Explore

Writes one LinkedIn post from a topic, notes, or a rough draft, or finds the idea first. Use when the user asks for a LinkedIn post or a hook, to turn notes or an article into a post, or what to post. Not for ads, newsletters, comments, DMs, or profile rewrites.

Clean a messy CSV safely, with no silent changes: profile it, show a plan, keep the original, and write a cleaned copy plus a cell-level change log. Use when asked to "clean this CSV", "remove duplicates", "fix the dates" or "fix missing values", or when a shared CSV/Excel export has ₹ or lakh-comma amounts, mixed date formats, NA/nil markers or lost leading zeros, even if the user only says the data looks wrong.

Intercepts, redacts sensitive credentials from, and compresses large terminal crash dumps, stack traces, and multi-line error outputs into a compact 25-line Failure Digest to conserve context windows. Use when an application, build, container, test suite, or CI pipeline crashes with massive stdout/stderr payloads, or whenever unhandled exceptions and runtime errors occur even if the user does not explicitly name this skill. Triggers on phrases like "debug this failure", "why did this build crash", or "here is the error log".

Find and triage API contract failures using bounded Schemathesis runs, redacted evidence and regression comparisons. Use when a developer provides an OpenAPI or GraphQL schema, asks to test a development API, or needs an actionable bug report from Schemathesis JUnit output.

Tailor a college student's resume to one specific job description for campus placements or internships in India, without inventing anything. Use when someone shares a resume plus a job description (JD) or company hiring post and asks to tailor, customise, match, shortlist-proof or improve the resume for that role, or asks why they are not getting shortlisted.

Check whether factual claims in a report are supported by supplied sources. Use when reviewing student research reports, checking citations, or auditing AI-generated summaries.

Use when the user asks to generate a video, make an AI video, create an image or poster from text, do text-to-speech, or give an agent media generation — e.g. "generate a video of a corgi running in snow", "make me a 15s promo video", "turn this text into speech". Covers Seedance 2.0/2.5 video (10s/15s/30s), Seedream 5.0 images, 7-voice TTS and OpenAI-compatible chat via the xzai.me API, with async polling and local download.

Validates, normalizes, formats, masks and generates Indian data with offline Python scripts (PAN, Aadhaar with Verhoeff, GSTIN with checksum, IFSC, UPI IDs, mobile numbers, PIN codes, vehicle numbers, rupee lakh/crore formatting and amount in words, DD/MM/YYYY dates, financial vs assessment year, PII masking). Use when asked to validate a GSTIN or PAN, clean a customer CSV, write an amount in words, find the FY for a date, or mask a ticket before sharing, and for any KYC, invoice or GST work.

Investigates software bugs, explains failing tests, reviews suspicious permissions, and traces errors across frontend, API, backend, and database layers. Use when a developer reports broken behavior or needs root-cause analysis and an evidence-backed fix, even when the faulty file is unknown.

Checks a codebase against recently published severe CVEs and fixes what's affected, across dependencies, language runtimes and Docker images, and certificate trust, not just packages. Use when asked "are we affected by the latest CVEs", "patch this repo for security", "anything critical this month?", "fix vulnerable dependencies", "are we hit by CVE-2026-…", "are we affected by php2shell", or after a security advisory makes the news.

Evidence-based bug localization for unfamiliar codebases. Use when investigating bug reports, exceptions, stack traces, failing tests, or unexpected behavior to rank suspicious files with verifiable evidence and practical verification steps.

Creates accurate, complete second-hand textbook listings for college and university students. Use when a student wants to "create a book listing", "sell my textbook", "check my textbook listing", "price my used book", or needs help with missing book details, conflicting information, condition disclosure, or safe campus exchanges.

Build personalized career roadmaps, study plans, and interview prep for students in software development, AI, ML, and data science. Use this skill when a student needs career guidance, learning paths, portfolio projects, or resume help.

Checks hackathon requirements and submission readiness. Use when users ask to "check hackathon requirements" or "review my competition submission," even if they don't name this skill.

Audits tabular machine learning datasets (CSV/Parquet) and Python training scripts (Scikit-learn, XGBoost, LightGBM) to detect and fix data leakage, pre-split scaling or oversampling contamination, identifier memorization, temporal leakage, and imbalanced accuracy traps. Activate when the user asks to train a model on a CSV, debug suspiciously high validation accuracy, clean a dataset, or review an ML pipeline.

Say what this does and when an agent should reach for it. This is the line that decides whether a skill is used at all, so write it for the agent choosing between tools rather than for a person browsing a list.

Say what this does and when an agent should reach for it. This is the line that decides whether a skill is used at all, so write it for the agent choosing between tools rather than for a person browsing a list.

Audits CSV datasets for missing values, duplicate rows, inconsistent data types, invalid values, and potential outliers. Use when a data analyst needs a reliable data-quality report and safe cleaning recommendations.

ExamPilot AI creates realistic exam study schedules from a syllabus, deadlines and available hours. Use when students ask "make a study timetable from my syllabus", "plan my exam preparation", "I have 5 days to finish these units", or need to recover after missing study sessions, even if they never mention ExamPilot by name.

Organizes everyday health information into symptom logs, medication lists, medical-record timelines, lab-report comparisons, and nutrition and wellness plans. Use when users track symptoms, compare blood reports, organize medicines, plan protein-rich meals, or prepare for a healthcare visit; also helps when someone feels unwell or has scattered health notes but is unsure what kind of help to ask for. Provides general education only, not medical advice, diagnosis, or treatment.

Say what this does and when an agent should reach for it. This is the line that decides whether a skill is used at all, so write it for the agent choosing between tools rather than for a person browsing a list.

Tailor a student's resume to a specific campus placement or internship job description (JD) without inventing anything. Use when a student or fresher shares a resume and a JD, or asks to tailor, customise, improve or make a resume ATS-friendly for a company or role, or asks what is missing for a role. Outputs an eligibility check, gap report, rewritten bullets using only confirmed facts, and a checklist. Not for experienced hires, cover letters or interview coaching.

Audits a student or beginner ML/DL project (notebook, script or repo) for data leakage, bad train/test splits, inflated accuracy, wrong metrics on imbalanced data and README claims the code does not support. Use when the user says things like "review my ML project", "is my model accuracy real" or "prepare me for my project viva". Also use when a user shares a notebook with very high accuracy (95% or more) or a README with performance claims, even if they never ask for an audit.

Say what this does and when an agent should reach for it. This is the line that decides whether a skill is used at all, so write it for the agent choosing between tools rather than for a person browsing a list.

Use when a user asks to analyze a CSV or spreadsheet, clean missing values, find duplicate rows, explore patterns, or explain dataset results. Trigger phrases include "analyze this dataset" and "clean my CSV". Also use this skill when someone needs a data-quality review but does not know which analysis to request.

Guide students, beginners, and small teams from a software project idea to a scoped MVP, technical architecture, actionable build plan, testing strategy, README, and demo. Use when planning, building, debugging, reviewing, or preparing to present a software project.

Audit an Indian student's scholarship application readiness against supplied official scheme criteria. Check eligibility evidence, required documents, missing information, deadlines and source reliability. Use when a student wants to check a scholarship application before submission.

Find errors in my C code, explain this compiler error, or fix my C program. Use when a beginner shares C source code, a compiler message, a runtime problem, or unexpected output and wants to understand and correct the issue.

Migration Guard reviews SQL database migrations for data-loss risks, production locks, unsafe backfills, rollback gaps, and incompatibility with rolling application deployments. Use when a user asks to review a database migration, check whether a schema change is safe, audit a migration before deployment, or assess a risky ALTER, DROP, constraint, index, rename, type change, or backfill. Use it even when the user does not explicitly say “database migration” but provides SQL or schema changes and asks whether the change could break production, lose data, cause downtime, or fail during a rollout. Do not use it for general SQL questions unrelated to schema changes.

Cleans messy Indian government open-data CSV and XLSX files (data.gov.in, state portals, ministry, census, rainfall, or health tables). Use when the user asks to "clean this dataset", "fix Indian numbers", "prepare data.gov.in file", or shares tabular data with title rows above the header, lakh-style numbers (1,23,456), NA/--/N.A. placeholders, Orissa/Uttaranchal names, dd/mm/yyyy dates, or Total rows mixed in the data. Not for general CSV analysis, charts, or non-Indian data.

RepoMedic is an evidence-based software debugging skill. Use when an agent needs to investigate a bug even if the user does not explicitly ask for debugging. Trigger on requests such as "fix this error", "why is my API returning 401", "my tests are failing", "debug this crash", or "find the root cause". It guides agents to inspect relevant evidence, separate confirmed causes from hypotheses, propose minimal fixes, create regression tests, and report honestly which checks were or were not run.

Verifies and compares Indian vocational courses and training providers using reliable evidence. Use when someone asks "Is this training institute trustworthy?", "Are this course's fees and certificate genuine?", "Can I trust this placement claim?", or wants to compare vocational courses, even when they do not explicitly ask for verification.

Cross-agent messaging via SQLite. Send messages between Claude Code, Codex, Gemini CLI, and other agents. No daemon, no network, no dependencies beyond bash and sqlite3.

Implement Flutter, React Native, or native Swift apps. Use for mobile screens, widgets, platform integrations, and application data flows.

Security audit of Solidity code while you develop. Trigger on "audit", "check this contract", "review for security", "loop mode", "run the auditor in loop mode", "run 3 passes". Modes - default (full repo) or a specific filename. Loop mode runs several passes in one scan, each pass told what the earlier ones found, and ends in one combined report; it remembers findings between scans in a ledger.

Use when working with iOS/macOS Keychain Services (SecItem queries, kSecClass, OSStatus errors), biometric authentication (LAContext, Face ID, Touch ID), CryptoKit (AES-GCM, ChaChaPoly, ECDSA, ECDH, HPKE, ML-KEM), Secure Enclave, secure credential storage (OAuth tokens, API keys), certificate pinning (SecTrust, SPKI), keychain sharing across apps/extensions, migrating secrets from UserDefaults or plists, or OWASP MASVS/MASTG mobile compliance on Apple platforms.

ARIS (Auto-claude-code-research-in-sleep) infrastructure setup and configuration. Configures MCP servers for cross-model adversarial review, installs Python tools, and validates environment. Run this first before using any other ARIS skills. Use when: setting up ARIS, configuring review servers, "aris setup", "配置ARIS".

Operate Tencent Cloud control-plane resources (monitoring/alarms, CLB, CAM roles, COS, MySQL, SCF) via cloud APIs when no dedicated MCP tool covers the task. Use when a task needs control-plane operations beyond CloudBase's own tooling, or when a callCloudApi call failed and needs classifying.

MiniMax multimodal model skill — use MiniMax Multi-Modal models for speech, music, video, and image. Create voice, music, video, and images with MiniMax AI: TTS (text-to-speech, voice cloning, voice design, multi-segment), music (songs, instrumentals), video (text-to-video, image-to-video, start-end frame, subject reference, templates, long-form multi-scene), image (text-to-image, image-to-image with character reference), and media processing (convert, concat, trim, extract). Use when the user mentions MiniMax, multimodal generation, or wants speech/music/video/image AI, MiniMax APIs, or FFmpeg workflows alongside MiniMax outputs.

小红书笔记采集 → 统一 frontmatter Markdown → 爆款拆解 + 衍生选题。 支持笔记链接和 xhslink 短链；爆款拆解按「人群×场景×痛点×情绪×钩子」生成可复用选题。

Posts content to WeChat Official Account (微信公众号) via API or Chrome CDP. Supports article posting (文章) with HTML, markdown, or plain text input, and image-text posting (贴图, formerly 图文) with multiple images. Markdown article workflows default to converting ordinary external links into bottom citations for WeChat-friendly output. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "贴图/图文/文章".

AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.

AI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.

Converts X (Twitter) tweets and articles to markdown with YAML front matter. Uses reverse-engineered API requiring user consent. Use when user mentions "X to markdown", "tweet to markdown", "save tweet", or provides x.com/twitter.com URLs for conversion.

1:1 rebuild of award-winning creative websites (WebGL / scroll-animation / portfolio sites). Evidence-driven pipeline - mirror-first forensics, line-number-traceable reverse engineering of minified bundles, verbatim porting, quantitative verification gates. Use when user asks to "复刻网站", "重建网站", "1:1 rebuild", "clone this site", or provides a URL of a creative/award site to reproduce.

Build MCP servers in Python with FastMCP. Define tools / resources / prompts, build the server, test locally, deploy to FastMCP Cloud or Docker. Use whenever the user mentions building an MCP server, exposing tools to LLMs, FastMCP, building a Claude integration, or troubleshooting FastMCP module-level server, storage, lifespan, middleware, OAuth, or deployment errors.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Security audit and vulnerability scanning for AI agent skills before install. Detects prompt injection, dangerous code, exfiltration, credential harvesting, and supply chain risks. Use when evaluating untrusted skills or gating installs.

Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.

Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific talk. Provides slide structure, design templates, timing guidance, and visual validation. Works with PowerPoint and LaTeX Beamer.

Use when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.

Use when search or investigation could run forever. Set an explicit good-enough threshold first, then stop at the first option that clears it.

A skill written the way the whole surface was written before 2026-10-05. The gate must reject it.

Set up or run the token build pipeline — transform the DTCG tokens/*.json (source of truth) into platform artifacts (CSS variables, Tailwind @theme, JS/TS, iOS Asset Catalog, Android, Compose) with Style Dictionary / Tokens Studio / W3C DTCG export. Use when the user wants to generate platform theme files from tokens, wire token CI, or multi-platform token output.

Scaffold a new design-product project that matches the recommended Claude Code layout (the reference structure). Use when starting a fresh product/app that will be built with this design system.

Upgrade an existing website or app to premium quality without breaking functionality — audit the current design, identify generic/AI tells, then apply taste and system rules surgically. Use when the user wants to improve, modernize, polish, or "make better" an existing UI/codebase.

Optimize UI performance against Core Web Vitals — LCP, INP, CLS — with loading/code-split strategy, layout-shift prevention, and animation performance rules. Use when the user wants to improve speed, fix jank or layout shift, hit Web Vitals budgets, or make a UI feel fast on low-end devices.

Map this token system to or from any external design system (Material Design 3, Apple HIG, Fluent, Carbon, Ant, shadcn/ui, Radix, Chakra, Mantine, Bootstrap…) — adopt their look, build on their stack, or migrate between systems. Use when the user mentions interop, migration, or a specific design-system/component-library bridge.

Govern how the design system evolves — SemVer for tokens/components, the contribution workflow, deprecation policy, and change communication. Use when the user wants to add/promote/deprecate a component or token, decide a version bump, set up a contribution process, or keep the system from fragmenting.

Run the one-command quality gate and report the real N/N result. Use before claiming any build/review is done.