skill-card-generator

Generate Skill Card

Skill directory to analyze: $ARGUMENTS

Purpose

Create a draft NVIDIA governance skill card for an existing agent skill. The skill gathers source signals, guides the agent to build a grounded JSON context, renders a deterministic markdown card, and checks that human-review markers were removed before submission.

Use this when:

• A skill directory already exists and needs a new governance card.
• A changed skill needs its existing card refreshed.
• A skill owner is preparing legal/safety review material.

Do NOT use for:

• Explaining, listing, comparing, or discussing skills or skill capabilities.
• Creating or rewriting the source skill itself.
• Generating cards for non-skill assets such as models, datasets, containers, or full systems.
• Signing, publishing, or approving a skill card.
• Replacing required human legal, safety, or owner review.

Prerequisites

• Python 3 is available.
• jinja2 is installed before running render_card.py.
• The target path is a skill directory containing SKILL.md or skill.md.
• The agent can write a temporary context JSON file and the rendered card output.
• Runtime permissions allow reads from target_skill_directory plus this skill's references/ and scripts/, writes only to the target skill directory or /tmp/, and shell execution only for the three scripts listed below.

Instructions

1. First, read this SKILL.md completely before running any script.
2. Resolve the target skill directory from $ARGUMENTS; if omitted, use the current working directory.
3. Stay within the declared permission scope. Do not read .env, credential files, hidden auth folders, or unrelated repo files; do not write outside the target skill directory or /tmp/.
4. Run scripts/discover_assets.py against the target. Use the structured signal summary first; if output is truncated, read only targeted files or small excerpts.
5. Build a context JSON file from the structured signal summary first, then from extracted file contents only when needed.
6. Populate credential_requirements with only two fields: requires_api_key_or_credential and credential_types. Ground the classification in SKILL.md prose documentation — not script inspection alone. For credential_types, use the controlled vocabulary in references/style-guide.md. Never include credential values, assignments, or raw environment variable names.
7. Follow references/style-guide.md for every context field. Use HUMAN-REQUIRED only when no source supports a truthful value.
8. Render the card with scripts/render_card.py and fix any schema errors before proceeding.
9. Review the card manually, remove resolved VERIFY and SELECT markers, then run scripts/validate_submission.py.
10. Before finishing, confirm the rendered card has no unrendered {{ ... }} or {% ... %} template fragments.

Available Scripts

Examples

Discover signals for a target skill:

run_script("scripts/discover_assets.py", args=["/path/to/target-skill"])

Render a card from the completed context:

run_script(
  "scripts/render_card.py",
  args=[
    "--context", "/tmp/target-skill-context.json",
    "--template", "references/skill-card.md.j2",
    "--out", "/path/to/target-skill/target-skill-card.md"
  ]
)

Validate the reviewed card before submission:

run_script("scripts/validate_submission.py", args=["/path/to/target-skill/target-skill-card.md"])

Limitations

• The generated card is a draft and must be reviewed by a human owner.
• Discovery is limited to local files and repo metadata visible from the target path.
• The renderer validates required context shape, not the legal or safety correctness of field values.
• Canned limitation and risk catalogs are starting points; remove entries that do not apply.

Troubleshooting

Files in this skill

• SKILL.md - this file (orchestration)
• references/style-guide.md - per-context-field guidance
• references/skill-card.md.j2 - exact card layout
• references/Skill Card Generator License.txt - license text for this skill package
• references/catalog/limitations.json - canned technical-limitations catalog
• references/catalog/risks.json - canned risk-management catalog
• scripts/discover_assets.py - discovery and signal extraction
• scripts/render_card.py - Jinja renderer with context validation
• scripts/validate_submission.py - pre-submission marker validator