[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PSE2YVS430EPTD4CS6N9GT":3,"skill-same:01M6PSE2YVS430EPTD4CS6N9GT":114},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6PSE2YVS430EPTD4CS6N9GT","tao-run-automl-deft-pipeline",null,"Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. This is the default entry point for any \"run the AOI workflow\", \"fine-tune my PCB AOI model end-to-end\", \"improve my AOI ChangeNet model\", or \"AOI workflow with AutoML\" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. \"run JUST the DEFT loop\", \"skip AutoML, only DEFT\"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include \"run the AOI workflow\", \"AOI end-to-end\", \"AutoML + DEFT\", \"AutoML then DEFT\", \"tune hyperparameters then DEFT\", \"DEFT with AutoML at both ends\", \"warm-start DEFT\", \"improve my AOI model\".","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"automl","tao run automl","tao run automl deft pipeline","tao","deft","pipeline","run","Bash","improve","loop","model","only","default","iteration","end","dataset","training","workflows","hpo","workflow","2026-11-10 10:12:30",false,"---\nname: tao-run-automl-deft-pipeline\ndescription: >\n  Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO),\n  Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on\n  the DEFT-augmented dataset. This is the default entry point for any \"run the AOI workflow\",\n  \"fine-tune my PCB AOI model end-to-end\", \"improve my AOI ChangeNet model\", or \"AOI workflow\n  with AutoML\" request — route here instead of tao-run-deft-aoi directly unless the user\n  explicitly asks for the DEFT loop ONLY (e.g. \"run JUST the DEFT loop\", \"skip AutoML, only\n  DEFT\"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML\n  baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML\n  refinement on the iteration-augmented dataset. Trigger phrases include \"run the AOI\n  workflow\", \"AOI end-to-end\", \"AutoML + DEFT\", \"AutoML then DEFT\", \"tune hyperparameters then\n  DEFT\", \"DEFT with AutoML at both ends\", \"warm-start DEFT\", \"improve my AOI model\".\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit. Workflows (tao-run-automl, tao-run-deft-aoi) declare additional requirements.\nmetadata:\n  author: NVIDIA Corporation\n  version: \"0.4.0\"\nallowed-tools: Read Skill Bash Write\ntags:\n- tao\n- applications\n---\n\n# AutoML + DEFT Pipeline\n\nA workflow-bridge skill that runs **three phases** in sequence by delegating to two existing skills — `tao-run-automl` for HPO and a DEFT application skill (default `tao-run-deft-aoi` for AOI; other `skills\u002Fapplications\u002Fdeft-*` skills for non-AOI cases) for the iterative data-improvement loop.\n\nThis skill **does not** re-implement AutoML or DEFT. It owns only the connective tissue: HPO spec inputs, the spec-handoff between AutoML and DEFT, and the post-DEFT AutoML re-run on the augmented dataset.\n\n## When this skill applies\n\n- User asks to \"run the AOI workflow\" or \"improve my AOI ChangeNet model\" — **default to this skill**, not `tao-run-deft-aoi` directly. The bare DEFT loop is the inner stage of this pipeline.\n- User wants AutoML and DEFT chained on the same model\u002Fdataset\n- User says \"AutoML at both ends\", \"tune HPs then DEFT\", \"warm-start DEFT\", \"AutoML before and after DEFT\"\n- User has an AutoML-tuned spec and asks how to feed it into DEFT\n\n## When this skill does NOT apply\n\n- User explicitly asks for the DEFT loop only (\"run JUST the DEFT loop\", \"skip AutoML\") → use `tao-run-deft-aoi` directly\n- User wants only AutoML with no follow-on DEFT → use `tao-run-automl` directly\n- User is doing zero-shot eval, RAG, or non-training workflows\n\n---\n\n## The mental model\n\n```\nPhase 1 (AutoML baseline)        Phase 2 (DEFT loop, plain train)        Phase 3 (AutoML refinement)\n─────────────────────────        ────────────────────────────────        ───────────────────────────\nspecs\u002Fbaseline_spec.yaml         (Phase 1 winner pre-seeds baseline      ${RESULTS_DIR}\u002Fiter${N}\u002Fdataset\u002F\ntrain\u002Fbase\u002Ftraining_set.csv       — DEFT skips its baseline train)       train_combined_iter${N}.csv\n        │                                       │                                       │\n        ▼                                       ▼                                       ▼\n[ AutoML HPO sweep ]               [ DEFT: baseline-inference → RCA       [ AutoML HPO sweep ]\n   N recommendations                 → iter 1..N (plain retrain) ]        re-tunes HPs against the\n   pick best by val_loss \u002F FAR      RCA \u002F route \u002F SDG \u002F mining             DEFT-augmented dataset\n        │                                       │                                       │\n        ▼                                       ▼                                       ▼\nbest HPs spec + ckpt ─────►      DEFT-augmented CSV ───────────►        final best checkpoint\n                                 + iter winner checkpoint               (the deliverable; no\n                                 (Phase 3 warm-starts from it)           further retrain)\n```\n\nThe handoffs are:\n\n- **Phase 1 → Phase 2**: a *spec file* AND the *winning checkpoint*. Retraining the same HPs in DEFT's baseline step is wasted compute, so the bridge deep-merges Phase 1's winning HPs onto `baseline_spec.yaml`, copies the winning checkpoint into `${RESULTS_DIR}\u002Fbaseline\u002Ftrain\u002F` under the filename DEFT expects, and pre-populates `deft_state.json` + `loop_log.jsonl` so DEFT resumes at baseline inference → evaluate → RCA → iter 1. DEFT itself stays plain-train (`automl_policy: off` preserved). Verbatim 4-step procedure in `references\u002Fhandoff.md`.\n- **Phase 2 → Phase 3**: a *training CSV* AND the *iter winner's checkpoint*. The CSV (`train_combined_iter${N_final}.csv`) is AutoML's training data; the checkpoint (`iterations.\u003Cbest>.best_ckpt_path` from `deft_state.json`) is wired into each rec's `train.pretrained_model_path` so Phase 3 **fine-tunes from Phase 2's winner** rather than from scratch. Without this warm-start Phase 3 routinely regresses vs the iter winner. Phase 3's winning checkpoint is the deliverable — no separate retrain after Phase 3. See `references\u002Fhandoff.md`.\n\n## Why three phases instead of two\n\n- **Phase 1 alone** finds good HPs on the *original* training distribution, but the model still has the distributional gaps DEFT is designed to fill.\n- **Phase 2 alone** (just DEFT) fills the gaps but uses whatever HPs `specs\u002Fbaseline_spec.yaml` was hand-authored with — usually not optimal.\n- **Phase 3 alone** would run AutoML against the augmented dataset, but without a tuned baseline the DEFT loop's iteration cost is higher (slower convergence, more iterations to hit the KPI).\n\nRunning all three: AutoML cheap-tunes once on the original data, DEFT does the heavy data work with reasonable HPs, then AutoML tunes again on the now-richer dataset. Phase 3 is the most important of the three for the final deployed FAR\u002Frecall.\n\n## Cost up-front\n\nThe pipeline is sequential. Total wall-clock ≈ Phase 1 (N_automl × per-rec train) + Phase 2 (M iterations × per-iter cost) + Phase 3 (N_automl × per-rec train).\n\nNote that **Phase 2 has no separate baseline train** — Phase 1's winning checkpoint is reused as DEFT's baseline, so the baseline cost lands inside Phase 1's N_automl trainings rather than as an extra retrain. Surface this to the user before kickoff. Typically Phase 2's iterations still dominate (each includes SDG + retrain), but Phase 1 and Phase 3 each add several hours on a single-GPU box. Use the per-job estimate from the user's setup (if they have one) rather than guessing minutes. See `references\u002Fpitfalls.md` for the per-phase cost breakdown.\n\n---\n\n## Consolidated Pre-Flight — one gate, all three phases\n\n**The pipeline has exactly one user gate.** Before any side-effecting action (docker pull, docker login, any job-launch call delegated to a downstream skill, file mutations under `${RESULTS_DIR}\u002F`), the agent must produce a single consolidated Pre-Flight Summary that subsumes every downstream skill's preflight. Once the user approves, the run is autonomous through all three phases — no further interactive pauses.\n\nThe user explicitly does not want to be paged between phases. The DEFT loop's own inline `## Pre-Flight Summary` gate becomes a **zero-question display step** (every value pre-supplied), as does `tao-run-automl`'s shared launch preflight in Phases 1 and 3.\n\nBefore printing the gate the agent must read every downstream preflight section in full and run **every read-only check** those sections prescribe, surfacing each *outcome* in the summary. Running every step of the DEFT skill's `## Pre-Flight` is mandatory — if any step is skipped the consolidated gate is invalid and the pipeline must not advance. The summary must include, in order: (1) workspace\u002Fhost\u002Fplatform\u002Fnetwork, (2) credentials SET\u002FUNSET status, (3) resolved container image URIs with PRESENT\u002FMISSING, (4) dataset table with leakage check, (5) Phase 1 config, (6) Phase 2 config incl. pre-seeded baseline source, (7) Phase 3 config, (8) compute estimate, (9) the confirmation line. After the gate, pass every collected value through to each downstream skill so it has nothing to ask. The only allowed post-gate pauses are mid-run hard-stop safety gates (e.g. DEFT's KPI regression gate); call them out in the summary.\n\nSee `references\u002Fpreflight.md` for the full build procedure, the exact mandatory contents of each summary section (with the GPU memory rule of thumb, DEFT loop defaults, and required inputs verbatim), the downstream gate-suppression inputs, and the fallback when an older skill-bank version hard-codes its own STOP gate.\n\n---\n\n## Phase 1 — AutoML baseline\n\nInvoke `tao-skill-bank:tao-run-automl` with:\n\n| Input | AOI default | Notes |\n|---|---|---|\n| `network_arch` | `visual-changenet` | Same model the DEFT loop expects |\n| `train_dataset_uri` | `\u003Cworkspace>\u002Ftrain\u002Fbase\u002Ftraining_set.csv` | Same training set DEFT will start from |\n| `eval_dataset_uri` | `\u003Cworkspace>\u002Ftrain\u002Fbase\u002Fvalidation_set.csv` | Held-out — must NOT be the KPI test set (`\u003Cworkspace>\u002Fkpi\u002Ftesting_set.csv`), since that set is reserved for DEFT's final reporting |\n| `metric` | FAR @ 100% recall (preferred) or `val_loss` | See `references\u002Fpitfalls.md` — ChangeNet AOI is class-imbalanced, val_loss alone can mode-collapse |\n| `algorithm` | `bayesian` | LLM-brain or `autoresearch` if compute is tight |\n| `automl_max_recommendations` | 5–10 for AOI | More recs = better HPs but linear in compute |\n| `spec_overrides` | Pin epochs \u002F batch_size; sweep optimizer-related HPs only | Otherwise AutoML wanders into long-train regimes that blow Phase 2's budget |\n\nAfter the sweep finishes, AutoML's `result[\"best\"][\"specs\"]` is the winning hyperparameter dict.\n\n### Handoff to Phase 2\n\nPhase 1 hands over **two artifacts**: the winning *spec* and the winning *checkpoint*. Instead of retraining the same HPs in DEFT's baseline step, pre-seed DEFT's baseline state from Phase 1's outputs so DEFT starts at baseline inference → evaluate → RCA → iter 1. The four steps — write the merged `baseline_spec_automl.yaml`, copy the winning checkpoint into `${RESULTS_DIR}\u002Fbaseline\u002Ftrain\u002F`, initialise `deft_state.json` with `iterations.baseline.stage_completed == \"train\"` (and append the matching `loop_log.jsonl` entry), then invoke DEFT — are given verbatim with the exact code in `references\u002Fhandoff.md`. `automl_policy: off` inside the loop is preserved.\n\n### Quality check before handing off\n\nRun a quick eval of the winning checkpoint against the held-out set: per-class prediction counts (if it collapsed to one class, evaluate the 2nd or 3rd best instead) and a comparison to a zero-shot ChangeNet baseline (if AutoML did not improve over zero-shot, surface that and pause). See `references\u002Fhandoff.md`.\n\n---\n\n## Phase 2 — DEFT loop (plain training, baseline pre-seeded from Phase 1)\n\nInvoke `tao-skill-bank:tao-run-deft-aoi` (read its `SKILL.md` for the full interface). For non-AOI applications, invoke the matching DEFT skill; the handoff shape is the same.\n\n**The DEFT loop's baseline-train sub-step is skipped.** Phase 1 already produced a checkpoint trained at the winning HPs, and Phase 1's handoff (see above) pre-populated `${RESULTS_DIR}\u002Fbaseline\u002Ftrain\u002F` and `${RESULTS_DIR}\u002Fdeft_state.json` so DEFT resumes at baseline inference → evaluate → RCA → iter 1. The rest of the DEFT loop runs unchanged. **Do not modify its `automl_policy: off` invariant.**\n\nThe DEFT loop owns:\n\n- The Pre-Flight Summary display step — **not** a fresh user gate. The Consolidated Pre-Flight (above) is the single gate; the DEFT summary still prints as an audit-trail display of the pre-seeded `baseline\u002Ftrain\u002F` source but must not re-prompt, since every input was collected in the consolidated gate.\n- Baseline inference → evaluate → RCA on the pre-seeded checkpoint, and the full per-iteration RCA → routing → SDG → mining → assemble → train cycle.\n- KPI gating and stop conditions; `${RESULTS_DIR}\u002F` layout, `deft_state.json`, `loop_log.jsonl`, `DEFT_Loop_Report.html`.\n\nAfter the loop exits (KPI met or `max_iterations` reached), capture two values from `deft_state.json`:\n\n- `iterations.\u003Cbest>.best_ckpt_path` — the loop's best plain-train checkpoint\n- The final iteration label `N_final` — used to locate the augmented training CSV\n\nIf the DEFT loop hard-stops on an unrecoverable gate, **skip Phase 3**. There is no validated augmented CSV to feed AutoML.\n\n---\n\n## Phase 3 — AutoML refinement on the DEFT-augmented dataset\n\nRe-invoke `tao-skill-bank:tao-run-automl` with the augmented training CSV as the train dataset, the same held-out validation CSV as before, and **Phase 2's iter winner checkpoint as the warm-start**:\n\n| Input | AOI value |\n|---|---|\n| `network_arch` | `visual-changenet` |\n| `train_dataset_uri` | `${RESULTS_DIR}\u002Fiter${N_final}\u002Fdataset\u002Ftrain_combined_iter${N_final}.csv` |\n| `eval_dataset_uri` | Same as Phase 1 (`\u003Cworkspace>\u002Ftrain\u002Fbase\u002Fvalidation_set.csv`) — keep the comparison apples-to-apples |\n| `metric` | Same metric as Phase 1 |\n| `algorithm` | Same as Phase 1 |\n| `automl_max_recommendations` | 5–10 |\n| Initial spec | Start from `\u003Cworkspace>\u002Fspecs\u002Fbaseline_spec_automl.yaml` (Phase 1's winner) — gives the sweep a strong centroid to refine around |\n| **Warm-start checkpoint** | **`iterations.\u003Cbest>.best_ckpt_path` from `${RESULTS_DIR}\u002Fdeft_state.json`** — set `spec_overrides[\"train\"][\"pretrained_model_path\"]` to this path. Each Phase 3 rec then **fine-tunes from Phase 2's winner** instead of training from scratch. |\n\nThe warm-start is **mandatory**: with no warm-start, every rec starts from random init with only 10-20 epochs to reconverge, Phase 3's `val_loss` regresses 0.03-0.05 vs iter1, and the `_pick_best` safety net silently rolls back to the iter winner — wasting Phase 3's compute. The concrete `spec_overrides` code (selecting the lowest-`far_pct` iteration, excluding any prior `final_automl`), the broad-exploration tradeoff, output to `${RESULTS_DIR}\u002Ffinal_automl\u002F`, and wiring Phase 3's checkpoint back into the DEFT report via `iterations.final_automl` + re-running `prepare_inference_spec.py` (with the `_pick_best` regression safety net) are all in `references\u002Fhandoff.md`.\n\n---\n\n## Pitfalls and quality checks\n\nThese apply to both AutoML phases — bake them into agent behavior, don't just paste once. The full detail is in `references\u002Fpitfalls.md`:\n\n- **Metric pitfalls (AOI is class-imbalanced).** ChangeNet AOI is PASS-dominant; `val_loss` can mode-collapse to a zero-recall PASS-everything model. Prefer FAR @ 100%-recall directly, or gate val_loss with a `pred_counts` sanity check, or decide top-K by FAR @ 100%-recall. For balanced \u002F regression tasks, val_loss is fine.\n- **Run-to-run noise.** AutoML can show 2–3× metric variance for the same config. If the winner looks suspiciously better than the runner-up, re-run with a fresh seed before committing the spec to Phase 2.\n- **Cleanliness (data leakage).** Both AutoML phases use a validation set distinct from the KPI test set (`kpi\u002Ftesting_set.csv`), which stays untouched until DEFT's evaluate stage. Phase 3 trains on the augmented CSV but keeps the same val set so Phase 1 and Phase 3 numbers stay comparable.\n- **Compute budget.** Surface the per-phase structure up front and only give a wall-clock range after the user supplies their per-job time.\n\n---\n\n## Quick Start (AOI worked example)\n\nWhen starting fresh from \"run the AOI workflow\", the agent delivers a three-phase worded message to the user (Phase 1 AutoML baseline → Phase 2 DEFT loop → Phase 3 AutoML refinement, with the cost framing and \"OK to proceed?\" close), then after confirmation invokes `tao-run-automl` (Phase 1), writes the merged spec, pre-seeds `deft_state.json`, invokes `tao-run-deft-aoi` (Phase 2) with every input pre-supplied, and invokes `tao-run-automl` again (Phase 3) — with no further pauses unless a downstream skill hits an unrecoverable hard-stop gate — then summarizes the trajectory (baseline AutoML best → DEFT iter 1 → ... → DEFT iter N_final → Phase 3 best).\n\nSee `references\u002Fquick-start.md` for the verbatim customer-facing message and the exact post-confirmation invoke sequence.\n\n## Non-AOI DEFT applications\n\nThe same three-phase pattern applies to other DEFT skills — swap `network_arch`, the Phase 2 DEFT skill, the spec\u002Fcheckpoint path conventions, and the Phase 3 augmented-CSV path. The handoff shape (Phase 1 emits spec + checkpoint that pre-seeds the DEFT baseline, Phase 2 emits an augmented dataset, Phase 3 emits the final checkpoint) is identical, and the baseline-skip mechanism is generic to any DEFT-style loop with a resumable baseline state. See `references\u002Fquick-start.md`.\n\n---\n\n## See also\n\n- `tao-skill-bank:tao-run-automl` — AutoML interface, algorithms, HP ranges\n- `tao-skill-bank:tao-run-deft-aoi` — full DEFT AOI loop (Phase 2 default)\n- `tao-skill-bank:tao-train-visual-changenet` — underlying ChangeNet train\u002Feval\u002Finfer skill (used by both AutoML and DEFT)\n- Other `skills\u002Fapplications\u002Fdeft-*` skills — non-AOI Phase 2 targets\n- `references\u002Fpreflight.md` — building the consolidated pre-flight gate\n- `references\u002Fhandoff.md` — Phase 1→2 pre-seed, Phase 2 quality check, Phase 3 warm-start + report wiring\n- `references\u002Fpitfalls.md` — metric, noise, leakage, and compute-budget guidance\n- `references\u002Fquick-start.md` — verbatim worked-example message and non-AOI variant\n","# AutoML + DEFT Pipeline\n\nA workflow-bridge skill that runs **three phases** in sequence by delegating to two existing skills — `tao-run-automl` for HPO and a DEFT application skill (default `tao-run-deft-aoi` for AOI; other `skills\u002Fapplications\u002Fdeft-*` skills for non-AOI cases) for the iterative data-improvement loop.\n\nThis skill **does not** re-implement AutoML or DEFT. It owns only the connective tissue: HPO spec inputs, the spec-handoff between AutoML and DEFT, and the post-DEFT AutoML re-run on the augmented dataset.\n\n## When this skill applies\n\n- User asks to \"run the AOI workflow\" or \"improve my AOI ChangeNet model\" — **default to this skill**, not `tao-run-deft-aoi` directly. The bare DEFT loop is the inner stage of this pipeline.\n- User wants AutoML and DEFT chained on the same model\u002Fdataset\n- User says \"AutoML at both ends\", \"tune HPs then DEFT\", \"warm-start DEFT\", \"AutoML before and after DEFT\"\n- User has an AutoML-tuned spec and asks how to feed it into DEFT\n\n## When this skill does NOT apply\n\n- User explicitly asks for the DEFT loop only (\"run JUST the DEFT loop\", \"skip AutoML\") → use `tao-run-deft-aoi` directly\n- User wants only AutoML with no follow-on DEFT → use `tao-run-automl` directly\n- User is doing zero-shot eval, RAG, or non-training workflows\n\n---\n\n## The mental model\n\n```\nPhase 1 (AutoML baseline)        Phase 2 (DEFT loop, plain train)        Phase 3 (AutoML refinement)\n─────────────────────────        ────────────────────────────────        ───────────────────────────\nspecs\u002Fbaseline_spec.yaml         (Phase 1 winner pre-seeds baseline      ${RESULTS_DIR}\u002Fiter${N}\u002Fdataset\u002F\ntrain\u002Fbase\u002Ftraining_set.csv       — DEFT skips its baseline train)       train_combined_iter${N}.csv\n        │                                       │                                       │\n        ▼                                       ▼                                       ▼\n[ AutoML HPO sweep ]               [ DEFT: baseline-inference → RCA       [ AutoML HPO sweep ]\n   N recommendations                 → iter 1..N (plain retrain) ]        re-tunes HPs against the\n   pick best by val_loss \u002F FAR      RCA \u002F route \u002F SDG \u002F mining             DEFT-augmented dataset\n        │                                       │                                       │\n        ▼                                       ▼                                       ▼\nbest HPs spec + ckpt ─────►      DEFT-augmented CSV ───────────►        final best checkpoint\n                                 + iter winner checkpoint               (the deliverable; no\n                                 (Phase 3 warm-starts from it)           further retrain)\n```\n\nThe handoffs are:\n\n- **Phase 1 → Phase 2**: a *spec file* AND the *winning checkpoint*. Retraining the same HPs in DEFT's baseline step is wasted compute, so the bridge deep-merges Phase 1's winning HPs onto `baseline_spec.yaml`, copies the winning checkpoint into `${RESULTS_DIR}\u002Fbaseline\u002Ftrain\u002F` under the filename DEFT expects, and pre-populates `deft_state.json` + `loop_log.jsonl` so DEFT resumes at baseline inference → evaluate → RCA → iter 1. DEFT itself stays plain-train (`automl_policy: off` preserved). Verbatim 4-step procedure in `references\u002Fhandoff.md`.\n- **Phase 2 → Phase 3**: a *training CSV* AND the *iter winner's checkpoint*. The CSV (`train_combined_iter${N_final}.csv`) is AutoML's training data; the checkpoint (`iterations.\u003Cbest>.best_ckpt_path` from `deft_state.json`) is wired into each rec's `train.pretrained_model_path` so Phase 3 **fine-tunes from Phase 2's winner** rather than from scratch. Without this warm-start Phase 3 routinely regresses vs the iter winner. Phase 3's winning checkpoint is the deliverable — no separate retrain after Phase 3. See `references\u002Fhandoff.md`.\n\n## Why three phases instead of two\n\n- **Phase 1 alone** finds good HPs on the *original* training distribution, but the model still has the distributional gaps DEFT is designed to fill.\n- **Phase 2 alone** (just DEFT) fills the gaps but uses whatever HPs `specs\u002Fbaseline_spec.yaml` was hand-authored with — usually not optimal.\n- **Phase 3 alone** would run AutoML against the augmented dataset, but without a tuned baseline the DEFT loop's iteration cost is higher (slower convergence, more iterations to hit the KPI).\n\nRunning all three: AutoML cheap-tunes once on the original data, DEFT does the heavy data work with reasonable HPs, then AutoML tunes again on the now-richer dataset. Phase 3 is the most important of the three for the final deployed FAR\u002Frecall.\n\n## Cost up-front\n\nThe pipeline is sequential. Total wall-clock ≈ Phase 1 (N_automl × per-rec train) + Phase 2 (M iterations × per-iter cost) + Phase 3 (N_automl × per-rec train).\n\nNote that **Phase 2 has no separate baseline train** — Phase 1's winning checkpoint is reused as DEFT's baseline, so the baseline cost lands inside Phase 1's N_automl trainings rather than as an extra retrain. Surface this to the user before kickoff. Typically Phase 2's iterations still dominate (each includes SDG + retrain), but Phase 1 and Phase 3 each add several hours on a single-GPU box. Use the per-job estimate from the user's setup (if they have one) rather than guessing minutes. See `references\u002Fpitfalls.md` for the per-phase cost breakdown.\n\n---\n\n## Consolidated Pre-Flight — one gate, all three phases\n\n**The pipeline has exactly one user gate.** Before any side-effecting action (docker pull, docker login, any job-launch call delegated to a downstream skill, file mutations under `${RESULTS_DIR}\u002F`), the agent must produce a single consolidated Pre-Flight Summary that subsumes every downstream skill's preflight. Once the user approves, the run is autonomous through all three phases — no further interactive pauses.\n\nThe user explicitly does not want to be paged between phases. The DEFT loop's own inline `## Pre-Flight Summary` gate becomes a **zero-question display step** (every value pre-supplied), as does `tao-run-automl`'s shared launch preflight in Phases 1 and 3.\n\nBefore printing the gate the agent must read every downstream preflight section in full and run **every read-only check** those sections prescribe, surfacing each *outcome* in the summary. Running every step of the DEFT skill's `## Pre-Flight` is mandatory — if any step is skipped the consolidated gate is invalid and the pipeline must not advance. The summary must include, in order: (1) workspace\u002Fhost\u002Fplatform\u002Fnetwork, (2) credentials SET\u002FUNSET status, (3) resolved container image URIs with PRESENT\u002FMISSING, (4) dataset table with leakage check, (5) Phase 1 config, (6) Phase 2 config incl. pre-seeded baseline source, (7) Phase 3 config, (8) compute estimate, (9) the confirmation line. After the gate, pass every collected value through to each downstream skill so it has nothing to ask. The only allowed post-gate pauses are mid-run hard-stop safety gates (e.g. DEFT's KPI regression gate); call them out in the summary.\n\nSee `references\u002Fpreflight.md` for the full build procedure, the exact mandatory contents of each summary section (with the GPU memory rule of thumb, DEFT loop defaults, and required inputs verbatim), the downstream gate-suppression inputs, and the fallback when an older skill-bank version hard-codes its own STOP gate.\n\n---\n\n## Phase 1 — AutoML baseline\n\nInvoke `tao-skill-bank:tao-run-automl` with:\n\n| Input | AOI default | Notes |\n|---|---|---|\n| `network_arch` | `visual-changenet` | Same model the DEFT loop expects |\n| `train_dataset_uri` | `\u003Cworkspace>\u002Ftrain\u002Fbase\u002Ftraining_set.csv` | Same training set DEFT will start from |\n| `eval_dataset_uri` | `\u003Cworkspace>\u002Ftrain\u002Fbase\u002Fvalidation_set.csv` | Held-out — must NOT be the KPI test set (`\u003Cworkspace>\u002Fkpi\u002Ftesting_set.csv`), since that set is reserved for DEFT's final reporting |\n| `metric` | FAR @ 100% recall (preferred) or `val_loss` | See `references\u002Fpitfalls.md` — ChangeNet AOI is class-imbalanced, val_loss alone can mode-collapse |\n| `algorithm` | `bayesian` | LLM-brain or `autoresearch` if compute is tight |\n| `automl_max_recommendations` | 5–10 for AOI | More recs = better HPs but linear in compute |\n| `spec_overrides` | Pin epochs \u002F batch_size; sweep optimizer-related HPs only | Otherwise AutoML wanders into long-train regimes that blow Phase 2's budget |\n\nAfter the sweep finishes, AutoML's `result[\"best\"][\"specs\"]` is the winning hyperparameter dict.\n\n### Handoff to Phase 2\n\nPhase 1 hands over **two artifacts**: the winning *spec* and the winning *checkpoint*. Instead of retraining the same HPs in DEFT's baseline step, pre-seed DEFT's baseline state from Phase 1's outputs so DEFT starts at baseline inference → evaluate → RCA → iter 1. The four steps — write the merged `baseline_spec_automl.yaml`, copy the winning checkpoint into `${RESULTS_DIR}\u002Fbaseline\u002Ftrain\u002F`, initialise `deft_state.json` with `iterations.baseline.stage_completed == \"train\"` (and append the matching `loop_log.jsonl` entry), then invoke DEFT — are given verbatim with the exact code in `references\u002Fhandoff.md`. `automl_policy: off` inside the loop is preserved.\n\n### Quality check before handing off\n\nRun a quick eval of the winning checkpoint against the held-out set: per-class prediction counts (if it collapsed to one class, evaluate the 2nd or 3rd best instead) and a comparison to a zero-shot ChangeNet baseline (if AutoML did not improve over zero-shot, surface that and pause). See `references\u002Fhandoff.md`.\n\n---\n\n## Phase 2 — DEFT loop (plain training, baseline pre-seeded from Phase 1)\n\nInvoke `tao-skill-bank:tao-run-deft-aoi` (read its `SKILL.md` for the full interface). For non-AOI applications, invoke the matching DEFT skill; the handoff shape is the same.\n\n**The DEFT loop's baseline-train sub-step is skipped.** Phase 1 already produced a checkpoint trained at the winning HPs, and Phase 1's handoff (see above) pre-populated `${RESULTS_DIR}\u002Fbaseline\u002Ftrain\u002F` and `${RESULTS_DIR}\u002Fdeft_state.json` so DEFT resumes at baseline inference → evaluate → RCA → iter 1. The rest of the DEFT loop runs unchanged. **Do not modify its `automl_policy: off` invariant.**\n\nThe DEFT loop owns:\n\n- The Pre-Flight Summary display step — **not** a fresh user gate. The Consolidated Pre-Flight (above) is the single gate; the DEFT summary still prints as an audit-trail display of the pre-seeded `baseline\u002Ftrain\u002F` source but must not re-prompt, since every input was collected in the consolidated gate.\n- Baseline inference → evaluate → RCA on the pre-seeded checkpoint, and the full per-iteration RCA → routing → SDG → mining → assemble → train cycle.\n- KPI gating and stop conditions; `${RESULTS_DIR}\u002F` layout, `deft_state.json`, `loop_log.jsonl`, `DEFT_Loop_Report.html`.\n\nAfter the loop exits (KPI met or `max_iterations` reached), capture two values from `deft_state.json`:\n\n- `iterations.\u003Cbest>.best_ckpt_path` — the loop's best plain-train checkpoint\n- The final iteration label `N_final` — used to locate the augmented training CSV\n\nIf the DEFT loop hard-stops on an unrecoverable gate, **skip Phase 3**. There is no validated augmented CSV to feed AutoML.\n\n---\n\n## Phase 3 — AutoML refinement on the DEFT-augmented dataset\n\nRe-invoke `tao-skill-bank:tao-run-automl` with the augmented training CSV as the train dataset, the same held-out validation CSV as before, and **Phase 2's iter winner checkpoint as the warm-start**:\n\n| Input | AOI value |\n|---|---|\n| `network_arch` | `visual-changenet` |\n| `train_dataset_uri` | `${RESULTS_DIR}\u002Fiter${N_final}\u002Fdataset\u002Ftrain_combined_iter${N_final}.csv` |\n| `eval_dataset_uri` | Same as Phase 1 (`\u003Cworkspace>\u002Ftrain\u002Fbase\u002Fvalidation_set.csv`) — keep the comparison apples-to-apples |\n| `metric` | Same metric as Phase 1 |\n| `algorithm` | Same as Phase 1 |\n| `automl_max_recommendations` | 5–10 |\n| Initial spec | Start from `\u003Cworkspace>\u002Fspecs\u002Fbaseline_spec_automl.yaml` (Phase 1's winner) — gives the sweep a strong centroid to refine around |\n| **Warm-start checkpoint** | **`iterations.\u003Cbest>.best_ckpt_path` from `${RESULTS_DIR}\u002Fdeft_state.json`** — set `spec_overrides[\"train\"][\"pretrained_model_path\"]` to this path. Each Phase 3 rec then **fine-tunes from Phase 2's winner** instead of training from scratch. |\n\nThe warm-start is **mandatory**: with no warm-start, every rec starts from random init with only 10-20 epochs to reconverge, Phase 3's `val_loss` regresses 0.03-0.05 vs iter1, and the `_pick_best` safety net silently rolls back to the iter winner — wasting Phase 3's compute. The concrete `spec_overrides` code (selecting the lowest-`far_pct` iteration, excluding any prior `final_automl`), the broad-exploration tradeoff, output to `${RESULTS_DIR}\u002Ffinal_automl\u002F`, and wiring Phase 3's checkpoint back into the DEFT report via `iterations.final_automl` + re-running `prepare_inference_spec.py` (with the `_pick_best` regression safety net) are all in `references\u002Fhandoff.md`.\n\n---\n\n## Pitfalls and quality checks\n\nThese apply to both AutoML phases — bake them into agent behavior, don't just paste once. The full detail is in `references\u002Fpitfalls.md`:\n\n- **Metric pitfalls (AOI is class-imbalanced).** ChangeNet AOI is PASS-dominant; `val_loss` can mode-collapse to a zero-recall PASS-everything model. Prefer FAR @ 100%-recall directly, or gate val_loss with a `pred_counts` sanity check, or decide top-K by FAR @ 100%-recall. For balanced \u002F regression tasks, val_loss is fine.\n- **Run-to-run noise.** AutoML can show 2–3× metric variance for the same config. If the winner looks suspiciously better than the runner-up, re-run with a fresh seed before committing the spec to Phase 2.\n- **Cleanliness (data leakage).** Both AutoML phases use a validation set distinct from the KPI test set (`kpi\u002Ftesting_set.csv`), which stays untouched until DEFT's evaluate stage. Phase 3 trains on the augmented CSV but keeps the same val set so Phase 1 and Phase 3 numbers stay comparable.\n- **Compute budget.** Surface the per-phase structure up front and only give a wall-clock range after the user supplies their per-job time.\n\n---\n\n## Quick Start (AOI worked example)\n\nWhen starting fresh from \"run the AOI workflow\", the agent delivers a three-phase worded message to the user (Phase 1 AutoML baseline → Phase 2 DEFT loop → Phase 3 AutoML refinement, with the cost framing and \"OK to proceed?\" close), then after confirmation invokes `tao-run-automl` (Phase 1), writes the merged spec, pre-seeds `deft_state.json`, invokes `tao-run-deft-aoi` (Phase 2) with every input pre-supplied, and invokes `tao-run-automl` again (Phase 3) — with no further pauses unless a downstream skill hits an unrecoverable hard-stop gate — then summarizes the trajectory (baseline AutoML best → DEFT iter 1 → ... → DEFT iter N_final → Phase 3 best).\n\nSee `references\u002Fquick-start.md` for the verbatim customer-facing message and the exact post-confirmation invoke sequence.\n\n## Non-AOI DEFT applications\n\nThe same three-phase pattern applies to other DEFT skills — swap `network_arch`, the Phase 2 DEFT skill, the spec\u002Fcheckpoint path conventions, and the Phase 3 augmented-CSV path. The handoff shape (Phase 1 emits spec + checkpoint that pre-seeds the DEFT baseline, Phase 2 emits an augmented dataset, Phase 3 emits the final checkpoint) is identical, and the baseline-skip mechanism is generic to any DEFT-style loop with a resumable baseline state. See `references\u002Fquick-start.md`.\n\n---\n\n## See also\n\n- `tao-skill-bank:tao-run-automl` — AutoML interface, algorithms, HP ranges\n- `tao-skill-bank:tao-run-deft-aoi` — full DEFT AOI loop (Phase 2 default)\n- `tao-skill-bank:tao-train-visual-changenet` — underlying ChangeNet train\u002Feval\u002Finfer skill (used by both AutoML and DEFT)\n- Other `skills\u002Fapplications\u002Fdeft-*` skills — non-AOI Phase 2 targets\n- `references\u002Fpreflight.md` — building the consolidated pre-flight gate\n- `references\u002Fhandoff.md` — Phase 1→2 pre-seed, Phase 2 quality check, Phase 3 warm-start + report wiring\n- `references\u002Fpitfalls.md` — metric, noise, leakage, and compute-budget guidance\n- `references\u002Fquick-start.md` — verbatim worked-example message and non-AOI variant\n",{"name":5,"tags":49,"license":15,"metadata":51,"description":54,"allowed-tools":55,"compatibility":56},[27,50],"applications",{"author":52,"version":53},"NVIDIA Corporation","0.4.0","Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase 3 AutoML refinement on the DEFT-augmented dataset. This is the default entry point for any \"run the AOI workflow\", \"fine-tune my PCB AOI model end-to-end\", \"improve my AOI ChangeNet model\", or \"AOI workflow with AutoML\" request — route here instead of tao-run-deft-aoi directly unless the user explicitly asks for the DEFT loop ONLY (e.g. \"run JUST the DEFT loop\", \"skip AutoML, only DEFT\"). Also handles the same three-phase pattern for non-AOI DEFT applications — AutoML baseline then DEFT loop warm-started from AutoML's winning HPs then post-DEFT AutoML refinement on the iteration-augmented dataset. Trigger phrases include \"run the AOI workflow\", \"AOI end-to-end\", \"AutoML + DEFT\", \"AutoML then DEFT\", \"tune hyperparameters then DEFT\", \"DEFT with AutoML at both ends\", \"warm-start DEFT\", \"improve my AOI model\".\n","Read Skill Bash Write","Requires docker + nvidia-container-toolkit. Workflows (tao-run-automl, tao-run-deft-aoi) declare additional requirements.","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".claude\u002Fskills\u002Ftao-run-automl-deft-pipeline","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui","https:\u002F\u002Fneuroads.com.br","2026-08-12 00:42:44",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-run-automl-deft-pipeline",{"tool":70,"command":71},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-run-automl-deft-pipeline",{"tool":73,"command":74},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-run-automl-deft-pipeline","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002FSKILL.md",true,[78,84,88,92,96,100,104,108],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"BENCHMARK.md","REFERENCE","参考文档",4392,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002FBENCHMARK.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"evals\u002Fevals.json",856,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002Fevals\u002Fevals.json",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fhandoff.md",6341,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002Freferences\u002Fhandoff.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fpitfalls.md",2586,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002Freferences\u002Fpitfalls.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fpreflight.md",6704,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002Freferences\u002Fpreflight.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fquick-start.md",3684,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002Freferences\u002Fquick-start.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"skill-card.md",4018,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002Fskill-card.md",{"path":109,"resourceType":110,"resourceTypeDesc":111,"sizeBytes":112,"sourceHtmlUrl":113},"skill.oms.sig","OTHER","其他",5541,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-run-automl-deft-pipeline\u002Fskill.oms.sig",[115,138,163,189,207,242],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":126,"publishedAt":44},"01M6PTDCZTXTGSTX4RFK901YSZ","xunit-skill","Generates xUnit.net tests in C#. Covers Fact\u002FTheory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal\", \"C# xUnit\". Triggers on: \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal C#\", \"xUnit.net\".","MIT","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxunit-skill\u002FSKILL.md",[122,125],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[127,128,129,130,131,132,133,134,135,136,137],"xunit","xunit skill","testing","injection","user","use","tests","triggers","unit","unit-testing","C#",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":146,"publishedAt":44},"01M6PTCB59ZTG5FTMWGPYEMMBP","xcuitest-skill","Generates XCUITest UI tests for iOS\u002FiPadOS apps in Swift. Apple's native testing framework for reliable, fast UI automation. Supports local simulators and TestMu AI cloud real devices. Use when user mentions \"XCUITest\", \"XCTest\", \"iOS UI test\", \"Swift test\", \"XCUIApplication\". Triggers on: \"XCUITest\", \"XCTest UI\", \"iOS UI test\", \"Swift UI test\", \"XCUIApplication\", \"TestMu\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxcuitest-skill\u002FSKILL.md",[144,145],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[147,148,129,149,150,151,152,153,132,154,155,156,157,158,133,134,159,160,161,162],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","for","objective",{"skillNo":164,"name":165,"nameZh":6,"description":166,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":167,"categories":168,"keywords":173,"publishedAt":44},"01M6PTATMNTY9NF4J7KSR76YK6","world-builder","Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworld-builder\u002FSKILL.md",[169,172],{"categoryNo":170,"categoryName":171,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[174,175,176,177,178,179,180,181,132,182,183,184,185,186,187,161,188],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","manage","style","via","theme","zone","generative",{"skillNo":190,"name":191,"nameZh":6,"description":192,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":193,"categories":194,"keywords":197,"publishedAt":44},"01M6PT9Z92JTSQEHE1QR0NNW5F","webdriverio-skill","Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions \"WebdriverIO\", \"WDIO\", \"wdio.conf\", \"browser.url\", \"$\", \"$$\". Triggers on: \"WebdriverIO\", \"WDIO\", \"wdio\", \"browser.$\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebdriverio-skill\u002FSKILL.md",[195,196],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[198,129,199,149,200,201,202,203,131,132,204,157,133,134,205,206],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":222,"publishedAt":44},"01M6PT9NVK36ZWCQ69YXK3FR4K","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb\u002FSKILL.md",[213,216,217],{"categoryNo":214,"categoryName":215,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":170,"categoryName":171,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":218,"categoryName":219,"taxonomyType":220,"taxonomyTypeDesc":221},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,134,241],"design","web","guidelines","web design guidelines","web design","css","performance","components","web components","tasks","code","web performance","ui","platform design","html","responsive design","responsive","platform","implementing",{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":119,"licenseFileUrl":6,"sourceHtmlUrl":246,"categories":247,"keywords":250,"publishedAt":44},"01M6PT9A3JKRE3X34276F2FW5R","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwatchos\u002FSKILL.md",[248,249],{"categoryNo":170,"categoryName":171,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":218,"categoryName":219,"taxonomyType":220,"taxonomyTypeDesc":221},[223,225,251,232,235,132,252,253,158,240,254,134,159,255,161,256,257],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]