realroc
10 verified skills10 total stars
ama-script-abuse-screening
Screen MongoDB conversation collections for script-driven abuse (prompt-injection templates, curl/empty user agents, probe-word floods, sessionless calls, multi-account IPs). Produces a two-tier triage report (confirmed abuse / suspicious) plus a multi-account IP list and a ban candidate CSV. Use when asked to find script callers, prompt-injection attempts, abnormal high-frequency users, accounts bypassing the web UI, or "who is using my AI as a cron job".
development1
backend-api-documenter
Automatically generate comprehensive backend API documentation in AGENTS.md format. Use when the user requests to: (1) Document backend API endpoints, (2) Update backend API specifications after code changes, (3) Create or refresh backend/AGENTS.md with complete API documentation including request/response schemas, business rules, and authentication details, (4) Generate API documentation from FastAPI route files
development1
ralph
Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.
development1
prd
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
documentation1
agents-md-generator
Generate comprehensive AGENTS.md documentation for backend projects with complete API specifications, business rules, data models, and data flows. Use when (1) Creating AGENTS.md from existing CLAUDE.md, (2) Documenting backend API modules with FastAPI routes, (3) Migrating documentation to AGENTS.md/CLAUDE.md symlink structure, (4) Adding complete API interface documentation to existing specs, (5) Creating module-level AGENTS.md for specific features (mcp, teamo_code, file_system, etc.)
tools1
shumei-user-violation-audit
Automate Shumei-based user violation-rate audits from MongoDB user and conversation collections, producing a CSV sorted by per-user request violation rate. Use when asked to screen users for forbidden/risky content, compute user-level violation rates, audit newly registered/free/suspicious users, or rerun a similar report with custom user filters, conversation filters, and a Shumei input-event key.
development1
ip-geo-distribution
Geolocate a batch of IPv4 addresses and produce a Markdown distribution table — Chinese IPs broken down by province (incl. HK/MO/TW), foreign IPs by country, with counts and percentages. Optionally exports CSV. Uses the free ip-api.com batch endpoint (no key, no signup, HTTP only, 15 batches × 100 IPs per minute). Use when the user pastes a list of IPs and asks for "IP 分布", "IP 归属地分布", "省份分布", "where are these IPs from", "geolocate these IPs", or wants an IP-region breakdown table.
development1
prompt-spec
Audit or rewrite a prompt into a six-section issue spec (Goal / Constraints / Non-goals / Verification / Architecture notes / Existing context) before any code gets generated. Use when the user pastes a vague request and asks for implementation, or explicitly says they want to frame an issue properly. Triggers on: prompt spec, audit this prompt, check my prompt, what's missing in this prompt, frame this issue, rewrite as a prompt spec, convert to issue spec, make this an issue, issue framing.
development1
newapi-usage-stats
Query a NewAPI gateway MySQL database for per-model usage stats (RPM/TPM, total tokens, peak minute) over a given time window, filtered by NewAPI username. Designed for the common case where NewAPI's MySQL is only reachable from inside a backend container running on a Tencent Cloud CVM. Uses Tencent Cloud TAT (Automation Tools) to run a read-only Python script inside that container; the container already holds the MySQL DSN in its environment, so credentials never leave the box. Use when asked to compute RPM/TPM for NewAPI models, audit askmanyai/teamo/upstream-user consumption, size rate-limit quotas from real traffic, or report per-model token volume for any hour/day window.
tools1
githire
GitHire's six-step AI-native engineering method: frame the issue, sandbox, AI execute, AI review, architect decision, ship. Use when planning or executing real work with AI agents — issue framing, prompt writing, PR review gating, architect handoff — or anytime humans-frame-AI-execute-architects-verify applies. Triggers on: use githire, githire methodology, issue-first onboarding, ai-native workflow, frame this issue, prompt spec, architect review, first PR for a candidate, hire through real PRs.
testing1