Decompose revenue and cost to the patient pathway level — what does each clinical pathway actually cost to deliver, what is the margin by pathway, where are loss-making pathways, and where could volume increase without proportional cost increase. Use when making pricing, capacity, or service line decisions.

从 git commit 历史自动生成人类可读的 CHANGELOG

Create, update, and audit SOUL.md, AGENTS.md, CLAUDE.md, and MEMORY.md from a PRD and the current repository state. Use when bootstrapping project governance, refreshing governance after PRD changes, or checking governance drift against the codebase.

Common software architecture patterns, ADR templates, and anti-pattern detection. Supports architectural review, design decisions, and system documentation.

Structured code review criteria for pre-implementation plan review (Critic) and post-implementation security/quality review. Covers security, performance, maintainability, and correctness with severity ratings.

Version management, release verification, and deployment procedures for software releases. Includes semver guidance, version consistency checks, and platform-specific constraints.

Security vulnerability detection patterns including OWASP Top 10, language-specific vulnerabilities, and remediation guidance. Load when reviewing code for security issues, conducting audits, or implementing authentication/authorization.

TDD workflow and test strategy patterns including test pyramid, coverage strategies, mocking approaches, and anti-patterns. Load when writing tests, designing test strategies, or reviewing test coverage.

One-line WHAT this skill does + two to three sentences on WHEN to trigger it. Be specific about contexts and use a pushy tone — skills undertrigger by default. Mention related phrases the user might say even when they don't name the skill explicitly. Replace this with your own description.

Enhances LaTeX lecture notes by analyzing pedagogical reference materials (like Todorov's PDFs) and systematically adding stunning visualizations, concrete examples, and intuitive explanations. Use when the user requests improving lectures, adding visualizations from papers, or adopting another author's teaching style.

Refines ML/scientific LaTeX papers based on reviewer or advisor feedback. Handles structural reorganization (moving problem statements, merging sections), concrete instantiations of abstract tables, cross-file deduplication, and compilation verification. Use when the user requests paper revisions, addresses reviewer comments, restructures sections, or improves exposition clarity.

Review a LaTeX research paper for mathematical rigor, notation consistency, proof obligations, numerical-analysis discipline, complexity claims, convergence/error bounds, figure quality, section flow, cross-references, and global coherence. Use when the user wants a deep technical review or verification pass on a paper, supplement, or LaTeX project. Do not use for initial drafting unless the user explicitly asks for review-first feedback.

Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered figure visibly has overlap, clipping, or label collisions; when setting up a per-figure review workflow across a large document; or when the user shows a screenshot of a figure that looks wrong. Trigger proactively whenever the user mentions figure alignment, TikZ layout, pgfplots legends/axes, figure cleanup, or asks to fix a figure — even if they don't explicitly say 'review'. Covers a fast iteration loop: extract each tikzpicture into a standalone, compile to PNG, fix, sync back to the main file.

Analyze contracts to identify key clauses, risks, obligations, deadlines, and parties. Multi-language support with focus on French and EU commercial law.

Evaluate AI agent outputs systematically using rubrics, assertions, and reference comparisons. Detect quality drift over time.

Detect and classify technical debt in AI-generated code — patterns specific to LLM outputs, shallow implementations, missing edge cases, and accumulation signals.

Manage skill versioning, freshness tracking, deprecation, changelog generation, and maintenance workflows for skill repository maintainers.

Validate SKILL.md structure, frontmatter completeness, token budget, freshness, naming conventions, and cross-platform portability before publishing.

>

Use when creating implementation plans from specs or requirements - phased task breakdown with deployment readiness gates before any coding begins

Use when committing, pushing, creating PRs, or completing branches - conventional commits, PR creation, Jira updates, worktree cleanup

Use when encountering any bug, test failure, or unexpected behavior - systematic root cause investigation before proposing any fixes

Use when executing an implementation plan task-by-task - dispatches subagents for implementation, manages git worktrees, handles phased multi-service deployment

Use when writing any code - enforces test-driven development discipline with RED-GREEN-REFACTOR cycle, fires during any coding task

Use when starting a software development conversation and the user's intent is not clearly matched by a specific enggenie skill - routes to the right role-based expert

Use when asking about previous sessions - cross-session context search via claude-mem with token-efficient 3-layer retrieval

Use when refining user stories, writing feature specifications, estimating story points, creating subtasks, planning spikes, or generating QA test plans - covers the product management side of development before implementation begins

Use for QA-perspective testing - Playwright automation or manual browser testing focused on user journeys, not implementation details

Use before claiming any work is complete - evidence-based verification that tests pass, builds succeed, and requirements are met

Use when requesting or receiving code review - dispatches reviewer subagent or processes human PR feedback with technical evaluation

Use when reviewing frontend implementation against design specs - design system compliance, responsive behavior, accessibility audit

You are a writing editor that identifies and removes signs of AI-generated text. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.

自动检测项目技术栈，生成 GitHub Actions workflow 及其他 CI/CD 配置

>

>-

Onboard quickly by reading design docs, plans, READMEs, or the codebase to extract key concepts, surface gaps, and generate comprehension checks with answer keys. Includes an adaptive proficiency probe with learning resources and persistent session memory so the user can resume onboarding where they left off. Use when a user wants help understanding a project, validating their grasp of the architecture, or creating a readiness plan before contributing code.

Evalúa la salud de un proyecto open source (repo GitHub, paquete npm/pip, o URL). Genera un brief estructurado con semáforo por categoría. Usar cuando el usuario quiera evaluar un nuevo proyecto, librería, o dependencia antes de usarlo.

>

>

自动检测技术栈，生成优化的 Dockerfile、docker-compose.yml 和 .dockerignore

Run the DesignVault `/bug` lane for narrow implementation issues found during playtest, QA, or observation. Use when Codex needs to start from a reported symptom, read only the minimum wiki truth needed, diagnose the implementation, repair it, verify the fix, and escalate to `/design` only if the root cause is really design truth.

Maintain DesignVault health and writeback quality. Use when Codex needs to scaffold a starter vault, search current truth, lint vault structure, trace changed files back to wiki pages, generate conservative writeback suggestions, draft change-review pages, or perform maintenance-only cleanup on a DesignVault repo.

Debug Go services, workers, tests, and CLIs using Delve. Use this for panic analysis, wrong output, stale callsites, interface-nil traps, channel behavior, goroutine issues, and state mismatches.

Debug Node.js runtime behavior using node inspect or IDE debuggers. Use this for wrong output, exceptions, async flow problems, promise chain issues, closure state bugs, event loop issues, and runtime shape drift.

Quality review skill based on EPUB 3.3 (W3C Recommendation). Performs structure validation, specification compliance checking, and accessibility evaluation of EPUB files, generating reports with specification rationale. Use this skill for any EPUB-related verification tasks including validation, quality checks, spec compliance confirmation, and e-book inspection.

>

Transforms legacy Java code to modern idioms. Use when migrating Java versions, converting verbose POJOs/DTOs to records, platform threads to virtual threads, for-loops to streams, anonymous classes to lambdas, or when a codebase targets Java 11-25 but uses older patterns. Version-aware (Java 8-25), framework-smart (Spring Boot, Quarkus, Micronaut), detects version from pom.xml or build.gradle automatically.

Run recurring Codex automations with Ceratops defaults. Use when an automation prompt needs shared policy for re-opening prompt and helper contracts, keeping task-specific logic in the automation prompt or helper scripts, suppressing routine clean-run alerts, avoiding routine automation memory, and reporting no-alert or no-memory conflicts explicitly.

Audit a repository after large refactors, branch merges, or parallel agent threads for contradictions between implementation, docs, configs, tests, examples, and control files. Use when the goal is post-merge validation, release-readiness consistency checking, documentation-drift detection, or merged-only edge-case hunting rather than style review.

Stage committed Ceratops skill changes into the runtime checkout's local `release/*` branch for coherent local preview. Use when Codex should merge ready task-worktree branches into a release branch created from `main`, switch the runtime checkout to that branch, update the local skill install, and run the local validation batch before GitHub shipping.