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 RasaHQ/rasa-agent-skills --skill rasa-simulating-conversationsgit clone --depth 1 https://github.com/RasaHQ/rasa-agent-skillsWrote 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/rasahq/rasa-agent-skills/rasa-simulating-conversations)<a href="https://agentmods.dev/skills/rasahq/rasa-agent-skills/rasa-simulating-conversations"><img src="https://agentmods.dev/badge/skills/rasahq/rasa-agent-skills/rasa-simulating-conversations/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/rasahq/rasa-agent-skills/rasa-simulating-conversations"><img src="https://agentmods.dev/badge/skills/rasahq/rasa-agent-skills/rasa-simulating-conversations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00159 | $0.09492 |
| Opus 5.5 | $0.00064 | $0.03797 |
| Sonnet 5.5 | $0.00032 | $0.01898 |
| Haiku 4.5 | $0.00016 | $0.00949 |
Grade A, and why
rasa-simulating-conversations 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 1mo 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 — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal-Driven Simulation for Rasa
Simulate realistic user conversations against a live Rasa assistant to catch flow failures, missing slot handling, and poor bot responses — before shipping.
How this works
- You write (or generate) a scenario YAML in
eval/scenarios/ - This skill calls the
evaluate_agentMCP tool - The tool uses an LLM to play the user role, driving the conversation via the REST API
- After each run it checks assertions (deterministic) and success criteria (LLM judge)
- Results land in
eval/results/<timestamp>/<scenario-name>/run_N.txt
Scenario YAML format
Currently only the text-based simulation is supported.
scenario:
name: User successfully completes <flow name>
simulation_context: >
<Prose block combining persona, goal, and any conversation guidance.
Write as a briefing to the simulator — e.g. "You are a cooperative user who wants
to transfer money. You have already authenticated. Provide details when asked.">
setup:
initial_slots: # injected before conversation starts
authenticated: true # set any slots that should be pre-filled
goals:
criteria: # evaluated by LLM judge
- Agent collects all required information without confusion
- Agent confirms the task was completed successfully
- Conversation ends naturally
assertions: # deterministic checks against the tracker
- flow_started:
flow_ids: [<flow_id>] # one or more flow ids
operator: any # any | all
- flow_completed:
flow_id: <flow_id> # singular; map; optional flow_step_id
flow_step_id: <step_id> # optional
- flow_cancelled:
flow_id: <flow_id>
- action_executed: <action_name>
- slot_was_set:
- name: <slot_name> # set to any non-null value
- name: <slot_name>
value: "<expected_value>" # set to an exact value
- slot_was_not_set:
- name: <slot_name>
- bot_uttered:
utter_name: <utter_response_id> # any of utter_name / text_matches / buttons
text_matches: "regex pattern"
- bot_did_not_utter:
text_matches: "I don't know"
- sequencing: # ordered: each step matches an event strictly after the previous step's match
- flow_started: transfer_money
- slot_was_set: recipient # slot name only (string); no value match
- action_executed: action_submit_transfer
- flow_completed: <flow_id> # NOTE: plain string inside sequencing
# also available as steps: flow_cancelled, flow_interrupted
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.
- 1mo ago Changed · +84 lines 0c1052ebd93c
- 1mo ago Changed · +54 lines 917cb8232648
- 2mo ago First seen · 584 lines · 159 tokens per session scan A 610610da6d95
rasa-simulating-conversations is a skill published in the GitHub repository RasaHQ/rasa-agent-skills (6 stars, last pushed 29d ago), licensed Apache-2.0. It adds 159 tokens to every session and 9,492 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.