Agent skills

Start dev server and interact with the platform via agent-browser.

Fetch OpenShift release dates and metadata from Sippy API

Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering.

Compare HEAD with the latest published npm versions and list all unpublished changes by release layer.

Hunting skill for idor vulnerabilities. Built from 26 public bug bounty reports. Use when hunting idor on any target.

Automate Getform tasks via Rube MCP (Composio).

Generate getopts-based argument parsing for shell scripts with short/long options and validation.

Write copy following Sentry brand guidelines.

Finds real correctness bugs in code changes.

This skill should be used when the user asks to "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or…

Initial Malga integration journey. Triggers: "start Malga", "X-Client-Id", "X-Api-Key", "sandbox vs production Malga", "activate account…

Use when generating or planting GitGuardian honeytokens, canary tokens, decoys, or tripwire credentials.

Scan a developer's entire machine for credentials across local git repositories, dotfiles, ~/.aws/credentials, ~/.kube/config…

GitHub CLI (212 man pages).

Enforces authenticated gh CLI workflows over unauthenticated curl, WebFetch, and MCP fetch patterns.

Fetch GitHub issues, select candidates, spawn background fix agents, open PRs, and optionally process PR review comments.

Analyze GitHub Actions failures and identify root causes

Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting…

Deep integration with Ghidra and IDA Pro for binary analysis and reverse engineering

Manus-level AI browser agent that drives Dhruv's REAL logged-in Chrome (any profile — AIV, Onsite, etc.) via natural-language commands.

Guidance for safe, reliable GitHub CLI workflows across issues, pull requests, and reviews.