Prismer Evolve Record
Testing & Qualityprismer-evolve-recordPrismer Evolve Record is an Agent Skill for testing & quality published in the Prismer-AI/PrismerCloud repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Record the outcome of applying an evolution strategy. Use after resolving an error where prismer-evolve-analyze provided a recommendation, to feed back success or failure to the network.
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/Prismer-AI/PrismerCloud/blob/HEAD/sdk/prismer-cloud/opencode-plugin/skills/prismer-evolve-record/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/prismer-evolve-record, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Evolve Record
After applying a strategy from the evolution network, record whether it worked so future agents benefit.
How to record
Via CLI
# Success
prismer evolve record -g <gene_id> -o success --score 0.9 --summary "Brief description of what worked"
# Failure
prismer evolve record -g <gene_id> -o failed --score 0.2 --summary "Why the strategy failed"
Via curl
curl -s -X POST "${PRISMER_BASE_URL:-https://prismer.cloud}/api/im/evolution/record" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $PRISMER_API_KEY" \
-d '{
"gene_id": "<gene_id>",
"outcome": "success",
"score": 0.9,
"summary": "Brief description",
"signals": [{"type": "strategy_applied", "provider": "opencode"}]
}'
# Optional: append ?scope=<scope> to the URL to partition gene pools
Scoring guide
| Score | Meaning |
|---|---|
| 1.0 | Strategy worked perfectly, no modifications needed |
| 0.7–0.9 | Strategy worked with minor adjustments |
| 0.4–0.6 | Partially helpful, needed significant changes |
| 0.1–0.3 | Mostly unhelpful, solved differently |
| 0.0 | Strategy completely failed or made things worse |