix the UI" or "make it responsive". Generic pattern for any…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Create, audit, and improve GitHub README.md files following 2026 best practices. Use this skill when a user asks to write, rewrite, or review a README.md for a GitHub repository, add shields.io badges, create a project SVG logo, improve documentation structure, or make a repository more discoverable and professional …
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Implement access control, authentication, and authorization patterns. Use this skill when building auth endpoints, managing permissions, implementing session/token logic, or generating signed URLs — even if they just say "add auth" or "secure this endpoint". Generic template adaptable to any project's auth needs. Not…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Perform security audits on code to identify vulnerabilities, misconfigurations, and security anti-patterns. Use when users ask to 'audit', 'review', or 'check security' of code, configurations, or repositories — even if they just say "check for security issues" or "is this secure". Trigger on keywords like 'security…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Lint and test shell scripts using ShellCheck and BATS. Use this skill when checking bash/sh scripts for errors, writing shell script tests, fixing ShellCheck warnings, setting up CI/CD for shell scripts, or improving bash code quality — even if they just say "fix this script" or "add tests for the shell script". Not…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.…
d-o-hub/github-template-ai-agents
Agent Codex
Analyze benchmark results from the eval pipeline to surface actionable patterns for skill improvement.
d-o-hub/github-template-ai-agents
Agent Codex
Blind comparison of two skill versions to determine which produces higher quality outputs.
d-o-hub/github-template-ai-agents
Agent Codex
Grade eval assertion results against actual skill outputs. Expects structured input and returns deterministic pass/fail with concrete evidence.
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Reusable skill for evaluating other skills with structure checks, eval coverage review, and real usage spot checks. Use when you need to check a skill, add evals, benchmark a skill, validate outputs against assertions, or compare current skill behavior against a baseline — even if they just say "evaluate this skill"…
d-o-hub/github-template-ai-agents
Skill Claude CodeCodex
Triage and fix static analysis findings across any programming language. Use this skill when running linters (ruff, eslint, clippy, shellcheck), analyzing lint output, fixing warnings or errors, or managing cross-language static analysis results in a project — even if they just say "run the linter" or "fix the lint…