Symptom-driven troubleshooting guide for HTTP/transport errors when integrating the Overlens IDP — the "why am I getting this status code?" skill. Use this whenever a developer is BLOCKED by an error response from the IDP or from their own auth flow and needs to map symptom → cause → fix: `401 invalid_client` on `/auth/token`, `400 unauthorized_client` (grant type not allowed), `400 invalid_grant` (code expired/reused/PKCE mismatch), `400 invalid_redirect_uri` (redirect_uri doesn't exact-match), `404` on `POST /login/google` (PostHog feature flag off — older docs said 403), `429 Too Many Requests` (rate limit), `Max-Age=0` cookies (the ms-vs-seconds bug), missing `Set-Cookie` (forgot `credentials: 'include'`), and CORS failures in prod that worked in dev (`\.overlens\.com\.br$` origin regex). Triggers on phrases like "401 Overlens", "invalid_client Overlens", "CORS error Overlens", "Overlens login works locally but not in production", "429 Overlens rate limit", "Overlens cookie not being set", "Max-Age=0", "redirect_uri_mismatch IDP", "unauthorized_client Overlens", "my Overlens Google login returns 404 (or 403)", or any stuck-on-an-error-code report against the Overlens IDP. This skill diagnoses HTTP/transport/config failures. If instead the token IS received but its CONTENTS look wrong (bad `iss`/`aud`, `kid not found`, signature verify fails, decode the payload, algorithm-confusion, stale JWKS after rotation), prefer `idp-debug-jwt`. If nothing is failing yet and the dev just wants to integrate, prefer the integration skills (`idp-integrate-oauth-web`, `idp-auth-nextjs`, `idp-integrate-m2m`, `idp-validate-token`).
Migrate Hermes Agent to a new server while keeping both instances running in parallel. Covers backup, SSH troubleshooting, skill/memory sync, and GitHub remote setup.
Use when the game store entitlement parity workflow needs a safe recovery, rollback, replay, or continuity check to produce a recovery-drill record for the platform entitlement test matrix with starting state, test, and observed outcome. Success means the dry-run or approved non-production drill meets the predeclared recovery target and leaves the baseline intact; purchases and restore behavior match the declared contract in sandbox only. Use configured search, fetch, read, browser, test, and write capabilities only when relevant and authorized. Record evidence, limit refinement to three focused passes, and seek approval before external or irreversible actions.
个人 IP 图解创作器。用你的 IP 形象，生成专属内容图解。用于把用户授权提供的照片、主页截图、简介、账号资料或角色档案转成稳定的极简手绘图解角色，并继续生成长文配图、图文号知识卡、手机海报、方法拆解图、分镜故事图、IP 演讲 PPT、直播分享课件和全图化手绘 PPT 页面等内容视觉。它强调 IP 主角 + 执行 Agent 的知识图解系统：用户 IP 做主讲、拆解、批注和调度，执行 Agent 做搬卡片、反馈、试错、标记风险和递交结果。用户想做个人 IP 形象、用自己的形象做知识图、图文号知识卡、文章配图、课程图解、内容海报、方法拆解图、IP 演讲 PPT、直播分享课件，或上传照片/主页截图/简介希望做内容视觉时，使用本 Skill。
Gera estrutura completa de testes automatizados (unitários, integração e edge cases) com base no código existente. Use para "escrever testes para este arquivo", "aumentar cobertura" ou "criar mocks".
Write or correct the section for the upcoming version in release-history.rst of a pywf open-source Python library, based on git history since the last tag. Use when the user wants to prepare release notes, update the changelog, record a change such as a dependency upgrade, or is about to publish or tag a new version.
Use Retro Diffusion for pixel-art image generation, img2img edits, spritesheets, and animation experiments such as platformer walk cycles, turnarounds, and action sheets from reference images.
Drive Pace, the Electron desktop GUI for the Pi coding agent, through the repo's Playwright Electron harness (e2e/fixtures/electron-app.ts launchPace). Use to prove a user-facing Pace flow — preflight, Live Chat, Session dock, Packages, Usage — against an isolated window, not a unit test.
This skill should be used when the user wants to build, launch, monetize, or promote a WeChat mini-program with AI (vibe coding) — including topic selection, account registration & ICP filing, AI-assisted development with TRAE/WeChat DevTools, ad monetization (流量主), review & publish, and growth/matrix operations. Trigger on keywords like 小程序, 微信小程序, 流量主, 小程序变现, 备案, 微信开发者工具, TRAE, 小程序开发, 激活码, 小程序推广, 小程序矩阵.
Map a standard to its closest equivalent in another framework, or report an honest gap. Do NOT use to check a code is current (use standards-match); never invent codes.
Optimize web performance through network protocols, resource loading, and browser rendering internals. Use when the user mentions "my site is slow", "Core Web Vitals", "HTTP/2 or HTTP/3", "resource hints", "network latency", "render blocking", "TCP/TLS optimization", "service worker", "Cache-Control or caching strategy", or "critical rendering path". Also trigger when diagnosing slow page loads, optimizing time to first byte, choosing between WebSocket and SSE, or reducing bundle sizes. For UI visual performance, see refactoring-ui. For font loading, see web-typography.
Scanpy is a scalable Python toolkit for analyzing single-cell RNA-seq data, built on AnnData. Apply this skill for complete single-cell workflows including quality control, normalization, dimensionality reduction, clustering, marker gene identification, visualization, and trajectory analysis.
Eng manager-mode plan review. Lock in the execution plan — architecture,
data flow, diagrams, edge cases, test coverage, performance. Walks through
issues interactively with opinionated recommendations. Use when asked to
"review the architecture", "engineering review", or "lock in the plan".
Proactively suggest when the user has a plan or design doc and is about to
start coding — to catch architecture issues before implementation.