Borrowing it
Nothing to install: this file belongs to dbcls/togomcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dbcls/togomcp/main/.claude/skills/qa-generator/SKILL.mdgit clone --depth 1 https://github.com/dbcls/togomcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dbcls/togomcp/qa-generator)<a href="https://agentmods.dev/skills/dbcls/togomcp/qa-generator"><img src="https://agentmods.dev/badge/skills/dbcls/togomcp/qa-generator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dbcls/togomcp/qa-generator"><img src="https://agentmods.dev/badge/skills/dbcls/togomcp/qa-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 36 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00186 | $0.05538 |
| Opus 5.5 | $0.00074 | $0.02215 |
| Sonnet 5.5 | $0.00037 | $0.01108 |
| Haiku 4.5 | $0.00019 | $0.00554 |
Grade A, and why
qa-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 28d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TogoMCP Benchmark QA Generator
This skill produces new, fully-validated benchmark questions one at a time, enforcing the type-first creation protocol and the 28-category QA review that the existing 100 questions passed. A question is only useful if it requires live RDF access to answer and is arithmetically self-consistent; this skill exists to guarantee both, not just to emit plausible-looking YAML.
It runs in a Claude Code environment with the TogoMCP MCP server (SPARQL + REST wrappers + TogoID), OLS4 (ontology lookup), and PubMed/NCBI tools connected, plus filesystem access. Use those tools freely — that is the normal mode here. Either TogoMCP server works — they expose the identical tool surface, differing only in the tool prefix (mcp__togomcp-dev__* vs mcp__togomcp__*). Prefer the local togomcp-dev when present because its registry is fresher (it picks up new endpoints.csv rows immediately); the remote togomcp is a fine fallback for the established databases, with the one caveat that its registry can lag, so a recently added database may not be available there yet. OLS4 and PubMed are separate servers, unaffected by which TogoMCP you use.
The Five Hard Rules
1. Nothing is invented. Every SPARQL query in sparql_queries must execute successfully against the real endpoint before it is written. Every result_count, every triple in rdf_triples, and every fact in ideal_answer must come from an actual query result you ran this session. A fabricated count or triple is worse than a missing one — it silently poisons the benchmark.
2. Question scope = query scope (no sampling). If exploration discovers N ontology terms (GO/MONDO/ChEBI/EC/MeSH), the SPARQL VALUES clause must use all N, including all getDescendants(). A "which/how many/list all" question must query the entire set, never a subset. This is the single most common way a question silently becomes wrong — see references/coverage-gaps.md.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 28d ago Changed · +2 lines a98b28eeef87
- 1mo ago Changed · +1 lines 76d7dbc80ecf
- 2mo ago First seen · 184 lines · 186 tokens per session scan A ebff5511db4a
qa-generator is a skill published in the GitHub repository dbcls/togomcp (20 stars, last pushed 2d ago), licensed MIT. It adds 186 tokens to every session and 5,538 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
open-ontologies
AI-native ontology engineering using 110 MCP tools backed by an in-memory Oxigraph triple store. Build, validate, query, and govern RDF/OWL ontologies with a generate-validate-iterate loop. Use when building ontologies, knowledge graphs, RDF data, SPARQL queries, BORO/4D modeling, SHACL validation, clinical…
post-cortex-memory
Long-term project memory through the post-cortex MCP server (tools named session, semanticsearch, updateconversationcontext, assemblecontext, queryconversationcontext, getstructuredsummary, manageworkspace, manageentity, admin). Use it whenever those tools are available and the work could benefit from what was learned…
api-simulation
Runs your code for real against stand-ins for the HTTP services it calls, served together as one environment on one local port or one deployed URL, whether that code is a service you're changing, a frontend, a test suite or a demo. Use when you add or change code that calls other services and need to run it, test it…
application-testing
Sets up, runs, debugs, and interprets results from postman application test — the Postman layer that runs your Playwright tests, captures their network traffic, matches it against a collection contract, runs pm.test assertions, and publishes results to Application Inventory. Covers the Postman side of the integration…
variables
Use when parameterizing requests across environments, choosing variable scopes, chaining values in scripts, or referencing credentials without committing or exposing them. Keeps one reusable collection while separating target configuration from secret values. Use for requests such as "where should I put this API key".
api-mocking
Finds, builds, runs and publishes a stand-in for one API — the owning team's published mock when there is one, otherwise one built from its spec or collection that behaves like the real API, stateful when callers write then read. Use when something needs an API that isn't built or reachable yet (a frontend, client or…