Skill Claude CodeCodex
Surface what I think we're doing before acting on it. Use when the user invokes the align skill, says "let's align first", "check in before you start", or "mirror what you're hearing". Also invoke before starting any task with real interpretive weight. An ambiguous request, a vague spec, a "build X" with the details…
Skill Claude CodeCodex
Surface and resolve underspecified decisions before designing. Use after task interpretation and terrain mapping, when you've understood what's being asked AND what's already there but still need user input on judgment calls. Boundaries and scope, edge behavior, trade-offs and calibration, integration with…
Skill Claude CodeCodex
Generate multiple strong design options with explicit tradeoff profiles. Use when the user invokes the design-options skill or asks "what are my options", "how should we approach this", "design this", "what's the architecture", "propose some approaches", or "give me options". Also trigger proactively during the Design…
Skill Claude CodeCodex
Drive a browser with Playwright as a dual-mode superset. Resilient locators/selectors for debugging your own web app (exact DOM, sub-second timing, CSS-media emulation) and a vision/coordinate loop (screenshot → click x,y → type) for genuinely opaque UI on unknown or messy real sites. Use whenever you actually drive a…
Skill Claude CodeCodex
Map the terrain before designing. Use before any substantive design or planning step. Codebase changes, doc drafting, strategy decisions, anything with non-trivial structure. Trigger when the user invokes the explore skill, says "explore first", "what's already there", "map the codebase", or "survey the landscape".…
Skill Claude CodeCodex
Write a durable handoff for work that's about to ship. Structured PR descriptions, summaries, memos, or memory notes about completed work. Use when creating a PR, wrapping up a session, writing a project summary, drafting documentation about what was built, or composing memory notes for future sessions. Trigger when…
Skill Claude CodeCodex
Systematically identify how a plan, design, or decision could fail before committing to it. Trigger when the user invokes the pre-mortem skill, asks "what could go wrong", "failure modes", "risk analysis", or "what am I missing". Also invoke proactively before finalizing significant design decisions, before deploying…
Skill Claude CodeCodex
Honest self-assessment of the current state of work before shipping. Use when the user invokes the preflight skill or asks "how happy are you", "how do you feel about this", "preflight check", "honest assessment", "are you satisfied", or "what's the state of things". This is about surfacing what's genuinely good…
Skill Claude CodeCodex
Multi-lens quality audit of docs, code, or other artifacts using the 13-adjective quality rubric. Use when the user asks for a quality review, quality audit, docs audit, "run the rubric", "audit these files", or /quality-review. Levels mirror /code-review (low/medium inline, high and above workflow-backed; default is…
Skill Claude CodeCodex
Capture durable lessons from a session before they fade. What surprised you, what friction repeated, which host or project instructions should change, and what belongs in memory, project notes, or a tooling ticket. Use at session end after work has shipped or reached a natural pause. Trigger when the user invokes the…
Skill Claude CodeCodex
Get an independent review of your thinking before presenting it to the user, from the strongest independent channel the session offers (a full-transcript advisor tool if available, fresh-context reviewers otherwise). Use when you need a fresh take, alternative approaches, or independent validation on a design, plan…
Skill Claude CodeCodex
Audit error handling in local code changes for silent failures, inadequate error feedback, and inappropriate fallback behavior. Trigger when the user invokes the silent-failures skill, says "check error handling", "find silent failures", "audit fallbacks", or "review error handling". Also invoke proactively right…
Skill Claude CodeCodex
Write the implementation spec (the structured document that drives execution). Use after design is chosen, for example through the design-options skill, and before writing code. Trigger when the user invokes the spec skill, says "write the spec", "draft the implementation plan", or "scope this out". Also invoke…
Skill Claude CodeCodex
Before flipping a previously-stated position under pressure, restate its strongest form and the goal it served, then check whether the triggering argument refutes the core on the same goal, not just a decorative argument or a different axis. Self-invoke when about to flip a stated position. Trigger when the user…
Skill Claude CodeCodex
Write code, comments, tests, or commit messages that read as if the project's own maintainer wrote them, so a contribution is accepted as native rather than rejected as foreign. Use when writing into a codebase or document you don't own: a pull request or patch to an upstream project, a fix matching a specific…
Skill Claude CodeCodex
Identify and verify unverified claims in your own responses. Especially LOAD-BEARING ones: claims about to drive a design decision, commit, diagnosis, or user-visible recommendation. Self-invoke proactively when a claim is about to become the foundation for action. Also trigger when you catch yourself using hedging…
Skill Claude CodeCodex
Black-box verification of any agent output. Code, documents, presentations, reports, configs. Examine from the consumer's perspective and show evidence. Use when the user invokes the verify-result skill or says "verify", "prove it works", "test this end-to-end", "show me it works", "check the document", or "does it…