Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/manykarim/robotframework-agentskillsnpx agentmods add skills/manykarim/robotframework-agentskills/rf-languageWrote 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/manykarim/robotframework-agentskills/rf-language)<a href="https://agentmods.dev/skills/manykarim/robotframework-agentskills/rf-language"><img src="https://agentmods.dev/badge/skills/manykarim/robotframework-agentskills/rf-language/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/manykarim/robotframework-agentskills/rf-language"><img src="https://agentmods.dev/badge/skills/manykarim/robotframework-agentskills/rf-language.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 | $0.00024 | $0.05601 |
| Opus 5.5 | $0.00010 | $0.02240 |
| Sonnet 5.5 | $0.00005 | $0.01120 |
| Haiku 4.5 | $0.00002 | $0.00560 |
Grade A, and why
rf-language 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 11d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Robot Framework Language
Write and review Robot Framework code in .robot and .resource files: test cases and suites, user keywords, resource files and variables, in modern syntax that fits the project's Robot Framework version.
Python keyword libraries and listeners belong to rf-python-library; library keywords, locators and waits belong to the library skills (rf-browser, rf-requests, …).
Verified against Robot Framework 7.4.2.
When to use
Load this skill first, before opening the .robot and .resource files or answering from memory, when Robot Framework test data is written, changed, reviewed or explained, even if the user just says "tests" or "keywords":
- test cases and suites, user keywords and variables in .resource files, tags, setups and teardowns,
__init__.robotsuite files; - data-driven tests with a Test Template table; Given/When/Then (BDD) scenarios and their step keywords;
[Arguments](optional, typed or embedded); replacing Force Tags,[Return], Run Keyword If or Set Suite Variable with current syntax;- selecting tests by tag on the robot command line;
Multiple keywords with name '...'and import scope between__init__.robotand child suites.
Not this skill: Python keyword libraries or listeners use rf-python-library; library keywords use rf-browser, rf-requests or another library skill.
Version gate
Establish the project's Robot Framework version once, before writing version-dependent syntax. Use rf.effective and rf.features from Step 0, or run this in the project (it exits 0; robot --version prints the version but exits 251):
uv run python -c "import robot; print(robot.__version__)"
| Feature | Min RF |
|---|---|
RETURN |
5.0 |
Test Tags, Keyword Tags, robot:private |
6.0 |
--parseinclude, suite Name setting, JSON variable files, embedded + normal arguments in one user keyword |
6.1 |
VAR, [Tags] -tag removal, --test matching the full name from the root suite |
7.0 |
VAR … scope=SUITES, BDD prefix before a leading embedded argument |
7.1 |
GROUP, (?i) in embedded patterns, templated test passes when some rows skip |
7.2 |
Typed user keyword arguments ${count: int}, typed VAR, Variables section and FOR variables |
7.3 |
Secret type |
7.4 |
What ships with it
28 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.
- assets/examples/resources/api.resource 1.1 KB
- assets/examples/resources/calc.resource 910 B
- assets/examples/resources/embedded.resource 891 B
- assets/examples/resources/keywords.resource 1.1 KB
- assets/examples/resources/login.resource 456 B
- assets/examples/tests/__init__.robot 293 B
- assets/examples/tests/01__keyword_driven.robot 378 B
- assets/examples/tests/02__data_driven.robot 431 B
- assets/examples/tests/03__templates.robot 532 B
- assets/examples/tests/04__bdd.robot 358 B
- assets/examples/tests/05__embedded.robot 500 B
- assets/examples/tests/api/__init__.robot 314 B
- assets/examples/tests/api/users.robot 458 B
- assets/examples/tests/env.robot 556 B
- assets/examples/variables/common.py 408 B runs code
- assets/examples/variables/dev.yaml 146 B
- assets/examples/variables/staging.yaml 160 B
- references/arguments.md 5.7 KB
- references/control-structures.md 5.9 KB
- references/embedded-arguments.md 5.5 KB
- references/migration.md 4.9 KB
- references/resources-and-variable-files.md 5.9 KB
- references/styles.md 4.0 KB
- references/suites-and-init.md 4.8 KB
- references/tags-and-selection.md 5.0 KB
- references/templates.md 4.7 KB
- references/variables-and-scopes.md 5.4 KB
- scripts/rf_conventions.py 36 KB runs 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.
- 11d ago Changed · -1 lines · -5 tokens per session 3bf8020eb88d
- 17d ago First seen · 314 lines · 29 tokens per session scan A 1fc6eca410cb
rf-language is a skill published in the GitHub repository manykarim/robotframework-agentskills (38 stars, last pushed 5d ago), licensed Apache-2.0. It adds 24 tokens to every session and 5,601 once invoked, about $0.0001 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 2026-10-01.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
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.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
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.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.