1.2K skills · sorted by relevance
Canonical PR description template for every PR shipped from this harness, with a validator that enforces the required sections. Use when opening or editing a PR (the /ship and /forge-ship steps), or when asked for the standard PR format or to check a PR body.
The English summary is being prepared. Showing the original description.
Meta-skill for creating Agent Forge skills under .claude/skills/ with SKILL.md, optional references/ and scripts/, and Bun scaffolds. Use when the user wants to add or author a skill, scaffold a new skill folder, or align skill docs with harness conventions (JSON script output, Beads for tasks).
The English summary is being prepared. Showing the original description.
Detect Kerberos Golden Ticket forgery by analyzing Windows Event ID 4769 for RC4 encryption downgrades (0x17), abnormal ticket lifetimes, and krbtgt account anomalies in Splunk and Elastic SIEM
The English summary is being prepared. Showing the original description.
Create and edit videos using a measured reference style for color and cutting rhythm. Combine generated clips, existing footage, overlays, and 3D props, then check visual measurements and deliver both a video and an editable timeline.
Design an OpenClaw agent persona from preferences or random draws. Build a consistent background, personality, behavioral boundaries, name, SOUL.md and IDENTITY.md files, plus an avatar prompt, with optional image generation through an approved skill.
Review Laravel authentication, permissions, database operations, forms, APIs, and production settings for security weaknesses. Use implementation examples to address unsafe input handling, exposed secrets, session risks, and insufficient access controls.
Review Solidity automated market makers, liquidity pools, and token swaps using security checklists and safer code examples. Check repeated calls during transfers, manipulated prices, share calculations, swap limits, and administrator permissions.
Keep project context across Claude Code sessions by saving progress, decisions, blockers, and next steps. Commands retrieve project briefings, while a session-start hook loads a compact summary to help resume previous work.
Inspect a site's login flow for token leaks, missing protections against forged requests, exposed session cookies, and OAuth configuration issues. Produce a structured findings report with severity ratings and a pass, warn, or fail verdict.
Review communication between different websites for security issues. Inspect code and browser behavior to identify overly broad CORS permissions, unchecked message senders, missing request protections, and unsafe redirects, then propose fixes and browser checks.
Use Biohub’s Python SDK to complete protein sequences with ESM3, extract numerical sequence representations with ESMC, and predict all-atom structures with ESMFold2. The skill guides local or hosted inference, input validation, and output checks.
Trace server-side request forgery, where a server fetches a supplied URL, through internal services and metadata endpoints in a CTF sandbox. Document credential scope and distinguish successful token extraction from access actually accepted by another service.
Evaluate whether a fine-tuned model is ready for release by checking training data, general capability loss, comparisons with the base model, and staged production rollout. Produces an evidence-based promotion or rejection report with one prioritized remedy when rejected.
Build and modify Java plugins for Minecraft servers running Paper, Spigot, or Bukkit. The skill covers commands, event handling, minigames, and saved player progress, with checks for configuration, task cleanup, and server API compatibility.
Support authorized Active Directory assessments of DCSync, which abuses directory replication rights to obtain credential data. Cover replication permission review, Golden Ticket persistence testing, detection validation, and documentation of evidence and remediation recommendations.
Design memory systems that help AI agents retrieve relevant past information. Choose short-term and long-term memory structures, compare vector storage options, and review document splitting and retrieval strategies for different kinds of knowledge and experience.
Add GBrain memory to an existing agent or connect a hosted brain while preserving current instructions and identity. Start with storage and keyword search that need no API key, then verify saving, retrieval, and recall across conversations.
Save a thought, note, or text excerpt to GBrain’s database and a Markdown file with one command. Automatic naming, titles, and metadata make individual captures immediately searchable, with a receipt confirming the save.
Review bulk deletions before they happen by showing affected data, recovery options, and alternatives. The skill asks for explicit user consent and records confirmed deletions, covering files and gbrain data through agent procedures.
Save facts, decisions, and discoveries to agentmemory for future sessions. The skill preserves the user's wording, adds specific search tags and referenced file paths, and confirms which terms can retrieve the saved knowledge.
Create and audit the files and routines that guide coding agents across sessions. It organizes instructions, progress tracking, verification, scope boundaries, and handoffs, with scripts for setup, structural checks, and shareable assessment reports.
Prepare a Web3 bug bounty investigation by scoring targets, setting up analysis tools, reviewing past audits, and tracing how funds move. Use the findings to prioritize smart contracts and assess whether suspected issues have concrete impacts.
Examine a DeFi yield aggregator, a protocol that collects investment returns, for missing role assignments and failures caused by tiny rewards. Includes a ten-category review, reproducible test templates, and vulnerability report drafts.
Build runnable Foundry tests that demonstrate smart contract vulnerabilities with before-and-after logs and assertions. Use fork tests, which copy blockchain state, and test helpers to reproduce known DeFi incidents or prepare evidence for a report.