The library

systematic-debugging · Use this skill when you need to systematic debugging.

high-fidelity-ecs-engineering · Use this skill when you need to high fidelity ecs engineering.

accessibility-review · Use this skill when you need to accessibility review.

logging-failures · Auditing authentication/authorization event logs and preventing credential exposure before code review

025-roemisches-recht-in-griechischer-sprache-terminologi · German legal scholarship or comparative law analysis requiring Roman law authority and terminology mapping

agency-unreal-systems-engineer · AAA-grade multiplayer and performance-critical Unreal Engine projects where C++ rigor meets designer accessibility

canvas-design · Creating original poster art, static designs, and visual identities that appear hand-crafted by a master designer

review · Catching real bugs in code changes before PR merge, with proof and concrete fixes

find-bugs · Authorized security audits of branch changes before deployment, with evidence-based findings

svelte-runes · Quick rune selection and Svelte 4→5 migration guidance to prevent reactivity bugs

branch-docs-sync · Keeping developer notes and user docs in sync with recent code changes and refactors

python-cli · Rapidly building structured Python command-line tools that feel professional and discoverable

agency-embedded-firmware-engineer · Production embedded systems requiring real-time safety, predictable latency, and robust error handling

schema-verify · Runtime validation of structured data before processing or API responses

networkx · Graph analysis and algorithm computation for networks, collaboration, supply-chain, and social-graph problems

Simplify · Refactoring code for clarity and DRY compliance without hunting for bugs (use code-review for correctness)

severity · Classifying smart contract audit findings against historical benchmarks.

html-ppt-zhangzara-editorial-tri-tone · Creating editorial or fashion-magazine-style presentations with tri-tone design.

perf-analyzer · Converting raw performance data into actionable optimization recommendations.

m06-error-handling · Ensuring consistent error handling across a codebase without boilerplate.

sequential-thinking · Working through multi-step reasoning where each step must be shown.

explain-visually · Making abstract or technical concepts concrete through annotated diagrams.

perf-code-paths · Understanding which functions are called and in what order during execution.

perf-investigation-logger · Recording what was tested, why, and what findings emerged.

next-16 · Upgrading codebases to leverage Next.js 16 features and performance improvements.

tool-usage · Constructing reliable exploits for memory corruption vulnerabilities.

d3k · Debugging web apps when full user-action replay is needed to reproduce errors.

perf-theory-gatherer · Prioritizing optimization work in unfamiliar codebases.

code-review · Enforcing type safety, access control, and API contracts in TypeScript teams.

dart-contribute · Contributing to projects with parallel release branches (patch vs. main).

ux-psychology · Defending design decisions with peer-reviewed behavioral science.

pr · One-command workflow to atomically format, stage, and push a PR without manual git steps.

km · Switching cognitive modes (e.g., from coding to research) without losing session continuity.

Q · MCP-first code intelligence queries when you need call/def/ref across the whole codebase without manual grep.

qa · Verifying semantic and regex search implementations work correctly across all file types and languages without blocking or pagination bugs.

cr · Catching language-specific bugs and design issues before commit by applying both project-local and generic review profiles to changed code.

ci · Testing a Haskell-to-Rocq compiler change locally before pushing by running the exact GitHub Actions workflow steps without Docker.

do · Managing multi-wave work streams where wave-dependent model routing and context-aware task selection accelerate delivery over manual task picking.

av · Programmatically launching and controlling multiple AI agent sessions without TUI overhead when orchestrating batch work or CI/CD-driven agent tasks.

pr · Separating code review (clean diff) from planning artifact archiving, allowing reviewers to focus on implementation while preserving design rationale as write-once history.

rlm · Deep codebase analysis on large repositories requiring multi-level reasoning without manual context pruning, routing models and tool access by depth/effort.

db · Quick ad-hoc database queries during development when Docker Compose is the deployment model and CLI access is faster than GUI tools.

ox · Maintaining team coding standards and recording agent execution traces when working in a SageOx-enabled team project.

qf · Gate code commits and PRs by enforcing type safety, linting, and RDO-specific conventions (database, auth, MUI Grid v2) before review.

fi · Marking a sprint or phase complete by bundling build verification, documentation updates, dialog export, and git history into a single protocol.

es · Grounding agent fact-checking in explicit evidence standards when making claims, combining project-agnostic and project-specific validation rules.

up · Synchronizing new project or environment preferences across all AI tools (Claude, Codex, Gemini, Cursor) in a single command.

dev · Routing developer tasks to the right specialist agent (debug, review, refactor, commit, PR) without manual agent selection overhead.

sc · Bundling file staging and commit creation into a single operation when no complex git workflow (rebase, cherry-pick) is needed.

ws · Monitoring current project phase and task progress.