Individual skill
genesis-evals
Use this skill to run the genesis maintainer-side eval suite against a target model (default: claude-opus-4.7). Activate when validating a genesis PR, when changing the genesis catalogue (architectural-patterns, primitives, design-patterns, refactor-patterns, composition-substrate, pattern-tradeoffs, SKILL.md), or when the operator asks to "run evals" or "regenerate the eval matrix". This skill orchestrates parallel cold sub-agent spawns via the harness's task tool, scores deterministically, and converges P>=0.8 / N>=0.8 / R==1.0 within max 3 iteration loops. This skill is contributor-only -- it lives under dev/skills/ (OUTSIDE .apm/) and is NOT shipped inside the user-facing skills/genesis/ bundle (BUNDLE LEAKAGE discipline). See "Why this lives outside .apm/" below.
dev/skills/genesis-evals/SKILL.md
Source commit 18e73c35e5cefaf431fbe4e080e8f125ebfece33
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Local scripts
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 79
- Repository last updated
- May 30, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-ai Repository topic
- ai-coding-agents Repository topic
- apm Repository topic
- claude-code Repository topic
- codex Repository topic
- cursor Repository topic
- github-copilot Repository topic
- llm Repository topic
- markdown Repository topic
- engineering Derived category
- design Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.gitignoreasset · 7 bytesSKILL.mdcore · 9,935 bytesSKILL.mdcore · 9,935 bytesSKILL.mdcore · 9,935 bytesSKILL.mdcore · 9,935 bytesSKILL.mdcore · 9,935 bytesSKILL.mdcore · 9,935 bytesrequirements.txtdoc · 28 bytesruns/.gitignoreasset · 29 bytesscenarios/n-001-debug-bug.ymlasset · 1,012 bytesscenarios/n-002-write-doc.ymlasset · 895 bytesscenarios/n-003-explain-concept.ymlasset · 619 bytesscenarios/n-004-cost-near-miss.ymlasset · 1,008 bytesscenarios/p-001-a10-recognition.ymlasset · 874 bytesscenarios/p-002-soc-extraction.ymlasset · 1,086 bytesscenarios/p-003-panel-fanout.ymlasset · 908 bytesscenarios/p-004-a12-gradient-workflow.ymlasset · 1,131 bytesscenarios/p-005-b13-cache-invalidator.ymlasset · 1,172 bytesscenarios/p-006-r5-cost-prune.ymlasset · 991 bytesscenarios/p-007-cost-stance-projection.ymlasset · 1,019 bytesscenarios/p-008-b12-model-router.ymlasset · 1,029 bytesscenarios/r-001-substrate-validation.ymlasset · 1,022 bytesscenarios/r-002-substrate-implied-not-github.ymlasset · 936 bytesschema/scenario.schema.jsonasset · 2,480 bytesscripts/score_run.pyruns · 5,769 bytesscripts/spawn_record.pyruns · 2,748 bytesscripts/validate_scenarios.pyruns · 2,211 bytes
Read excerpt
# genesis-evals: maintainer-side eval runner
Run the genesis self-eval suite. Steers the parent LLM session to
orchestrate cold sub-agent spawns, capture responses, score
deterministically, and report convergence.
## Why this lives outside `.apm/`
Genesis ships to USERS via npx / `apm install`. Eval scenarios LOOK
LIKE real user requests (that is the point). Colocating them under
`skills/genesis/evals/` would risk DISPATCH CONTAMINATION (an
over-eager harness loader pulling scenario prompts into the active
context) and PAYLOAD BLOAT for users who never run evals.
