AGENT SKILLS ATLASAgent Eval Adoption
Substrate-primitive reference for adopting @tangle-network/agent-eval (0.50.x+) + @tangle-network/agent-runtime (0.33.x+) in a product. Covers defineAgent manifest, runLoop driven loops + topology drivers (refine / fanout-vote / dynamic agent-authored topology via createDynamicDriver + createSandboxPlanner), identity-gated prompt-surface optimization (optimizePrompt), MCP delegation tools, ProductionTraceSink, scorecard + ship-gate CI, held-out promotion, cross-profile matrix benchmarks, analyst-loop, assertRealBackend Phase A guard. PAIRS WITH: agent-stack-adoption (9-phase pipeline shape that consumes these primitives), agent-eval (substrate footgun bible + canonical product-agent file layout), eval-agent (LLM-as-judge rubric generation specifically).
Skill stats
Skills1CategoryProduct & designStars0
About this skill
Substrate-primitive reference for adopting @tangle-network/agent-eval (0.50.x+) + @tangle-network/agent-runtime (0.33.x+) in a product. Covers defineAgent manifest, runLoop driven loops + topology drivers (refine / fanout-vote / dynamic agent-authored topology via createDynamicDriver + createSandboxPlanner), identity-gated prompt-surface optimization (optimizePrompt), MCP delegation tools, ProductionTraceSink, scorecard + ship-gate CI, held-out promotion, cross-profile matrix benchmarks, analyst-loop, assertRealBackend Phase A guard. PAIRS WITH: agent-stack-adoption (9-phase pipeline shape that consumes these primitives), agent-eval (substrate footgun bible + canonical product-agent file layout), eval-agent (LLM-as-judge rubric generation specifically).
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Installation guide →
Review, license & listing details
Review the source before using this skillThis is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Automated security scan: PartialOnly SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: a3850c2ee723ed7d8ae24f3dc55254b3d6f847b6ae214d2c4e2bde77c6bfd0a9
About scan coverage and limitations Original listing metadata
Original name
agent-eval-adoptionOriginal description
Substrate-primitive reference for adopting @tangle-network/agent-eval (0.50.x+) + @tangle-network/agent-runtime (0.33.x+) in a product. Covers defineAgent manifest, runLoop driven loops + topology drivers (refine / fanout-vote / dynamic agent-authored topology via createDynamicDriver + createSandboxPlanner), identity-gated prompt-surface optimization (optimizePrompt), MCP delegation tools, ProductionTraceSink, scorecard + ship-gate CI, held-out promotion, cross-profile matrix benchmarks, analyst-loop, assertRealBackend Phase A guard. PAIRS WITH: agent-stack-adoption (9-phase pipeline shape that consumes these primitives), agent-eval (substrate footgun bible + canonical product-agent file layout), eval-agent (LLM-as-judge rubric generation specifically).
About this listing
- Category
- Product & design
- Reported license
- Not specified
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.