Files
wehub-resource-sync 2114ccd278
CI / Lint & Test (Python 3.13) (push) Failing after 2s
CI / Lint & Test (Python 3.14) (push) Failing after 1s
CI / Lint & Test (Python 3.12) (push) Failing after 2s
CI / DCO Check (push) Has been skipped
Scorecard supply-chain security / Scorecard analysis (push) Failing after 2s
chore: import upstream snapshot with attribution
2026-07-13 12:23:39 +08:00

68 lines
1.5 KiB
Markdown

# SkillSpector Pi Extension
SkillSpector can be installed into Pi as a local package. The extension registers a `skillspector_scan` tool that runs the existing SkillSpector CLI.
## Requirements
- Pi installed.
- Python `>=3.12,<3.15`.
- `uv` recommended.
- This repo checked out locally.
## Install
```bash
cd /path/to/SkillSpector
uv sync
pi install /path/to/SkillSpector
```
Then reload Pi:
```text
/reload
```
## Basic scan
Ask Pi:
```text
Use skillspector_scan on tests/fixtures/safe_skill/SKILL.md with noLlm=true.
```
Equivalent CLI:
```bash
.venv/bin/skillspector scan tests/fixtures/safe_skill/SKILL.md --no-llm
```
## Tool parameters
- `target`: path, URL, zip, Git repo, or `SKILL.md` to scan.
- `format`: `terminal`, `json`, `markdown`, or `sarif`. Default: `terminal`.
- `output`: optional report path.
- `noLlm`: default `true`.
- `provider`: optional `openai`, `anthropic`, `anthropic_proxy`, `nv_build`, or `nv_inference`.
- `model`: optional model override.
- `yaraRulesDir`: optional directory of extra YARA rules.
- `verbose`: optional detailed progress.
## LLM-backed analysis
Static scan is default. To use semantic LLM analysis, configure provider credentials in your shell before launching Pi, then call the tool with `noLlm=false` and a provider.
Example:
```text
Use skillspector_scan on ./my-skill with noLlm=false and provider=anthropic.
```
The extension does not read `.env` and redacts secret-looking output.
## Remove
```bash
pi remove /path/to/SkillSpector
```