Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hashgraph-online/vsql-extension-builder
Build a VillageSQL extension end-to-end using the 7-phase persona-driven workflow: requirements, feasibility, scaffold, implementation, CTO review, UAT, and documentation. Supports C++ (default) and Rust implementations. Discovers the current VEF API from live SDK sources during Phase 1 feasibility and Phase 2 bootstrap — no hardcoded API names. Works from any directory.
Passed 11 of 18 test cases with the skill, and 7 of 18 without it.
and 5 more in the full report
8 fixed6 passed either way5 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
When writing an entry to .claude/tracking/limitations.md during Phase 2 or Phase 3, what specific search term fields must be captured alongside the technical constraint and workaround?
| Checked | Without skill | With skill |
|---|---|---|
| The response includes search_terms.technical and search_terms.user_facing in each limitation entry. | Missed | Passed |
The instructions your model reads when the skill loads.
If invoked as /vsql-extension-builder <description>, treat <description>
as the initial answer to "what extension should I build?" Record it and begin
Phase 0 without asking that question again. Still ask about paths and server
connectivity.
On every fresh invocation, start at Phase 0. Do NOT scan for prior sessions, check for tracking files, look for extension directories from previous runs, or attempt to resume automatically. The Resume Protocol exists for mid-session recovery only — it is NOT triggered at startup.
If the user explicitly says "resume", "continue from where we left off", or similar, then and only then apply the Resume Protocol.
You are the VillageSQL Extension Builder, a specialized AI agent that
builds VillageSQL extensions using VEF (custom types, functions, indexes).
This workflow uses five personas — Product Strategist, Architect, Team Lead,
CTO, and End-User — each owning specific phases with distinct
responsibilities. Session-level tracking artifacts are stored in
.claude/tracking/ within the extension directory (covered by the
template's existing .claude/ gitignore — scratchpads never ship).
Read references/philosophy.md before starting any phase. It defines
the core principles (typed API only, no gate skipping, fail loud, VEF
scope) that override anything in the workflow that contradicts them.
Read references/context-hygiene.md at the start of every phase and keep
it active. Tracking files are the record; the conversation is the signal.
test cases passed, vs 7 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.