jev-typesafe-brief
Skill0 starsChanged 48 days agoMITView on GitHub
Author a schema-checked brief for Hermes, Trigger.dev, or another agent runtime. Any time agent I/O must be validated, versioned, and replayable across sessions.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- clay-table-designSkill
- competitor-teardownSkill
- deploy-surface-checkSkill
- fde-handoff-packSkill
- hermes-herdr-loopSkill
- icp-scorecardSkill
- n8n-flow-scaffoldSkill
- signal-to-sequenceSkill
- trigger-job-patternSkill
- weekly-pipeline-pulseSkill
The file
Files
Skill: jev-typesafe-brief
Author a schema-checked brief for Hermes, Trigger.dev, or another agent runtime.
When to use
Any time agent I/O must be validated, versioned, and replayable across sessions.
Steps
- Header block:
schema: name of the brief typeversion: semver or integercustomer_slug: active desk slugproduced_at: ISO timestamp
- Body: goals, constraints, input refs (file paths or ids, not raw PII dumps), success criteria, stop conditions.
- Validate against the declared TypeSafe / Jev schema before handoff.
- Save to
ops/<slug>/agents/brief-<name>.json(or.mdwith a fenced JSON block if the runtime expects markdown). - On schema mismatch, fix the producer; do not silently drop fields.
Anti-patterns
- Free-form chat paste as the only brief
- Embedding API keys or full contact exports in the brief
- Reusing an old brief version after the schema moved
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

