Reverse engineering of compiled, packed, virtualized, or obfuscated targets for authorized CTF challenges. Use when the task is to understand, decompile, disassemble, or unpack an unknown executable across ELF, PE, Mach-O, APK, WASM, firmware, bytecode, or custom-VM targets.
Get an independent second-opinion review from Codex (the codex CLI) on code or implementation plans that Claude just produced. Use this whenever Claude has just finished writing or substantially editing code, or has just drafted an implementation/design plan, and an independent cross-check would add value — and…
End-to-end help filing an Indian ITR-2 for AY 2026-27 (FY 2025-26) for a salaried person with capital gains from shares and mutual funds, plus interest from RD/FD/savings. Parses Form 16, AIS, TIS, Form 26AS and broker/RTA capital-gains statements, reconciles them, classifies every gain under the current…
Scan a codebase and generate a new-developer onboarding guide as HTML, then publish to uselink. Use when the user wants to create a getting-started guide, onboard a new team member, or share 'how to work in this repo' docs.
Project bootstrap wizard — turns any codebase into a fully planned, agent-ready project with coordination docs, debugging guidelines, and parallel execution infrastructure. Use when starting work on a new or unfamiliar project that needs structure.
Runs a durable inspect/plan, implement, verify, and fresh-review loop toward an explicit repository goal. Preserves manually resumable state and uses oh-my-claudecode for autonomous continuation. Use only when the user explicitly invokes goal-loop.
Profile and explore datasets -- schema inference, distributions, missing values, outliers, correlations. Use when starting work with a new dataset or investigating data quality issues.
Runtime contract for the Just One Prompt Challenge. Invoked exclusively via the /justone and /justone-publish slash commands. Do NOT auto-trigger from general conversation — only act on this skill when one of those commands has been issued in the current turn.
MCP server for AI agents to create video ads via Streamable HTTP. Primary auth is OAuth 2.1 + Dynamic Client Registration (the modern Claude Desktop / Claude.ai / ChatGPT / Cursor "Connect" flow); long-lived API keys remain supported for headless clients.
Create supplier (AP) invoices in SAP S/4HANA Cloud Public or on-prem private edition via the SOAP A2X "Supplier Invoice ERP Create Request" service. Use whenever the user wants to post, create, add, generate, seed, or backdate supplier/vendor/AP invoices on S/4HANA — including phrases like "make me a few invoices"…
Build Simply-MCP servers with createTool(), createResourceTemplate(), code execution mode, or MCP Apps. Use when creating MCP servers, testing tool handlers, writing simply-mcp test harnesses, building servers where AI composes tool calls into JavaScript, deploying MCP servers to Cloudflare Workers, or creating…
Register a repo with the server-side census sync: hive repo add writes the durable repo registry (the sync daemon picks it up on its next tick — no restart), private remotes authenticate via a token env var NAME (never a stored secret), and hivehealth(includecensushealth=true) verifies both that the sync daemon itself…
Runs a Monday-morning review across a portfolio of accounts and produces a single prioritised action list with the reasoning shown. Use when the user says "weekly review", "what should I work on this week", "run my Monday review", or asks what has gone quiet across their accounts. Designed to be run as a scheduled…
Author a new terva skill, a reusable SKILL.md instruction set that terva loads on demand. Install it where terva discovers it, in the project .terva/skills/ or the global $TERVAHOME/skills/. Use for create/add/write-a-skill requests, not extensions.
Onboard a project into this governance layer: scan a repo that was pasted or cloned into Projects/, draft its bible from what the code actually shows, create its tracker and workspace pointer, register it in the composition manifest, and echo the reconstructed setup back for correction. Use this whenever the user…
Capture a failed or blocked task before it disappears. Categorizes the failure mode, extracts what was learned, and generates either a retry packet with the root cause fixed or an escalation message with specific decision points. Use whenever an agent returns a blocker, error, or partial result.
A review process for a pull request, which is a proposed set of code changes. It examines the changed code and its surrounding files for bugs, security problems, design issues, and lint errors.
Use TypeCast to turn LLM output into validated, typed JVM values. Reach for it whenever code calls an LLM and then parses/validates the response by hand: extraction of case classes or Java records from text, classification/routing via sealed traits, constraint enforcement with retry, streaming partial JSON into a UI…
Measure what a change to an AI coding setup actually saved, in dollars. Compares recorded before/after usage from the AI Insights MCP server — either two specific sessions by id, or everything in one period against another — and attributes the cost difference to the factor that moved it: fewer API calls, less context…
A Chinese company and executive background-check workflow examines a named person together with a company's Unified Social Credit Code, the identifier used for Chinese businesses.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: