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.

Tests whether an agent turns API test evidence into accurate, scoped and reproducible findings without leaking secrets or claiming unverified fixes.

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.

Evaluate whether an agent correctly checks research claims against supplied evidence, identifies contradictions, and reports insufficient evidence without inventing support.

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 that an agent using the cve-patch-sweep skill finds recent severe CVEs across dependencies, runtimes and certificate trust, fixes them safely, and refuses unsafe shortcuts.

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.

Measures whether an agent validates, normalizes, formats and masks Indian identifiers, rupee amounts, dates and financial years correctly instead of guessing — 26 cases with deterministic must-contain / must-not-contain checks and per-category rubrics; companion to the india-data-formats skill.

Checks whether an agent ranks the right suspicious files with evidence and avoids auto-fixing or claiming an unproven root cause.

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.

Measures whether a career-mentor AI provides personalized, realistic, actionable career roadmaps for students without inventing resources or promising guaranteed jobs.

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.

This evaluation tests whether the skill reliably checks hackathon submissions against provided rules without inventing facts or marking unsupported requirements as verified.

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.

Measures whether an agent using the data-janitor skill cleans CSV files safely: profiling first, planning before changing, preserving the original, protecting identifiers, never guessing ambiguous dates, and delivering a complete audit trail.

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.

One-sentence benchmark measuring whether an AI agent creates feasible, syllabus-grounded exam study plans, respects time limits, handles missing information, recovers from missed sessions, and avoids unsupported score guarantees.

Evaluates whether an everyday health and wellness assistant responds safely to symptoms, medication questions, lab reports, nutrition requests, eye red flags, privacy concerns, and health-record organization.

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.

Checks whether an agent tailors a fresher's resume to a job description using only facts the student confirms, and refuses to invent skills.

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.

Whether an AI skill consistently follows its instructions and produces accurate, relevant, clear, and useful responses to user requests.

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.

Measures whether an AI agent reliably identifies production risks in database migrations and recommends safe rollout strategies.

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.

Benchmark testing messy Indian government table cleaning, entity mapping, and placeholder handling.

Measures whether RepoMedic ensures evidence-based debugging, honest test execution, and safe remediation without inventing root causes or fake test passes.

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.

Checks whether an AI agent helps Indian students evaluate vocational courses fairly by separating verified facts from provider claims, identifying missing evidence, and avoiding invented information.

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.

Checks whether a study plan is realistic, prioritized, includes breaks and revision, and stays within the student's available time.

Make specific lines, paragraphs, list items, tables and code blocks in markdown citable with short readable ^ids, cite them with links that carry a verifying quote, and check every reference with a script that reports dangling, stale and moved references instead of silently pointing at the wrong text. Use when writing or editing markdown that refers to other parts of itself or other files, when a person asks about "line 14" or "that paragraph", when reviewing docs for broken internal links, or when an agent must cite exactly which passage supports a claim.

Helps college students plan study time around subjects, exams, deadlines, and available hours. Use when a student asks for a study timetable, exam preparation plan, daily schedule, subject priority, or help managing limited study time. Trigger phrases include “make me a study plan” and “how should I prepare for my exams".

Troubleshoots deployment failures, build errors, missing dependencies, environment configuration issues, and application startup problems. Use when users ask "why is my deployment failing?", "fix my build error", or "my app will not start", even if they do not mention deployment troubleshooting or this skill by name.

Drafts a ready-to-file Right to Information (RTI) application under India's RTI Act 2005. Use when a user wants records, status or decisions from an Indian government body, e.g. pending scholarship, delayed pension, road work expenses, exam evaluation. Also drafts first appeals. Not for legal advice, court cases or private companies.

Checks whether an agent using rti-drafter writes correct, safe RTI applications and appeals without inventing fees, names or dates.

Diagnose and improve an AI agent's task workflow by reducing unnecessary steps, clarifying instructions, adding verification, and designing honest before/after evaluations. Use when an agent is slow, verbose, unreliable, repeats work, loses state, or needs reusable operating instructions.

Checks a C or Python assignment against its own spec before submission, like a strict autograder: file and zip names, function signatures, exact output format, banned headers or libraries, and edge cases the spec names. Runs the spec's samples and reports each requirement as PASS, FAIL or CANNOT VERIFY with evidence, without writing the solution. Use when a student says "check my assignment", "will this pass the autograder" or "review my lab before I submit", or shares a spec with code.

Measures whether an agent prechecks a student's C or Python programming assignment against its own spec the way a strict autograder would: it must catch spec violations (prompts in output, wrong file names, output format, unhandled edge cases, banned libraries, modified provided headers, code that runs on import), avoid inventing failures the spec never asked for, mark unverifiable requirements as such, and never write the graded solution, even when the student asks it to.

Checks whether an agent produces an evidence-based, safe, and actionable triage report for common Python and Node.js CI failures.

Analyze GitHub Actions CI failures for Python and Node.js projects, identify the most likely root cause from logs and repository evidence, and produce safe, evidence-based remediation and verification steps. Use when a user asks "why is my GitHub Actions build failing", says "debug this CI log", shares a failed npm ci, pytest, build, test, or lint job, provides workflow YAML, or asks why an automated check failed.

Helps agents plan and validate software ideas. Use when a user asks to evaluate a startup idea, research competitors, define an MVP, or test product demand.