evidence-upload
Use when publishing visual evidence through Pylot assets for a PR, issue, report, mission, or conversation.
How do I install this agent skill?
npx skills add https://github.com/fellowship-dev/dogfooded-skills --skill evidence-uploadIs this agent skill safe to install?
- Gen Agent Trust Hubpass
The skill allows an agent to upload visual evidence (images, videos) to a backend service using standard command-line tools. It follows secure practices by using environment variables for authentication and safe JSON processing methods.
- Socketpass
No alerts
- Snykpass
Risk: LOW · No issues
What does this agent skill do?
evidence-upload
Publish a local image, recording, or other accepted evidence file through the Pylot asset lifecycle and return the resulting reference or public URL.
Workflow
- Read the owning repo's playbook and determine its evidence policy and the intended destination.
- Invoke or read
pylot-cli, then follow its Assets section exactly. It is the single source for supported actions, flags, retention, and upload transport. - Return the receipt required by the destination, including the asset id and any reference needed by the reviewer or conversation.
If the repo playbook defines no Pylot asset policy, do not invent one. Use the repo's accepted evidence host and state what was used.
Critical Rules
- Use
pylot-clias the single source of truth; do not copy its commands into this skill or call Pylot gateway asset endpoints directly. - An upload problem is advisory unless the owning repo explicitly makes evidence a gate. Report the missing evidence instead of concealing it or failing an otherwise valid PR.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/fellowship-dev/dogfooded-skills/evidence-upload">View evidence-upload on skillZs</a>