RuoYi AI is a full-stack enterprise platform for building AI assistants and agents that combine language models, knowledge bases, visual workflows, and multiple cooperating agents. Developers and organizations use it to manage model providers, retrieve information from documents, connect tools through MCP, and orchestrate agent workflows. The catalogue includes skills for working with RuoYi AI.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ageerle/ruoyi-ai --skill verificationgit clone --depth 1 https://github.com/ageerle/ruoyi-aiWrote 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/ageerle/ruoyi-ai/verification)<a href="https://agentmods.dev/skills/ageerle/ruoyi-ai/verification"><img src="https://agentmods.dev/badge/skills/ageerle/ruoyi-ai/verification.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00054 | $0.00604 |
| Opus 5 | $0.00027 | $0.00302 |
| Sonnet 5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
verification 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 9d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verification
Turn the task's acceptance criteria into trustworthy evidence. Verification is part of implementation, not a ceremonial final command.
Build an evidence matrix
For each requirement, identify:
- the observable behavior or invariant;
- the cheapest deterministic check that can falsify it;
- the artifact that records the result (test report, exit code, diff, event ledger, benchmark, or trace);
- gaps that require a broader integration test or human decision.
Use existing repository commands and focused tests first. Add a regression test when the behavior was previously broken or the boundary is subtle.
Derive semantic boundary cases
Turn every normative sentence in the requirement and relevant repository contract into a falsifiable example before accepting a visible green test.
- For parsers and serializers, preserve delimiter and escape provenance until structural tokenization is complete. Test adjacent escapes, escaped delimiters, whitespace normalization, malformed escapes, exact field counts, duplicates, empty values, and round trips where applicable.
- For idempotent or batched mutations, validate both shape and semantic conflicts across the entire batch and against existing state before the first write. Test same-key/same-payload and same-key/different-payload behavior, serial and concurrent calls, and assert rejected operations leave state unchanged.
- For state machines, test invalid transitions, retries, stale revisions, cancellation, and crash/restart windows rather than only the happy path.
- For resource limits, test the exact boundary, one below, one above, and cumulative accounting after retry or restart.
Interpret results correctly
- A successful compile does not prove runtime behavior.
- A test command that selects zero tests is not a pass.
- A skipped environment-dependent security test must be identified and covered elsewhere when it matters.
- Tool text beginning with an error, a non-zero exit, timeout, cancellation, incomplete assertion set, or missing artifact cannot count as success evidence.
- Validate streamed/durable systems from committed state and replay, not only the live UI.
- For concurrency and recovery, exercise the race/crash boundary rather than infer correctness from sequential code.
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.
- 9d ago First seen · 51 lines · 54 tokens per session scan A 1c7935dadc3d
verification is a skill published in the GitHub repository ageerle/ruoyi-ai (5,683 stars, last pushed 3d ago), licensed MIT. It adds 54 tokens to every session and 604 once invoked, about $0.0003 per session on Opus 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
fix-failing-tests
Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
ulw-qa
This is a Hermes-native ultraqa workflow skill.
ai-discover
Parallel discovery of performance hotspots (perf track) and failure surfaces (bug track) for the auto-improvement loop. Fans out one subagent per hot-path area or failure surface; each returns ONE concrete, behavior-preserving fix candidate (perf) or a reproducing test plus fix (bug). Discovery only — no code changes…
audit-remediate
Macro workflow for auditing a single domain layer against its authoritative layer skill, applying fixes, and gating the result. Use when you need to prove a layer skill on real code, clean up an existing layer after a skill update, or verify that a layer is already compliant. Always captures a golden baseline before…
03-assert
Assert the work behaves by iterating the project's coding assertions until they pass, plus optional architecture and frontend facets. Use to validate an implementation. Not for reviewing or writing tests.