Codex Auto Pilot
codexThin guidance for fully verified release-ready PRs or proven production delivery.
2 skills
Tom Tang's maintained agent skills for engineering and product work
Plugin tomstack-skills from marketplace tomstack in tombelieber/tomstack. Commands read from the repo's manifest — 21 days ago.
auto-pilotFinish one approved software goal at exactly one of two successful boundaries: PR_READY, meaning the open candidate is fully production-release-ready and only the production action remains; or SHIPPED, meaning the exact candidate is live and proven in production with zero scoped leftovers. The invok
batch-grill-meInterview unresolved product or architecture decisions in dependency-ordered question batches.
impact-aware-qaSelect repository checks for a change's actual impact, including required commit, merge and release gates.
ui-mr-visual-reviewPrepare or review any UI-related pull request or merge request with comparable Before/After screenshots embedded in its description, so a human can see every material visual change. Apply during UI implementation and PR/MR creation or updates, including layout, styling, copy, responsive behavior and
backupManage Claude Code backups — sync config and sessions, list/restore sessions, check status. Use when the user asks about backups, restoring sessions, or migrating their Claude environment.
chatgpt-share-dumpDump ChatGPT shared conversations from https://chatgpt.com/share/... into agent-readable archives. Use when a user gives an AI agent a ChatGPT share link and asks it to continue, analyze, test, migrate, summarize, implement from, or preserve the full transcript as Markdown, JSON turns, current-state
claude-clean-rebornUse when a user wants guided local Claude Desktop, Claude Code, or browser cleanup before a legitimate fresh sign-in, especially across Chrome profiles or with persistent Claude extension cookies.
cleanupScan and kill orphan dev processes (storybook, esbuild, vite, next, etc.) left behind by AI agent sessions. Use when the user mentions slow machine, hot CPU, orphan processes, or asks to clean up dev processes.
first-principles-xy-problemsFrame ambiguous product, strategy or architecture problems before choosing a solution; design-only.
pain-point-miningMine real chats, support logs or transcripts for evidence-backed customer pain points and product decisions.
product-demo-studioBuild product demo batches, review alternative demos, and iteratively polish a selected demo through an interactive requirements interview.
Thin guidance for fully verified release-ready PRs or proven production delivery.
2 skills
Kill orphan dev processes left by AI agent sessions
1 skill · hooks
Interactive overview of real application pages, states and flows
1 skill
Back up and restore your Claude Code environment
1 skill
Dump ChatGPT share links into agent-readable transcript archives
1 skill
Mine real transcripts into ranked product pain points and requirements
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Use Alibaba Open Code Review from local Codex.
2 skills
Binary reverse engineering, malware analysis, firmware security, and software protection research for authorized security research, CTF competitions, and defensive security
4 skills · 3 agents
Long-term semantic memory for Claude Code, powered by OpenViking
5 skills · 1 command · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.