project-workflows
Operate spaCy project.yml workflows safely with local validation, dry runs, and explicit network boundaries.
- License 许可
- MIT
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- project-workflows
- license
- MIT
- metadata
- { "disco-role": "operating" }
- description
- Operate spaCy project.yml workflows safely with local validation, dry runs, and explicit network boundaries.
- disable-model-invocation
- true
02 资源文件 4
- 参考文档references/project-workflows.md6.1 KB
- 参考文档references/project-yml-reference.md6.0 KB
- 参考文档references/troubleshooting.md4.3 KB
- 脚本scripts/validate_project_yml.py19.7 KB
03 SKILL.md 正文
project-workflows
Use this sub-skill for project-level spaCy orchestration: cloning templates, fetching assets, running commands and workflows, generating docs, generating DVC config, and pushing or pulling outputs from remotes.
Read or run these first
references/project-workflows.md— read this for the command map, safe vs side-effect boundaries, dependency/output tracking, and workflow order.references/project-yml-reference.md— read this forproject.ymlkeys, command and asset field rules, and requirements checks.references/troubleshooting.md— read this when clone, assets, run, document, push, pull, or DVC fails or warns.scripts/validate_project_yml.py— run this on a local project file before any networked or remote command.
Default operating order
- Validate the project file locally.
- Inspect or generate documentation.
- Use
project run --drybefore the first real run. - Fetch assets only when you know whether
--extrais needed. - Run the narrowest command that covers the change.
- Use
push,pull, anddvconly after remotes or DVC are confirmed.
Route elsewhere when the work shifts
- If the project command centers on training config,
spacy train,spacy convert,spacy evaluate, orspacy package, usetraining-and-cli. - If the issue is package import, installation, or model download, use
install-and-inspect. - If a project script defines custom pipeline components or factories, use
pipeline-components.
Verification focus
project-document-dry-run: local temp project,project document, andproject run --dry.project-assets-remote: help-only and skip-network checks forproject assets,push, andpull.
Boundaries
- Do not treat external template cloning as a validation step.
- Do not assume remote storage, credentials, or network access are available.
- Do not move into training internals or model-serving integrations here.
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).