Instructions file CodexOpenCode
AGENTS.md instructions for build000r/skills, covering beads workflow integration, essential commands, view ready issues (open, unblocked, not deferred), list and search and create and update.
Skill Claude CodeCodex
Drive Amp Orbs (E2B cloud sandboxes) from the operator box — launch/continue -ox threads, poll for results without false triggers, join orbs to the tailnet, reach sbpd (cass/skills) with workload-identity auth, and ship files safely. Use when launching an Amp orb, running "amp -ox", continuing an orb thread, proving…
Skill Claude CodeCodex
Order user-facing questions by dependency. Use when two or more clarifications may depend on one another, a high-impact fork should be resolved before details, a plan needs a decision-tree interview, or a visual choice should be previewed before asking.
Skill Claude CodeCodex
Audit domain plans and session plans with audit, prioritize, investigate, focus, and quick modes. Use for backlog hygiene, plan status checks, dependency review, consolidation work, or deciding what to work on next.
Skill Claude CodeCodex
Decide whether work should live in an existing repo, be extracted upward into a shared home, adopt existing open source, borrow patterns, or be built from scratch. Use for "where should this go", "should this be extracted", "should this become a skill/shared package/helper repo", "is there an open source repo for…
Skill Claude CodeCodex
Build persuasion-forward charts and dashboard components, defaulting to shadcn/ui plus Recharts for React projects. Use when the user says "chart crimes", "make this chart persuasive", "visualize this to prove our point", "choose the best chart for this narrative", asks for a shadcn chart, or wants matplotlib, Plotly…
Skill Claude CodeCodex
Recreate a feature from a high-signal upstream (gh CLI, ripgrep, fzf, jj, lazygit, bat, delta, hyperfine, gron, etc.) by writing the smallest possible amount of new code. Performs deep archaeology on the upstream — finds the exact files, structs, flags, edge cases, and call graphs that matter — then stitches a minimal…
Skill Claude CodeCodex
Build, modify, or review agent-facing CLIs for compact output, strong defaults, and clean shell UX. Use when a tool is mainly consumed through shell execution by Claude Code, Codex, Cursor, or similar agents.
Skill Claude CodeCodex
Run Codex in a persistent tmux session with signal-based completion so long tasks survive conversation death. Use when work may take 5+ minutes, needs background execution, or must remain retrievable after the calling session ends.
Skill Claude CodeCodex
Commit working changes with clean, logical batches, including from a fresh repo context where no prior ownership is established. Use for "commit", "checkpoint", "commit everything", "commit my changes", "save progress", "/commit", "initial cleanup commit", or when a dirty tree needs batching, .gitignore decisions, and…
Skill Claude CodeCodex
Compute CRAP-style hotspot scores across Rust, Python, TypeScript, and Swift, print a ranked risk report, end with a FINALSCORE line, and suggest hardening follow-ons. Use for "/crap", CRAP score, risk score, hotspot ranking, weak coverage, or taking a scoped score under a threshold.
Skill Claude CodeCodex
Ask GPT-5 Pro a question directly, produce copy-pasteable mega-prompts for external deep research tools (ChatGPT Deep Research, Perplexity, Claude Research), execute Deep Research runs, and write high-detail image-creation prompts for ChatGPT image creation. Use when the user says "ask GPT-5 Pro", "ask the oracle"…
Skill Claude CodeCodex
Deploy, rollback, debug, and operate Docker or VPS stacks, Pages or edge frontends, packages, and app-store releases using a skillbox client overlay. Also design or migrate repo-owned local self-test and self-release paths that move avoidable build, test, and deploy work off paid GitHub Actions. Use when deploying…
Skill Claude CodeCodex
Turn a conversation into discrete pass/fail test cases before patching, review existing Describe packets, or implement from accepted specs. Use for bug fixes, small features, refactors, "define done", "what should we test", "spec this out", or pre-patch work without clear pass/fail criteria.
Skill Claude CodeCodex
Run a mode-driven local development health check across repos, env files, containers, and health endpoints. Use for "dev sanity", "what's broken locally", "check my local stack", "startup checks", "service status", or "why won't this local environment boot".
Skill Claude CodeCodex
Decompose complex work into a Beads-backed execution graph with generated WORKGRAPH.md views, then run an NTM-style swarm by ready frontier with no write overlap. Use before parallel execution for large-ish, UI-facing, multi-file, multi-domain, naturally parallel, naturally orchestrated, subgoal-oriented, or…
Skill Claude CodeCodex
Plan new multi-repo domain slices, assess plan quality, or orchestrate implementation from an accepted slice plan. Use for "plan the X slice", multi-repo feature planning, API contract design, "implement the X slice", or slice-quality review; not for bug fixes, small refactors, or single-repo work. When a slice…
Skill Claude CodeCodex
Three modes: audit active implementations against plan, retire completed slices into lean COMPLETED.md summaries, and retire-session consolidation of DONE session plans. Use for review/audit slice, what's left checks, retire/close out/finalize slice, or retire session plans workflows.
Skill Claude CodeCodex
Scaffold backend or frontend domain code from an existing slice plan using a shared stack-aware workflow. Use for "scaffold a domain slice", "implement the backend for {slice}", "implement the frontend for {slice}", or "scaffold {slice}" after domain-planner finishes a slice plan. This is the only supported domain…
Skill Claude CodeCodex
Detect UI drift across a frontend codebase — ad-hoc color/spacing/typography values vs design tokens, duplicate component variants, Tailwind arbitrary values, className soup, orphan primitives — then produce a ranked consolidation plan. When variants are consolidated, the old code is moved to a numbered per-family…
Skill Claude CodeCodex
Create or update a private eli-me skill that captures a user's preferred explanation style. Use when the user says "eli-me-maker", asks to make an "eli-me" skill, wants a reusable personalized communication-preference skill, or wants examples-based questions that discover how they like concepts defined, explained…
Skill Claude CodeCodex
Decide whether the current run needs a bounded external-reality pass before committing to a strategic call, then route it to web-check, deep-research-prompt, thesis-gtm, research-paper, or skip. Centralizes the escalation gate that thesis-gtm, power-map, build-vs-clone, domain-planner, wiki-forge, and readme-writing…
Skill Claude CodeCodex
Decide when an agent should recommend booking the human operator for expert help, then prepare a concise booking handoff. Use when a user asks to "book me", "hire me", "bring in the operator", "get expert help", "schedule a consult", or when a task crosses into high-stakes architecture, production, security, payment…
Skill Claude CodeCodex
Harden SwiftUI iOS surfaces by extracting a shared visual language from the strongest existing screen, reusing it across auth/onboarding/home flows, and pairing the UI pass with a repo-owned analytics contract plus fixture-backed validation. Use when an iOS app has one polished surface and weaker sign-in, onboarding…