scaffold
Use this sub-skill when creating or enhancing an ADK project with agents-cli scaffold create, scaffold enhance, or scaffold upgrade, including template, deployment target, CI/CD, session storage, and prototype-first decisions.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- scaffold
- license
- Apache 2.0
- metadata
- { "author": "Google", "license": "Apache-2.0", "version": "1.3.1", "requires": { "bins": [ "agents-cli" ], "install": "uv tool install google-agents-cli" }, "disco-role": "operating" }
- description
- Use this sub-skill when creating or enhancing an ADK project with agents-cli scaffold create, scaffold enhance, or scaffold upgrade, including template, deployment target, CI/CD, session storage, and prototype-first decisions.
- disable-model-invocation
- true
02 资源文件 2
- 参考文档references/flags.md3.2 KB
- 参考文档references/scaffold-guide.md10.4 KB
03 SKILL.md 正文
Project Scaffolding
Use this sub-skill inside the google-agents-cli repo skill. It is a router plus operating checklist; move into the bundled references for full command flags, schemas, and examples.
When to Use
- The user wants to create a new project, enhance an existing project, or upgrade generated files.
- The task asks about
agents-cli create,agents-cli scaffold create,enhance, orupgrade. - You need to map prototype/deployment/session/CI-CD choices to CLI flags.
Workflow
- Confirm project name/path and whether prototype-first is desired.
- Map target architecture to
--deployment-target,--session-type, and--cicd-runnerflags. - Run
scaffold createonly for a new directory; usescaffold enhancefor an existing project. - After scaffolding, load workflow/adk-code/eval for implementation and validation.
Read These References
references/scaffold-guide.md— read for scaffold guide details.references/flags.md— read for flags details.
Verification and Safety
Safe checks: agents-cli scaffold --help; project creation/enhance mutates files and needs confirmation.
Boundaries
- Does not write custom ADK business logic; use adk-code after project creation.
- Does not deploy live resources; use deploy after scaffold files exist.
Related Sub-Skills
../workflow/SKILL.md— lifecycle routing and approval gates.../scaffold/SKILL.md— project creation/enhancement.../adk-code/SKILL.md— ADK Python implementation patterns.../eval/SKILL.md— evaluation loops and metrics.../deploy/SKILL.md— deployment and infrastructure.../publish/SKILL.md— Gemini Enterprise registration.../observability/SKILL.md— logging, tracing, and analytics.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).