analyze-publish
Inspect, compare, regrade, export, share, upload, and publish Harbor results, trajectories, artifacts, Hub records, and versioned task or dataset packages with mutation and credential gates.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- analyze-publish
- license
- Apache 2.0
- metadata
- { "disco-role": "operating" }
- description
- Inspect, compare, regrade, export, share, upload, and publish Harbor results, trajectories, artifacts, Hub records, and versioned task or dataset packages with mutation and credential gates.
- disable-model-invocation
- true
02 资源文件 6
- 参考文档references/analysis-viewer-hub.md4.9 KB
- 参考文档references/parity-reporting.md3.7 KB
- 参考文档references/publish-upload-versioning.md5.5 KB
- 参考文档references/results-and-trajectories.md6.8 KB
- 参考文档references/troubleshooting.md6.2 KB
- 脚本scripts/generate_parity_summary.py7.0 KB
03 SKILL.md 正文
Analyze and publish Harbor outcomes
Use this skill when a Harbor run already exists and the task is to inspect its results, understand trajectories or artifacts, compare runs, regrade a recorded execution, browse the local viewer or Hub, export traces, upload/share job results, or publish and version task/dataset packages. Keep the source record immutable unless a command below explicitly creates a derived result or asks for confirmation.
Route by intent
- Inspect result files, rewards, retries, artifacts, ATIF, or native sessions: read results-and-trajectories.md.
- Run a rubric analysis or quality check, browse locally, query Hub records, or compare jobs: read analysis-viewer-hub.md.
- Download, share, upload, publish, inspect package versions, or move a tag: read publish-upload-versioning.md.
- Summarize benchmark parity records: read parity-reporting.md.
- Diagnose malformed outputs, missing artifacts, auth, viewer, or version failures: start with troubleshooting.md.
Route task/schema/verifier authoring to author-benchmarks, job/provider/agent
execution failures to run-evaluate, and custom framework or plugin code to
integrations. Do not relaunch an evaluation merely to inspect a recorded run.
Safety and mutation gates
- Identify whether the input is a local trial directory, local job directory,
Hub job/trial UUID, task package, or dataset package before selecting a
command. Check
harbor --versionwhen command behavior may be version-sensitive. - Prefer local parsing,
--json,harbor hub ... show/list/tasks/trials/shares,harbor version list/show, andharbor viewfor read-only inspection. - Treat
harbor analyzeandharbor checkas source-preserving but not cost-free: they create derived Harbor jobs, may run an evaluator agent and environment, and write reports. Show rubric, agent/model, environment, attempts, filters, and output directory before running them. - Never run
harbor upload, Hub copy/share/retry/cancel/delete, visibility or access changes,harbor publish, orharbor version tagwithout explicit approval for the exact target, credentials, visibility, recipients, and mutation.harbor traces exportis local by default;--pushor OTLP endpoint upload is an external mutation and needs the same gate. - Keep credentials in the CLI's auth flow or environment. Do not print tokens, copy private result contents into prompts, or infer that a local login grants access to another organization.
Safe operating sequence
- Inventory the local tree (
config.json,lock.json,result.json,job.log/trial.log,artifacts/manifest.json,agent/trajectory.json, native session files, retry folders) and preserve a digest or copy when an audit needs reproducibility. - Read result and manifest JSON before opening large logs. Separate the recorded agent/model/configuration from verifier rewards, exceptions, costs, retries, and post-hoc analysis. A retry is a new attempt; a regrade is a new derived trial that does not rerun the agent.
- Use the narrowest read-only command or local parser. For a Hub record, inspect
with
harbor hub job show,tasks,trials,shares,compare, orhub trial show; use--jsonfor machine processing and--include-retrieswhen retry history changes the conclusion. - For a regrade, verify the source has readable
result.json, a trustworthy artifact manifest and bytes, and that the replacement verifier is single-step and separate-mode. Useharbor job regradeorharbor trial regrade; record the new output path and compare the printed reward delta. - For any external operation, preview the exact command and expected side effects, obtain confirmation, check authentication, then verify the returned ID, visibility, revision, digest, or URL. Record partial failures and retry only the failed/idempotent portion.
What this skill does not claim
Help/parser checks and mocked/unit evidence validate command contracts only. Docker, cloud providers, model APIs, Hub/registry credentials, Hugging Face, OTLP endpoints, GPU, and frontend build toolchains are optional capabilities and must remain explicitly unverified unless actually exercised with approval.
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).