hypothesis-elimination
Systematic elimination reasoning for diagnosis and debugging. Use when you need to identify THE cause among many possibilities through evidence-based elimination. Ideal for production incidents, bug diagnosis, root cause analysis, and differential diagnosis. Unlike BoT (which explores), HE eliminates. Example: "Server is slow" → Generate 10 hypotheses, design discriminating tests, eliminate 9, confirm 1.
integrated-reasoning-v2
Enhanced meta-orchestration for selecting and combining reasoning patterns. Now includes 9 methodologies (ToT, BoT, SRC, HE, AR, DR, AT, RTR, NDF) with weighted multi-dimensional selection, feedback loops, uncertainty propagation, and validated confidence aggregation. Use when facing complex problems requiring optimal reasoning strategy selection.
integrated-reasoning
Meta-orchestration guide for choosing optimal reasoning patterns. Analyzes problem characteristics and recommends which cognitive methodology to use - tree-of-thoughts (find best), breadth-of-thought (explore all), self-reflecting-chain (sequential logic), or direct analysis. Use when facing complex problems and unsure which reasoning approach fits best.
negotiated-decision-framework
Multi-stakeholder coordination for decisions involving competing interests, different value systems, or organizational politics. Use when multiple parties must agree, when power dynamics affect decisions, or when consensus is required but perspectives diverge. Unlike DR (resolves conceptual tensions), NDF resolves stakeholder tensions.
parallel-execution
Parallel execution patterns for cognitive reasoning tasks. Use when independent sub-problems can be solved simultaneously, multiple solution approaches need exploration, ensemble confidence is required, or time permits depth without sequential constraints. Integrates with ToT, BoT, HE, and AT for accelerated reasoning with fan-out/fan-in, MCTS-style search, and MoA aggregation patterns.
ralph-loop-integration
Persistent iteration wrapper for cognitive reasoning patterns using ralph-loop's Stop hook mechanism. Use when high confidence (>90%) is required, complex multi-pattern orchestration needs iterative refinement, self-correcting analysis is needed, or long-running tasks require checkpointed persistence. Wraps IR-v2 patterns in completion promise-gated loops.
rapid-triage-reasoning
Fast decision-making methodology for time-critical situations. Use when you have minutes (not hours) to decide, during incidents, emergencies, or hard deadlines. Optimizes for "good enough now" over "perfect later". Unlike other patterns that maximize quality, RTR maximizes decision speed while maintaining acceptable quality floors.
reasoning-handover-protocol
Protocol for cognitive pattern handovers during complex reasoning sessions. Defines .reasoning/ directory structure, handover schemas, and IR-v2 orchestration integration. Use when reasoning sessions require mid-stream pattern transitions, parallel branch merging, state checkpointing, or multi-pattern orchestration. Essential for complex problems where ToT, BoT, HE, or other patterns must hand off work to each other.
self-reflecting-chain
Sequential reasoning with deep self-reflection and backtracking. Use when problems have step-by-step dependencies, need careful logical reasoning, or require error correction. Each step includes self-reflection, and incorrect steps trigger backtracking. Ideal for debugging, mathematical proofs, sequential planning, or causal analysis where order matters.
tree-of-thoughts
Advanced recursive reasoning methodology for systematic problem-solving. Use when you need to explore multiple solution approaches in parallel, evaluate them rigorously, and recursively deepen the best path. Ideal for complex decisions with trade-offs, optimization problems, or strategic planning. Example: "Should we use microservices or monolith?" → Apply ToT to spawn 5+ architectural approaches, evaluate each systematically, recurse on the winner.
agent-creator
Comprehensive guide for creating high-quality specialized agents following v2 architecture patterns. Use this skill when users need to design and implement new agents, understand agent architecture, or learn best practices for agent creation.
agent-memory-skills
Self-improving agent architecture using ChromaDB for continuous learning, self-evaluation, and improvement storage. Agents maintain separate memory collections for learned patterns, performance metrics, and self-assessments without modifying their static .md configuration.
chromadb-integration-skills
Universal ChromaDB integration patterns for semantic search, persistent storage, and pattern matching across all agent types. Use when agents need to store/search large datasets, build knowledge bases, perform semantic analysis, or maintain persistent memory across sessions.
confidence-check-skills
Pre-implementation validation framework requiring ≥90% confidence before coding. Prevents wrong-direction work by assessing duplicates, architecture alignment, documentation, OSS references, and root cause understanding. Use before implementing features, fixes, or refactoring to save 5K-50K tokens per prevented error.
document-writing-skills
Teaches document writing patterns and templates that agents apply when generating documentation, reports, contracts, guides, and technical writing. Use when creating API docs, user guides, reports, changelogs, ADRs, or technical documentation.
error-handling-skills
Universal error handling, exception management, and logging best practices for all development agents across JavaScript/TypeScript, Python, Rust, Go, and Java. Use when implementing error handling, exception management, logging, error recovery, or debugging production issues.
git-workflow-skills
Provides standardized Git workflows, commit message conventions, branching strategies, and collaboration patterns for all agents performing Git operations. Use when creating commits, choosing branching strategies, creating PRs, performing git operations (merge vs rebase), or handling git collaboration workflows.
security-analysis-skills
Comprehensive security analysis framework teaching STRIDE threat modeling, OWASP Top 10 vulnerabilities, CVSS risk scoring, and secure coding patterns. Use when conducting security assessments, code reviews, threat modeling, or implementing security controls. Applicable to all development work requiring security consideration.
mcp-setup
Add, inspect, authenticate, or remove MCP server registrations for the current Codex runtime. Use when the operator asks to configure an MCP server or diagnose whether a registered server is available. Do not clone server code into projects, assume every project needs the same servers, or manage app-specific business workflows.
determinism
Design machine-checkable assertions, stable hashes, fixtures, and exit-code contracts for behavior that must be reproducible. Use when an outcome currently depends on subjective agent judgment or when prompts and generated artifacts need versioned integrity checks. Do not use merely to run an existing repository verification gate; that is verify's job.
remotion-best-practices
Router for all Remotion skills
remotion-create
Create a new Remotion video
remotion-render
Export a Remotion video
activitykit
Implement, review, or improve Live Activities and Dynamic Island experiences in iOS apps using ActivityKit. Use when building real-time updating widgets for the Lock Screen and Dynamic Island — delivery tracking, sports scores, ride-sharing status, workout timers, media playback, or any time-sensitive information that updates in real time. Also use when working with ActivityKit, ActivityAttributes, Activity lifecycle (request/update/end), Dynamic Island layouts (compact/minimal/expanded), push-to-update Live Activities, or Lock Screen live widgets.
project-context-installer
Install a project-local context graph into a repo. Use when the operator asks to set up, scaffold, install, or wire a project context graph, durable decision graph, session-mining memory graph, or `project-context` CLI. This skill creates a deterministic local Python CLI, root wrapper script, docs/workflow wiring, and validation hooks inside the target project while keeping global doctrine in `~/.codex` and repo-specific behavior in the repo.
apple-developer
Configure and verify Apple Developer signing, bundle identifiers, capabilities, provisioning, entitlements, App Store Connect, TestFlight, Developer ID, notarization, and release readiness for any iOS, iPadOS, macOS, watchOS, tvOS, visionOS, or app-extension target. Use when creating a new Apple app or extension, repairing Xcode signing, selecting an Apple team, registering App IDs, adding widgets or App Groups, preparing archives/uploads, or auditing signed artifacts and Apple release evidence. For Xcode Cloud workflow design and operations, use the xcode-cloud skill with this skill as the signing owner.
artifact-template-likeminded-profile-and-soulmate
Create an image using the Likeminded Profile and Soulmate template and its retained reference file. Use when the user selects this template, names Likeminded Profile and Soulmate, or explicitly invokes $artifact-template-likeminded-profile-and-soulmate. Create Likeminded Profile and Soulmate interface mockups with warm ivory surfaces, deep forest typography, topographic linework, editorial hierarchy, restrained cards, and calm relationship-focused content.
cli-for-agents
>-
cloudkit
Implement, review, or improve CloudKit and iCloud sync in iOS/macOS apps. Use when working with CKContainer, CKRecord, CKQuery, CKSubscription, CKSyncEngine, CKShare, NSUbiquitousKeyValueStore, or iCloud Drive file coordination; when syncing SwiftData models via ModelConfiguration with cloudKitDatabase; when handling CKError codes for conflict resolution, network failures, or quota limits; or when checking iCloud account status before performing sync operations.
code-quality-audit
Use for read-only code quality, correctness, security, maintainability, observability, and operational audits that produce a ranked PROGRESS.md backlog in an isolated audit worktree.
codex-efficient-delegation
Measure and tune bounded Codex subagent workflows for quality, speed, context efficiency, and token or cost efficiency. Use when deciding whether independent repo scans, evidence audits, browser proof, role-based customer or UI reviews, test analysis, or other separable work should run in parallel; when replacing microtask agents with complete outcome missions; when comparing direct main-thread work with explorer or verifier sidecars; or when turning delegation observations into a repeatable experiment without surrendering main-thread judgment.
create-design-md
>-
create-skill
Compatibility and deterministic maintenance layer for locally authored skills. Use when the official skill-creator has drafted a skill, or when the operator asks to audit, validate, optimize, shrink, repair, or diagnose activation of an existing skill. Owns local schema, reference, and progressive-disclosure checks; it does not own first-draft authoring or portfolio-level duplicate routing.
enforcement
Design a deterministic blocking gate for a repeated unsafe or invalid transition after advisory guidance has failed. Use when the operator asks to enforce a state transition, prevent a destructive or secret-bearing action, or convert a proven verification rule into a runtime guard. Do not assume Claude hook events or invent a hook surface; confirm the current runtime's supported mechanism first.
execplan
Create or maintain one repository-local living execution plan for a complex implementation that cannot be safely completed from a short task plan. Use when the operator asks for an ExecPlan, a durable phased implementation plan, or a self-contained plan another agent can execute. Do not use for product-roadmap ownership, cross-session program selection, or simple tasks.
knowledge-base
Maintain the canonical local agent-engineering knowledge corpus under ~/.codex/knowledge: ingest an accepted source, refresh an existing article from its primary source, repair metadata, reindex search, or rebuild the generated browser. Use only when the operator asks to change or maintain that corpus. Do not use for evaluating whether research should be adopted or for recalling session history.
macos-widget-reinstall
Replace a stale macOS desktop widget after its host app or WidgetKit extension changes. Use when the visible widget is cached, missing, or must be removed and added again.
playwright
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
product-sites
Design and direct premium product, SaaS, app, portfolio, and launch sites with a clear product story, high data-ink ratio, grounded polished product imagery, responsive evidence composition, purposeful GSAP motion, and independent customer UI/UX acceptance. Use when creating or materially redesigning a product site. Coordinate with frontend-app-builder for concept-to-code implementation, imagegen for capture-grounded product imagery, review-customer-ui-ux for the final review loop, and Sites for setup, runtime, and deployment; do not replace those owners.
repo-readiness-bootstrap
Bootstrap or assess a Codex-first day-one readiness baseline for an unfamiliar repo. Use when entering a repo for the first time, making a repo agent-runnable, or needing one canonical readiness report before implementation.
resume-session
Inspect `.session/CURRENT.md`, surface the tactical handoff, and restore only an eligible explicit Codex goal. Triggers: `/resume-session`, `resume session`, `continue where I left off`, `pick up where we left off`. Use when a prior session may contain useful intent, but first reject stale, malformed, branch-diverged, commit-diverged, route-invalid, or reference-only checkpoints. Read legacy `.claude/session-data/CURRENT.md` only before `.session/` exists.
save-session
Snapshot only resume-relevant tactical context and an explicitly resumable Codex goal to `.session/CURRENT.md`. Triggers: `/save-session`, `save session`, `save progress`, `checkpoint`. Use when the next agent needs a compact, time-bounded handoff with the exact goal, first action, validation, blockers, route, and context to avoid. Do not capture noisy recent files or treat the checkpoint as permanent truth. Use the shell command `save-session` for the deterministic write path.
screenshot
Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-specific capture capabilities are unavailable and an OS-level capture is needed.
session-introspection
Use when closing meaningful sessions or auditing agent-harness inefficiency: capture preventable friction, optionally mine recent prior sessions for recurrence, choose the narrowest durable control, route it to one owner, and apply obvious safe controls immediately.
session-orchestrate
Orchestrate product-plan completion across substantive Codex tasks. Use when the operator invokes $session-orchestrate, asks to continue eligible saved work, derive implementation goals from a roadmap, coordinate work across sessions, or avoid repeated compaction. A bare invocation reuses a fresh source-fingerprinted program map, rebuilding only when stale; it resumes saved work only when resume-session proves the checkpoint fresh and consistent and the current owner plan still permits it.
speech
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run the bundled CLI (`scripts/text_to_speech.py`) with built-in voices and require `OPENAI_API_KEY` for live calls. Custom voice creation is out of scope.
swiftui-animation
Implement, diagnose, or review SwiftUI motion using explicit and scoped implicit animations, springs, transitions, PhaseAnimator, KeyframeAnimator, matched geometry or navigation zoom, SF Symbol effects, and custom Animation types. Use when views should animate on state changes, insertion, removal, navigation, or multi-step choreography, or when motion must respect Reduce Motion and Swift concurrency.
swiftui-pro
Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or reviewing SwiftUI projects.
transcribe
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
verify
Dispatch repository verification through the narrowest declared validation owner and return one evidence-backed readiness verdict. Use when the operator asks to verify a build, run quality checks, validate current changes, or decide whether work is ready. Do not invent generic commands when AGENTS.md, package scripts, a phase gate, or a specialist skill already owns validation.
Page 310 of 1637 · 81818 results