Audit and safely refactor a repository's directory layout while preserving behavior, imports, build tooling, history, generated-file rules, and user.
Verify that refactoring preserves existing behavior through before/after comparison, test coverage verification, contract checking, and semantic equivalence.
Interact with GitHub through an already available `gh` CLI using focused issue, pull-request, CI-run, and API workflows.
Perform recommendation-grade research on a named listed company using exact security identity, point-in-time primary filings, business/segment economics, earnings quality, balance…
GraphQL development guidelines with type-safe clients, schema design, and integration with React and Next.js.
Azure-specific infrastructure expertise for designing and managing cloud environments. Use when provisioning Azure resources with Bicep or Terraform.
Review AI-generated code by verifying acceptance criteria pass/fail status rather than reading implementation line-by-line. Triggers detailed code.
Draft accurate, traceable physiotherapy documentation from supplied facts. Use for initial evaluation, visit/daily note, re-examination/progress report, discharge or episode…
Define and enforce business rule assertions as automated checks using contract testing, schema validation, and invariant verification. Covers API contract.
Reference for nimble search command. Load when searching the live web. Contains: all flags, 8 focus modes. — from yigityildiz0/universal-ai-skill-library
Orchestrate evidence-based investment research and decisions across equities, funds/ETFs, BIST/TEFAS, macro regimes, technicals, crypto, futures, warrants, portfolios, sizing,…
Compare current AI models, providers, gateways, subscriptions, local routes, and free/paid endpoints for a concrete task.
Review one completed investment/trade or a journal of many decisions while preserving the original plan, separating process quality from profit/loss, testing thesis and forecast…
Design and verify provider-neutral spend, token, request, and concurrency controls for AI workloads. Use when an application or agent can incur usage.
Maintain docs/todos.md as the project's living progress tracker. Use at session start (read current state), when tasks complete (check them off), when new.
Help submit an expense or reimbursement on any platform. Detects the right tool (Benepass, Brex, Concur, Expensify, etc.), finds receipts, checks for.
Audit, compare, merge, repair, or improve user-owned Codex and ChatGPT skill variants while preserving proven behavior.
Creative direction for image prompts, presentation slides, and ideation. Use when asked to generate image prompts, design slide decks, brainstorm ideas.
Read, translate, and deeply teach English physiotherapy and rehabilitation language without losing scientific detail.
Coordinate two or more available AI assistants or model sessions through explicit roles, artifact handoffs, and quality gates. Use for high-risk.
Expert Terraform/OpenTofu specialist mastering advanced IaC automation, state management, and enterprise infrastructure patterns. — from yigityildiz0/universal-ai-skill-library
Research crypto assets in a strictly read-only mode using verified network and contract identity, multi-venue price checks, liquidity and derivatives structure, tokenomics and…
Generate code patches from bug reports, error messages, and failing tests. Use when converting bug descriptions into fixes, creating patches from error.
Initialize a complete C#/.NET project with solution structure, testing framework, and configuration. Use when starting ASP.NET Core APIs, console.
Design a privacy-aware product telemetry plan with event taxonomy, properties, identity rules, validation, and decision links.
Create integration and end-to-end test scenarios covering workflows, API interactions, database operations, and system boundaries. Use when testing.
Generate framework-specific UI components by prompting the agent's own LLM directly - no external generation service or MCP required
Audit project dependencies for known vulnerabilities (CVEs), license issues, and outdated packages with SBOM generation. Use when deploying to production.
Translate code between programming languages while preserving logic, idiomatic style, and test coverage. Use when porting code between languages, migrating.
Select and compare physiotherapy PROMs, ClinROMs, performance tests, and diagnostic special tests using population-specific evidence.
Diagnose and improve ComfyUI text conditioning with architecture-aware prompts, encoder and node compatibility checks, controlled experiments, and.
Route operational work to focused, evidence-based workflows for SOPs, capacity, change, risk, compliance evidence, runbooks, vendor review, stakeholder updates, and process…
Design and verify Claude API access across Anthropic direct and supported cloud/platform integrations without hard-coded model IDs or silent failover. Use.
Transform Gmail into a business intelligence system for MTL Craft Cocktails. Answer questions about emails, detect leads, draft responses, and track client communications with…
Review product metrics, KPI movement, metric definitions, segmentation, anomalies, and decision implications.
Meeting-workflow umbrella skill. Use when Codex should turn Zoom-style meeting artifacts into prep notes, transcript summaries, or follow-up actions.
Pinpoint bug locations using stack traces, error logs, code flow analysis, spectrum-based fault localization, and bisection techniques. Use when debugging.
Apply exact design standards to any UI component or page. Use when building web components, landing pages, dashboards, React components, or any UI. Triggers.
Branded social-carousel skill. Use when Codex needs to turn ideas or content into a slide-by-slide social carousel with brand-consistent copy and visual.
Determine whether a CVE in a dependency actually affects your application by tracing call paths from your code to vulnerable functions, analyzing transitive.
Grassroots-first campaign design for anyone being outspent — startups vs. incumbents, NGOs vs. corporate comms, movements vs. state-backed machines, solo.
Ground agent answers in local library documentation (pydoc, go doc, vendored READMEs, help() in REPLs) rather than routing queries through a third-party.
Help return an item or request a refund from any retailer. Identifies the item, finds the return policy, navigates the process, and handles shipping labels.
Perform a static, read-only security and trust preflight on a downloaded or third-party skill, plugin, ZIP, repository, installer, or update.
Apply gofmt, remove unused packages, improve error handling, and clean up Go codebases. Use when cleaning up Go projects, removing unused imports, applying.
Make a phone call to book an appointment or reservation. Checks calendar first, gets explicit consent before dialing, discloses AI identity on the call, and.
Build test doubles (mocks, stubs, spies, fakes), data factories, and fixtures for test isolation. Use when tests need external dependency isolation.
Compile multiple research reports (.docx/.md/.pdf/.pptx/.html/.txt/URLs) into one unified document (.docx, .pdf, or .md) with deduplicated inline [N].
Activate, change, or stop the manual Caveman response mode only when the user explicitly says $caveman, /caveman, Caveman plus a level, asks to open/activate/switch to Caveman or…
Expert SQL query writing, optimization, and database schema design with support for PostgreSQL, MySQL, SQLite, and SQL Server.
Structured analytical reasoning and data presentation principles. Use when asked to analyze data, compare options, evaluate trade-offs, create decision.
Evidence-first verification and rebuttals to specific claims. Use only when the user explicitly wants an opposing or corrective response, for example "what can I say against…
Quantify, categorize, and prioritize technical debt using SQALE methodology with interest calculation and remediation planning. Use when assessing code.
Run a final read-only readiness check before an investment or trade across exact identity, evidence cutoff, executable entry, thesis, payoff, catalysts, invalidation, quantity,…
Generate professional PDF documents programmatically using Python and JavaScript libraries with precise layout control, typography, and multi-format.
Build, improve, or review web and product interfaces as one coherent system across layout and optical balance, accessibility, UX writing, typography, color, surfaces, icons,…
Remove unused exports, fix ESLint issues, modernize to ES6+, and clean up JavaScript/TypeScript codebases. Use when cleaning up JS/TS projects, removing.
Apply a preservation-first workflow to read, create, edit, and validate Word DOCX documents while protecting structure, styles, relationships, accessibility, and existing user…
Initialize a complete Java project with Maven/Gradle build, testing framework, and standard structure. Use when starting Spring Boot applications, Maven.
Analyze and compare mutual funds, ETFs, index funds, money-market funds, pension funds, and TEFAS products using exact identity, mandate, benchmark, holdings, look-through…