@lioneldraghi/bbt-skill-copilot
ACreate, improve, convert, validate, run, and integrate bbt scenarios for black-box CLI testing. Use when the user mentions bbt, behaviour scenarios in Markdown, executable documentation, CLI test automation, scenario conversion, or CI/CD integration for bbt.
Install
agr install @lioneldraghi/bbt-skill-copilot --target claudeWrites 2 files into .claude/skills/, pinned to git-fda8cb70.
- .claude/skills/bbt-skill-copilot/README.md
- .claude/skills/bbt-skill-copilot/SKILL.md
Document
name: bbt-skill-copilot description: Create, improve, convert, validate, run, and integrate bbt scenarios for black-box CLI testing. Use when the user mentions bbt, behaviour scenarios in Markdown, executable documentation, CLI test automation, scenario conversion, or CI/CD integration for bbt. license: Apache-2.0 compatibility: Requires bbt to be installed for execution tasks; authoring tasks require no runtime dependency. metadata: author: Lionel Draghi version: "1.0.0"
bbt skill for agents
Use this skill when the user wants to work with bbt scenarios: write them, convert existing documentation into them, check their syntax, run them locally, or integrate them in CI/CD.
bbt is both:
- a lightweight scenario format embedded in Markdown documentation;
- a command-line tool that executes recognised scenarios against CLI programs.
Route the task
Choose the smallest relevant reference file. Do not load all references by default. Use progressive discovery: start from this file, then read only the reference needed by the user's intent.
Read authoring when the user wants to
- create, write, improve, fix, refactor, or validate bbt scenarios;
- convert existing documentation, examples, README files, test notes, tutorials, or Gherkin scenarios into bbt-compatible Markdown;
- make documentation examples executable or checkable by bbt.
Typical requests:
- "make my README.md runnable"
- "make tests.md bbt compatible"
- "make examples provided in user_guide.md checkable by bbt"
- "turn examples from my documentation into executable tests"
- "convert this guide into bbt scenarios"
- "fix this bbt scenario"
Read execution when the user wants to
- run existing bbt scenarios;
- check whether a Markdown file executes correctly with bbt;
- understand or troubleshoot bbt command-line usage;
- integrate bbt into CI/CD.
Typical requests:
- "run my README.md"
- "check my README.md"
- "how do I run these bbt tests?"
- "create a GitHub Actions workflow for bbt"
- "why does this bbt run fail?"
Inspect examples when the user asks for complete examples
Use this directory only when the user needs realistic, copyable, complete scenario files or when examples are useful to guide authoring.
If the request involves both conversion and execution, read authoring.md first, then execution.md.
Trustgrade A
- passBody integrity
Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.
- passType matchnot applicable to this artifact type
Whether the artifact is really the kind of thing its metadata claims it is.
- passFreshness
How long since the source repository was last pushed to.
- passPrompt injection
Scans the artifact's own text for instructions aimed at your agent rather than at you.
- passLicense
Whether the source repository declares an SPDX license permissive enough to redistribute.
How the grade is calculated
Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:
- Aevery check passed
- Bone warning
- Ctwo warnings
- Dprompt injection or body integrity failed, or three warnings
- Fone of those failed, and something else is wrong
These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.
Versions
git-fda8cb7083992026-07-31