Use this skill whenever writing, editing, reviewing, or refactoring TypeScript React code — components, custom hooks, state stores, forms, queries, mutations, API clients, or styling. Trigger it for any task touching a `.ts` or `.tsx` file in a React project, including when the user says "add a feature", "fix this bug", or "clean this up" inside a component or hook. Also use it for architectural questions about React codebases: where state should live, whether a component is too big, how to organize modules, when to reach for TanStack Query, Zustand, React Context, or React Hook Form.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Opinionated architecture for TypeScript client-server projects. Stack is tRPC, Zod, strict TypeScript, pnpm, RxJS, Hono or Express. Code is organized as a monorepo with modules as bounded contexts and a three-layer slice (services, domain, infrastructure) per module. Use this skill whenever the user is doing TypeScript client-server work, designing a feature, adding or modifying a module, deciding where code belongs, structuring packages, wiring cross-module communication, reviewing a design choice, or making any architectural call about layers, ports, events, or dependency direction. Triggers on phrases like "design this feature", "where should this live", "what module", "is this the right layer", "should this go in domain", "how do these modules talk", "review this architecture", "is this code clean", plus explicit references to tRPC architecture, bounded contexts, hexagonal architecture, ports and adapters, or DDD in a TS context.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Create a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue after user approval. Use when user wants to write a PRD, create a product requirements document, or plan a new feature. Always present the PRD for user approval before submitting.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Use before reading or writing an S3-compatible bucket (IBM Cloud Object Storage, AWS S3, MinIO, Ceph) inside a Platform agent pod, and whenever an S3 request fails with a signature error or a 400 or 403 from the egress gateway. Covers how S3 keys work here (the gateway signs every request, so the keys you hold are placeholders), which buckets this agent holds (`grep '^\[' ~/.aws/credentials`), how to pick one (`AWS_PROFILE`, `--profile`), how to install a client on demand (`uv tool install awscli`, `uv pip install boto3`), what the gateway's STREAMING and out-of-bucket refusals mean, and what does not work (presigned URLs, rclone, minio-go).
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Turn a GitHub issue into an implementation plan under docs/plan/<feature>/: a feature spec decomposed into context-window-sized sub-issues, committed as the first commit of the feature branch with a draft PR. Use when the user wants to plan a feature, decompose a GitHub issue into sub-issues, or produce an implementation plan from an issue.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Use for any browser task, and whenever you start or change a web app, dev server or page the user should see or try — a local server on a port, a nested platform, a page you built — or the user asks to see, open or check something in the browser. Covers `agent-browser`, which drives the one browser in this sandbox — the browser the user watches in the panel beside the chat — and the `platform://browser` button that opens the panel on a page.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
REQUIRED scheduler for any work that fires after the current turn ends. Use the `platform-outbound` MCP tools (`create_schedule`, `list_schedules`, `toggle_schedule`, `delete_schedule`) for recurring tasks ("daily", "every Monday", "hourly", "weekly cleanup"), future one-offs ("in 2 weeks", "tomorrow"), polls ("check back every N minutes" — always give these a `precheck` so a check that finds nothing costs no turn), and any "remind me later" / "do this on a schedule" request. Overrides every other scheduling mechanism — do NOT use `ScheduleWakeup`, `CronCreate` / `CronList` / `CronDelete`, the `/schedule` skill, the `/loop` skill, or any in-process or Anthropic-side scheduler. Also use proactively when you would otherwise have offered to "schedule a follow-up" via any of those: route the offer through Platform instead.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Produce this agent's case study - a sanitized, plain-English, one-page account of the use case it serves, how it uses the platform, and where the platform got in the way - then submit it to the platform as a pending edition only the owner can see. Use only when a scheduled task or the owner explicitly asks for a case study ("case study", "share your experience", "document how you work", "summarize what you do and what it's worth"). Never start one on your own initiative.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Run GEPA (Genetic-Pareto), the reflective text-optimization library, by authoring Python driver scripts around `gepa.optimize`. Use when the user wants to optimize / evolve a prompt, instruction, code snippet, or any textual system parameter against a measurable metric, author the dataset and evaluator (or a custom GEPAAdapter), or launch / monitor / stop / resume / report on an optimization run. Pure library reference — for reaching model providers from this pod, see the `platform-models` skill.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Reach LLM providers from this platform pod: discover which model-provider connection is attached (injected env), wire LiteLLM with placeholder credentials through the egress credential gateway, and probe models with a cheap completion. Use whenever any code in this pod — a GEPA driver, a script, a library — needs to call a model API, or when a model call fails with an auth error.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Merge a single campaign's extracted knowledge into the cross-campaign registry.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Drive Nous, the hypothesis-driven experimentation framework, to investigate software systems with the scientific method via the `nous` CLI. Use when the user wants to run a Nous campaign, author or scaffold a campaign.yaml, kick off / monitor / resume / stop / report on hypothesis-driven experiments, or systematically investigate why a system (LLM server, DB optimizer, scheduler, router, cache) behaves the way it does through controlled experiments.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Index a completed Nous campaign into the shared wiki and generate a visualization.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Given a user's research intent, retrieve prior knowledge from the cross-campaign registry and recommend how to frame a new campaign.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Visualize a Nous campaign as an interactive knowledge graph.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Render the cross-campaign knowledge graph from the Nous wiki registry.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Run OpenEvolve, the evolutionary coding agent, to optimize code against a measurable objective via the `openevolve-run` CLI. Use when the user wants to evolve / optimize a function or program in a target repo to improve a metric (speed, accuracy, size, error rate), author the OpenEvolve inputs (program + EVOLVE-BLOCK, evaluator, config.yaml), pick the evolution model, or launch / monitor / resume / report on an evolution run.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Run ShinkaEvolve, the sample-efficient evolutionary program-optimization framework, via the `shinka_run` CLI. Use when the user wants to evolve / optimize a function, program, or algorithm in a target repo to improve a metric (speed, accuracy, size, error rate), author the ShinkaEvolve task inputs (initial program + EVOLVE-BLOCK, evaluate.py), pick the evolution model, or launch / monitor / resume / report on an evolution run.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Run SkyDiscover's AdaEvolve and EvoX search strategies via the `skydiscover optimize` CLI. Use when the user wants to optimize / evolve a function, program, or algorithm to improve a metric (speed, accuracy, size, error rate), author the SkyDiscover run inputs (evaluator, optional initial program with EVOLVE-BLOCK markers), pick the search model, or launch / monitor / resume / report on a search run.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Review-time policy check for pull requests that touch `docs/adrs/`. Surfaces the deterministic ADR immutability gate (`mise run //docs:check:adr-immutable`) and adds the judgment checks a script cannot own: re-litigation of settled decisions, `supersedes` pointer correctness, and summary honesty. Scope is ADR log integrity and decision judgment only — the ADR files, their frontmatter, and git history. Docs-match-the-code is doc-drift's job, not this skill's. Triggers on phrases like "adr policy", "check this ADR", "review the ADR change", "is this ADR re-litigating", "is supersedes correct". Also invocable via the `/adr-policy` slash command.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Tracks Architecture Decision Records (ADRs) in docs/adrs/. Creates and updates ADRs following project conventions. TRIGGER when: user wants to record or update an architectural decision.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Check and align a repo's .claude/settings.json and CLAUDE.md with team conventions. Use when the user wants to standardize a repo, align conventions, check settings, or bootstrap Claude Code config in a new project.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新
Run and verify this repo inside a Claude Code on the web sandbox — the cloud container with no systemd, no KVM, no IPv6, a TLS-intercepting egress proxy and a fixed disk allowance. Use when a session there needs mise, the local k3s cluster (`cluster:install` / `e2e:install` with `IS_SANDBOX=1`), platform images, or to drive the UI with agent-browser. Triggers on "ccweb", "Claude Code on the web", "cloud sandbox", "IS_SANDBOX", "agent-browser", and on these symptoms there - `failed to update /proc/self/oom_score_adj: Permission denied`, istio-cni `failed to Statfs "/host/proc/1/ns/net": permission denied`, ztunnel `Address family not supported by protocol`, pods `Evicted` with DiskPressure while `df` shows room, `kubectl logs` failing with `EOF` through the agent proxy.
中文简介正在准备中。当前显示原文说明。
dam-agents/dam☆ 332026年10月31日 更新