Skills

Isolated Codex goal-loop skill that combines spec-to-plan, goal-loop-native phase planning, and gated phase-by-phase execution. Use when the user asks to turn a spec into a goal-loop plan, run a goal-loop plan, or package the spec-to-goal-plan, goal-loop-planner, and goal-loop flow as one Codex skill. Planner work uses GPT-5.4 high, implementation and gate-fix subagents use model 5.5 high, and review gates use model 5.4.

Autonomous phase-by-phase plan execution loop. Plan-subagent decomposes each phase into a dependency-tagged wave graph, parallel Opus sub-agents implement via the inlined orchestrator pattern (main thread plans/synthesizes, sub-agents do all edits), advisor + /code-review --effort extra-high + the inlined review-swarm protocol gate every phase, IMPLEMENTATION_NOTES.md captures off-spec decisions. Self-contained — orchestrator and review-swarm protocols ship inline as references, no third-party skill dependencies. Use when the user invokes /goal-loop <plan-path>, when /goal hook fires with a goal-loop directive, or when the user wants autonomous phase-by-phase execution of a markdown plan file. Pairs with goal-distill (which produces compatible plan prompts).

Distill the current session — conversation, decisions, corrections, repo state, and recent history — into a single paste-ready /goal prompt that drives an autonomous phase-by-phase loop (decompose → Plan-subagent on Opus → main-thread execute → re-measure → repeat) until the success criterion is met or a stop condition fires. Universal — works in any repo, writes no files. Copies the prompt to the clipboard on macOS. Use this whenever the user says "distill goal", "distill this session", "goal-distill", "reconstruct goal", "rebuild the spec", "rebuild the masterplan", "give me a /goal", "phase-by-phase to the goal", "loop until done", "iterate toward the goal", or "turn this into a /goal prompt I can paste later" — and prefer it even when the user doesn't name the skill but clearly wants this session compressed into a runnable prompt for a future agent.

Deep strategic analysis of a project to identify the single highest-leverage, most innovative addition. Use this whenever the user asks what to build next, what the most impactful improvement would be, what the "next big thing" is for their project, what's the smartest thing to add, or any question about strategic direction and priorities. Also trigger when the user seems stuck choosing between competing features, is evaluating what matters most, or asks open-ended questions like "what would you do with this project?" or "what am I missing?"

Enter orchestration-only mode where Claude plans, delegates to sub-agents, and synthesizes results instead of implementing directly. Use whenever the user says they want to act as tech lead, wants Claude to orchestrate, wants sub-agents to do the work, says things like "you orchestrate, I brainstorm", "don't code yourself", "delegate this", "break this up and dispatch it", or explicitly invokes /orchestrator. Also use when the user frames the session as brainstorming-to-spec-to-delegation and wants Claude to stay out of the implementation seat.

Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures. Use when the user asks to investigate a bug, find the root cause, trace a regression, understand why something broke, or wants a ranked diagnosis with the fastest proof path without making code edits.

Parallel read-only multi-agent review of a current git diff or explicit file scope to find behavioral regressions, security or privacy risks, performance or reliability issues, and contract or test coverage gaps. Use when the user asks for a review swarm, parallel review, diff review, regression review, security review, or wants high-signal issues plus a prioritized fix path without editing files.

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data — including interactive Mermaid diagrams with auto-playing source→target flow animation, hover-to-trace the full upstream+downstream chain, and tap-to-pin a node + open its detail panel. Use when the user asks for a diagram, architecture overview, diff review, plan review, project recap, comparison table, or any visual explanation of technical concepts. Also use proactively when you are about to render a complex ASCII table (4+ rows or 3+ columns) — present it as a styled HTML page instead.

Use when the user asks to consult ChatGPT Pro, ask chatgpt.com, get an external ChatGPT second opinion, have GPT Pro review a plan, codebase, diff, design, architecture, bug, or "ask your big brother" through the Codex in-app browser. This skill uses browser-use:browser with the iab backend, prepares an allowlisted sanitized review packet, shows the exact packet and visible ChatGPT account/workspace for approval, submits it to chatgpt.com only after approval, then validates the external advice against local evidence before recommending changes.

Use when the user asks to consult ChatGPT Pro, ask chatgpt.com, get an external ChatGPT second opinion, have GPT Pro review a plan, codebase, diff, design, architecture, bug, or "ask your big brother". This skill builds an allowlisted sanitized review packet, shows the exact packet and active ChatGPT account/workspace for approval, uses Computer Use to operate the user's desktop browser at chatgpt.com, then validates the external advice against local evidence before recommending changes.

Generate beautiful, self-contained HTML blueprint pages that visually plan implementations with architecture diagrams, phased task breakdowns, file change maps, dependency graphs, risk matrices, and verification checklists. Use this skill whenever the user asks for a blueprint, implementation plan, feature spec, architecture plan, project plan, or says things like "plan this out visually", "blueprint this feature", "give me a full plan", "create a spec for X", or "how should I build X". Also use proactively when the user describes a non-trivial feature or change that would benefit from structured planning before implementation -- especially multi-file changes, architectural decisions, or cross-cutting concerns. Even if the user doesn't say "blueprint", if the work is complex enough to warrant a plan, offer to generate one.

Disciplined bug-fix-and-lock-down workflow: catalog every issue, fix each one with verification, then create comprehensive e2e integration tests that would have caught each fixed issue plus similar failure modes. Use this skill whenever the user has just identified multiple bugs or problems to fix, wants to fix everything systematically without losing track, or wants regression test coverage after fixes. Trigger on phrases like "fix all of that", "fix absolutely everything", "keep a TODO list of all items", "make sure this can't happen again", "write tests for what we just fixed", "add regression tests", "lock down these fixes", "create a test safety net", "write e2e tests for these fixes", "don't lose track of anything", or any request that combines thorough bug-fixing with regression prevention. Also trigger when the user asks to "fix and verify" multiple issues, wants granular tracking of fix progress, or says things like "I need you to fix each of those problems and then write tests so this never happens

Deep codebase audit that first reads project docs (AGENTS.md, README.md) and investigates the architecture, then systematically finds hardcoded constants that should be dynamic and unfinished code (TODOs, "will"/"would" in comments). Use this skill when the user wants a thorough code review for hygiene issues, asks to find hardcoded values, wants to audit for TODOs or incomplete code, says things like "audit this codebase", "find hardcoded stuff", "what's unfinished", "find tech debt", "code hygiene check", or asks you to look across the whole project for issues. Also use when the user asks to understand a project before making changes, or wants a comprehensive health check of their codebase.

Review a git diff or explicit file scope for reuse, code quality, efficiency, clarity, and standards issues, then optionally apply safe Codex-driven fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes", or "run simplify".

Generates AGENTS.md file using the WHAT/WHY/HOW framework. Explores the codebase and produces a minimal (<100 line) context file with progressive disclosure.