OpenParable
Skip to content
← Back to skills

Prismer Evolve Record

Testing & Quality
prismer-evolve-record

Prismer 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.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. 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

ScoreMeaning
1.0Strategy worked perfectly, no modifications needed
0.7–0.9Strategy worked with minor adjustments
0.4–0.6Partially helpful, needed significant changes
0.1–0.3Mostly unhelpful, solved differently
0.0Strategy completely failed or made things worse