Agent building

Cross-agent self-inspection of your AI-agent stack.

Find, clone, inspect, and summarize high-quality GitHub reference repositories for coding agents.

DrawAI 的 Session 制作入口。图像可使用宿主能力或用户配置的 API；最终制作默认保留当前 Agent 的模型和配置，调用统一核心完成设计、转换与检查。

Convene a Round Table (โต๊ะกลม): 3–8 souls — persona files, Oracles, or real people's DNA — debate ONE stakes-bearing decision over exactly 4 rounds (OPEN…

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification.

Retrospective on one coding session that proposes changes to the agent's environment (hooks, checks, steering files, tool access) and files each as an ax…

Design well-structured agent loops with best-practice coaching and cross-model review gates before you run them.

Rigorous engineering orchestrator ported from Lauren Tan's pstack (poteto-mode): reads your task, picks one of 23 playbooks (bug fix, feature, refactoring…

Score one analytical answer against a verified golden, and score which of the entities the golden depends on retrieval delivered to the answerer.

Diagnose why a scored answer failed and who owns the fix, then cluster the failures by shared root cause.

Make the smallest safe edit that closes a diagnosed gap the model repo owns: a Malloy model edit, or a package skill under skills/.

Conduct preliminary research on a topic and generate research outline.

Build benchmarks of realistic, hard agent tasks, researched from real work, admitting only verified, shortcut-resistant, calibrated tasks and reporting how…

Delegate a bounded task from a Codex session to a Fable-powered Cursor Agent in the same Herdr workspace, then wait for and collect the result.

Delegate a bounded task from a Codex session to Grok 4.6 with xhigh reasoning in the same Herdr workspace, then wait for and collect the result.

Delegate a bounded task from a Codex session to GPT-5.6 Sol in the same Herdr workspace, then wait for and collect the result.

Check for available upgrades to the pi coding agent framework by comparing the current `@earendil-works/pi-*` or legacy `@mariozechner/pi-*` version in…

Deep audit of a Frappe app for security, correctness, and customization defects.

Inspect OpenLoomi Goals from a skill-capable agent.

OpenLoomi first-use setup and readiness guidance for skill-only agent runtimes.

Design, start, supervise, inspect, and continue HomeRail DAG workflows from any agent with CLI or HTTP access.

Use when designing or auditing how an LLM or multimodal LLM is evaluated on a clinical task (report generation, VQA, text extraction).

Use when turning a personal agent skill into an open-source, distributable one.

Have Codex review a feature or change from Claude Code, then let Claude address the findings and request verification.