Tool

Description

Example Prompt

algo_run_sandboxed

Runs code in Python, JS, TS, C++, C, or Go in an isolated process with strict time and memory limits.

"Run this C++ solution with the test input 5\n1 2 3 4 5."

algo_run_docker

Runs code inside a zero-trust ephemeral Docker micro-container (python:alpine, node:alpine, gcc:alpine).

"Run this untrusted script inside a Docker sandbox."

algo_stress_test

Automated Differential Tester: Compares an optimal algorithm against a brute-force baseline on randomized inputs to find failing edge cases.

"Stress-test my Dijkstra implementation against a brute-force solution to find where it fails."

algo_check_plagiarism

Token-based AST code similarity checker that compares two code submissions and detects suspicious duplicated logic.

"Check if solution_a.py and solution_b.py have plagiarized logic."

algo_generate_edge_cases

Generates adversarial corner cases (min $N=1$, max constraints, identical items, extreme negatives, disconnected graphs).

"Generate edge testcases for a binary tree problem."

Tool

Description

Example Prompt

db_generate_erd

Parses SQL CREATE TABLE and foreign key statements to automatically generate Mermaid Entity-Relationship Diagrams.

"Generate a Mermaid ERD diagram from this schema.sql file."

Tool

Description

Example Prompt

perf_audit_assets

Scans directory for uncompressed raster images (>250KB) and calculates bandwidth savings from WebP/AVIF conversion.

"Audit the images in /public and show me how much size we can save with WebP."

perf_check_headers

Audits HTTP response headers of a web application for Gzip/Brotli compression, Cache-Control, and security headers.

"Check the performance and security headers on http://localhost:3000."

Tool

Description

Example Prompt

doctor_diagnose_project

Auto-detects runtime (Node, Next.js, Python, Docker), missing node_modules, missing .env, and unconfigured virtual environments.

"Diagnose why this repo won't start."

doctor_check_env

Diffs .env against .env.example to detect missing or surplus keys.

"Check if my .env is missing any keys from .env.example."

doctor_port_inspect

Identifies which background processes and PIDs are locking ports (3000, 6379, 5432).

"Check why port 6379 is occupied."

Tool

Description

Example Prompt

security_scan_secrets

Scans codebase for leaked OpenAI keys, AWS access tokens, GitHub PATs, and private keys.

"Scan my repository for accidentally committed secrets."

security_auto_sanitize

Auto-replaces detected secrets with process.env references and populates .env.example.

"Sanitize all hardcoded keys across the project."

Tool

Description

Example Prompt

api_test_request

Executes live HTTP calls (GET, POST, PUT, DELETE) with headers, auth, and query params — measures latency (TTFB) and formats JSON.

"Send a GET request to https://api.github.com/zen and show the latency."

api_generate_mock_data

Generates realistic synthetic mock datasets (users, products, posts, transactions) for frontend and backend testing.

"Generate 10 mock user records with IDs and emails."

Tool

Description

Example Prompt

docs_check_broken_links

Scans all markdown files (.md, .mdx) to detect broken internal links and dead file references.

"Check all markdown files in the repo for broken links."

docs_auto_fix_links

Automatically updates and rewrites broken markdown links when target files have moved.

"Fix broken links in the docs/ folder."

docs_extract_code_snippets

Extracts all fenced code blocks from markdown documentation for quick inspection.

"Extract all code snippets in docs/ so we can verify their syntax."

code_find_todos

Scans the codebase for TODO, FIXME, HACK, and BUG comments with line numbers and file paths.

"Find all TODO and FIXME comments in the codebase."

code_inspect_heavy_dependencies

Inspects package.json to identify bloated dependencies (moment, lodash, monaco, katex) with optimization tips.

"Check if we have heavy dependencies slowing down our bundle."

Tool

Description

Example Prompt

git_generate_changelog

Parses conventional git commit history between tags and outputs a clean markdown changelog.

"Generate a changelog for all commits since v1.0.0."

git_pr_readiness_check

Verifies uncommitted files, unpushed commits, and branch health before opening a Pull Request.

"Check if my branch is ready for a Pull Request."

git_generate_pr_description

Generates a structured markdown Pull Request description summarizing branch commits and diffs.

"Generate a structured PR description for my current branch."

problem_fetch_codeforces

Fetches problem statements, sample inputs/outputs, tags, and contest limits from Codeforces.

"Fetch the details for Codeforces problem 2060A."

ci_generate_workflow

Generates production-ready GitHub Actions CI/CD workflows for Next.js, NPM Publishing, Docker, or Python.

"Generate a GitHub Action workflow to automatically publish this package to NPM."

Skill Name

What It Instructs the AI Agent to Do

campus-fyp-architecture

Plans and documents university Final Year Projects (FYP) with C4 architecture diagrams, tech comparisons, and IEEE Std 830 SRS chapters.

campus-ieee-citation

Formats online software, journals, DOIs, and papers into strict IEEE referencing format.

campus-lab-report-generator

Auto-generates structured IEEE 2-column practical lab reports and experiment write-ups.

campus-git-team-workflow

Guides student group projects on feature branching, rebase strategies, and conventional commits.

campus-presentation-script

Generates 10-minute slide outlines and word-for-word viva defense speaking scripts.

campus-assignment-cleaner

Pre-flight LMS assignment validator (strips node_modules/.DS_Store, checks student ID headers).

campus-hackathon-fast-scaffold

10-minute rapid prototyping architecture for 12h/24h hackathons (SLIITXtreme).

campus-dsa-visualizer

Generates step-by-step ASCII memory traces for LinkedLists, BST trees, DP tables, and Graphs.

Skill Name

Description

algo-stress-testing

Differential testing against brute-force baselines to find edge-case failures.

algo-edge-case-generator

Generates corner cases ($N=1$, bounds, extremes, disconnected graphs).

algo-plagiarism-detector

AST token similarity analysis between code submissions.

algo-complexity-analyzer

Asymptotic Big-O time and space complexity auditing.

Skill Name

Description

frontend-clean-ui

Modern, high-contrast, accessible SaaS UI design with Tailwind and dark mode tokens.

react-state-architecture

State architecture using Zustand, TanStack Query, and React Server Components.

Skill Name

Description

backend-rest-api-design

Production REST API design with Zod schemas, status codes, and cursor pagination.

database-migration-guardian

Zero-downtime database schema migrations, indexes, and safe alterations.

db-architect

Parses SQL DDL statements into visual Mermaid ER diagrams.

api-mock-generator

Generates realistic synthetic datasets (users, products, transactions).

Skill Name

Description

ai-rag-pipeline-architect

Retrieval-Augmented Generation (RAG) pipelines with vector embeddings and reranking.

ai-prompt-evaluator

System prompt engineering, red-teaming, and structured JSON output validation.

test-unit-generator

Vitest / Jest unit test suites with parameterized edge cases and 100% coverage.

test-e2e-playwright

Resilient Playwright browser test specs with user-facing accessibility locators.

devops-dockerfile-optimizer

Secure multi-stage Dockerfiles with layer caching and non-root users.

devops-vercel-render-deploy

Cloud hosting configuration for Vercel, Supabase, and Render.

repo-doctor

Identifies broken runtime dependencies, missing packages, and setup errors.

env-sync

Compares and synchronizes .env against .env.example.

port-inspector

Resolves socket collisions (EADDRINUSE) and identifies holding PIDs.

ci-workflow-architect

Generates GitHub Actions CI/CD workflows for Node, Docker, and Python.

security-auditor

Pre-flight scanner to detect and auto-sanitize leaked API credentials.

docs-broken-link-checker

Scans markdown files for broken internal links and dead references.