Find Vendor

Trust Score 70/100

Orchestrate natural-language vendor searches: parse requests to structured JSON, rank candidates from Baserow, and summarise feedback with an LLM for hiring or

triggers:find vendorvendor searchrank vendorsbaserow rankingparse requestsourcing

GitHub SKILL.md

What it does

Find Vendor is an end-to-end orchestrator that turns a manager's natural-language request into a structured search and ranked candidate list. It parses the request into a JSON schema, queries Baserow customer/vendor tables, runs ranking scripts, and produces an LLM-powered summary of candidate strengths, risks, and specialty matches. Outputs are formatted for chat and saved to temporary files for follow-up.

When to use it

Use this skill when a manager describes the specialist they need in plain language (translation, editing, proofreading, or domain-specific tasks like game genres/franchises). It's useful for sourcing contractors, shortlisting candidates, and preparing concise comparative summaries for decision-making.

What's included

Scripts: references to ranking script (agent2_rank_baserow.py) that integrates with Baserow; expects several Baserow env vars for API access.
References: detailed schema and static specialty tables in the SKILL.md that map domain keywords to table IDs.
Instructions: stepwise guidance for parsing NL→JSON, running the ranking script, loading raw Baserow feedback via MCP, and constructing final per-candidate summaries. The SKILL.md also specifies required env vars and where outputs are saved.

Compatible agents

Designed to run where Python and MCP/Baserow access are available; integrates with MCP tools and expects environment variables for Baserow. Best used in agent hosts that can run external scripts and call mcp__baserow__list_rows.

Audit Summary

Vendor search orchestration skill for a translation/localization company. Accepts natural-language requests, converts to structured JSON, ranks candidates via Baserow API, and summarizes feedback with LLM analysis. All instructions are in Russian, limiting accessibility. The skill references an external script (agent2_rank_baserow.py) that isn't bundled, so it cannot run standalone without the parent repo.

Watch Out

All documentation and prompts are in Russian — non-Russian speakers cannot use it
Requires 5 Baserow environment variables (BASE_URL, API_TOKEN, and 3 table IDs) specific to one company's setup
References external script scripts/agent2_rank_baserow.py not included in the skill bundle
Uses 'py' command instead of 'python3' which may not work on all systems

Notes

Well-structured orchestration skill for a specific business workflow. Security is clean — no hardcoded creds, uses env vars for API tokens, no destructive commands. Main issues: (1) external script dependency makes it non-functional standalone, (2) Russian-only documentation severely limits audience, (3) hardcoded Baserow table IDs in specialty catalog are brittle and org-specific. Useful only for the specific company that authored it.

Information

Repository: pos-sprint
Stars: 8

Trust Score

Overall70

Security93

Code Quality52

Architecture41

Usefulness18

Related Skills

Starlark Dev

Create, debug, and test Kurtosis Starlark packages — write package structure, run dry-runs, and inspect plan execution for reliable orchestration.

Maestro Orchestrate

Orchestrates complex engineering workflows with enforced design and approval gates, child-agent delegation, and session state management.

Run Execute

Orchestrates execution of work items across modes (autopilot, confirm, validate) with scripted init/complete tooling, plan/test/report artifacts and strict gati

Overnight — Autonomous Long-Running Coding

Orchestrates long-running coding goals: decomposes objectives into atomic tasks, dispatches isolated worktree workers, verifies acceptance criteria, and merges

tmux Remote Control

Control tmux sessions for interactive TTYs: send keystrokes, capture panes, orchestrate parallel coding agents, and monitor output safely.

Build Unplanned Feature

Orchestrates ad-hoc feature development: requirement gathering, planning, implementation and validation across task-planning, implementation, and validation loo

AI Pair Collaboration

Orchestrates a small heterogeneous team of AI agents (author/developer + Codex reviewer + Gemini reviewer) to produce and review content or code in a coordinate

Box0 (b0)

Run and coordinate parallel AI sub-agents locally or on a server to delegate reviews, tests, research, and other specialist tasks.

Back to Skills