Skill Claude CodeCodex
Capture recurring agent-development friction as a local, privacy-safe Markdown report. Use only when the user explicitly requests a friction review of blockers, misleading errors, missing documentation, incompatible tools, or manual workarounds that should improve a doc, tool, skill, process, or evaluation.
Skill Claude CodeCodex
Route reusable agent learning after an error, success pattern, review finding, or repeated workflow. Use when deciding whether an improvement belongs in the model prompt, memory/context note, durable docs, SKILL.md, checklist, script/tool, eval, golden fixture, or should be rejected as overfit.
Skill Claude CodeCodex
Define and review concrete agent capability cards, asynchronous operation receipts, decision receipts with revalidation, isolated and trust-graded memory scopes, and evidence-backed provider or tool registry entries. Use when a project introduces named agents, scheduled or long-running work, durable decisions or…
Skill Claude CodeCodex
Review tools, MCP functions, CLI commands, SET inputs, and AGENTS.md generator outputs as agent-facing contracts. Use when a tool description, schema, workflow input, or generated instruction may be ambiguous, unsafe, noisy, or hard for agents to call correctly.
Skill Claude CodeCodex
Design, audit, or improve agentic systems and agent harnesses. Use for agent MVP blueprints, tool design, permission models, planning and goal loops, context compaction, memory, skills, connectors, observability, evals, safety, and provider-neutral agent architecture.
Skill Claude CodeCodex
Review an implemented product UI or public prose surface for hard visual defects, design-system incoherence, repeated template patterns, and AI-writing tells without treating subjective taste as universal law. Use for pre-ship screenshots, browser review, README/tool-page copy, launch notes, guide prose, or redesigns…
Skill Claude CodeCodex
Review a codebase for architecture deepening opportunities: shallow modules, weak seams, scattered domain logic, low testability, high coupling, and AI-navigability friction. Use when the user asks for architecture improvement, refactoring opportunities, modularity, test seams, or maintainability review.
Skill Claude CodeCodex
Surface hidden assumptions in plans, specs, AGENTS.md, SKILL.md, SET bundles, and workflow contracts before implementation or handoff. Use when an artifact looks plausible but may rely on unstated environment, dependency, behavioral, temporal, or success assumptions.
Skill Claude CodeCodex
Route authorized defensive security and reverse-analysis tasks by scope, target type, user intent, and available toolchain before taking action. Use for APK review, static binary triage, frontend JavaScript security review, firmware inventory, malware/YARA analysis, API/LLM/supply-chain audit, security report…
Skill Claude CodeCodex
Convert books, papers, long documents, or prior reading notes into compact reusable agent skills. Use when the user provides a PDF, EPUB, DOCX, HTML, Markdown, text file, article bundle, or structured notes and wants reusable workflows, mental models, frameworks, checklists, anti-patterns, or a public/private SKILL.md…
Skill Claude CodeCodex
Design small evaluation gates for agent outputs, skill changes, prompts, and tool contracts. Use when a change needs rubric checks, pairwise comparison, position-bias mitigation, regression fixtures, or LLM-as-judge discipline without building a heavy eval platform.
Skill Claude CodeCodex
Design a small recurring product, content, SEO, analytics, or go-to-market review loop with evidence checks, durable state, explicit stop rules, and approval-gated outputs. Use before scheduling recurring growth work or turning a repeated marketing task into an agent loop.
Skill Claude CodeCodex
Coordinate an opt-in Planner, Reviewer, and bounded Executor workflow with stable findings, at most five review rounds, disjoint write ownership, explicit route evidence, and root-owned verification. Use when the user asks for plan review, multi-agent orchestration, routed executors, parallel implementation, or the…
Skill Claude CodeCodex
Create a single working brief before substantial implementation, audit, or migration work. Use when tasks are non-trivial, risks are real, or the session is likely to drift without one source of truth for scope, non-goals, verification, and done criteria.
Skill Claude CodeCodex
Verify frontend changes in a real browser, including layout, console errors, responsive states, network failures, screenshots, and interactions. Use after local or deployed web UI changes, visual fixes, forms, navigation, asset updates, canvas or 3D work, or whenever browser verification should replace static guessing.
Skill Claude CodeCodex
Capture and classify minimal red-to-green evidence for a diagnosed bug and scoped fix, with command hashes, Git/environment identity, broader-check records, risk-based approval, route evidence, and optional cpat linkage. Use after diagnose establishes a credible reproducer or when a reported regression needs an…
Skill Claude CodeCodex
Preserve working state across long sessions and context compaction by checkpointing decisions, edited files, blockers, open hypotheses, and unresolved errors into compact resumable artifacts. Use on long coding tasks, audits, research, or any session at risk of losing state after compaction.
Skill Claude CodeCodex
Analyze or improve codebase complexity and performance hotspots without broad rewrites. Use when reviewing nested loops, repeated scans, N+1 queries, rendering churn, excessive recomputation, slow tests, large-input paths, memory pressure, or requests to reduce complexity while preserving behavior and tests.
Skill Claude CodeCodex
Review whether an artifact's confident claims are backed by evidence, tests, contracts, or operational safeguards. Use before shipping, publishing docs, accepting generated plans, or trusting a workflow that may present fragile assumptions as certainty.
Skill Claude CodeCodex
Review agent work for context poisoning, lost-in-the-middle failures, distraction, context clash, and stale carryover. Use before long-session handoffs, SET runner handoffs, skill changes, memory writes, or any task where too much or conflicting context may degrade behavior.
Skill Claude CodeCodex
Shape partner-facing and institutional surfaces so they read as credible operating systems rather than generic SaaS templates. Use for corporate landings, capability pages, partner sections, investor-facing surfaces, and other public pages that must feel clear, evidence-backed, and commercially serious.
Skill Claude CodeCodex
Audit claimed delivery against the starting baseline and the current working tree. Use when a task has declared deliverables, when a long run might say 'done' before shipping real changes, or when final verification must check the actual artifact set rather than only the transcript or commits.
Skill Claude CodeCodex
Run a baseline preflight before long implementation, autonomous execution, or publishing a PR. Use when a task has multiple phases, mandatory commands, high risk of thrashing against an already-broken repo state, or should be checked in an isolated push gate before reaching the real remote. Deduplicate the minimum…
Skill Claude CodeCodex
Critique and polish frontend interfaces before shipping, with focused review of hierarchy, typography, spacing, states, color, and UX clarity. Use when a page, component, or app surface feels unclear, inconsistent, flat, awkward, under-tested, or not yet production-grade and needs design verification instead of a…