[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73B8HASMHJV96Z3P5NFFKRE":3,"skill-same:01M73B8HASMHJV96Z3P5NFFKRE":56},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":39,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M73B8HASMHJV96Z3P5NFFKRE","arbor",null,"Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Farbor\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: arbor\ndescription: Applies Arbor Hypothesis Tree Refinement to research artifacts with repeatable evaluators, including model training, agent harnesses, data synthesis and benchmark optimization. Uses persistent hypotheses, isolated experiments, evidence propagation and held-out candidate comparison for multi-experiment research runs. Includes a standard-library state manager and guidance for the RUC-NLPIR Arbor CLI.\nallowed-tools: Read Write Edit Bash Agent\nlicense: MIT license\ncompatibility: Requires Python 3.10+ for the bundled state manager and Git for experiment worktrees. The optional arbor-agent CLI needs a separate installation; autonomous model calls need provider credentials and network access.\nmetadata:\n  version: \"1.6\"\n  last-reviewed: \"2026-09-30\"\n  upstream-version: \"arbor-agent 0.1.4\"\n  skill-author: K-Dense Inc.\n---\n\n# Arbor — Autonomous Optimization via Hypothesis Tree Refinement\n\n## Overview\n\nThis skill runs an **Autonomous Optimization (AO)** loop: starting from an existing artifact and a measurable objective, improve it through many rounds of experiment and evaluation — without step-by-step human supervision, while checking for overfitting to the development signal. It's the right tool when the bottleneck isn't writing one good change, but *organizing dozens of trials* so that lessons accumulate instead of evaporating.\n\nIt implements **Hypothesis Tree Refinement (HTR)** from *Arbor* (Jin et al., 2026). The key idea: keep the research state in a persistent **hypothesis tree** rather than in conversation history. Each node binds a hypothesis, the distilled insight it produced, and a pointer to the artifact version that realizes it. You play the long-lived **coordinator** that owns this tree and decides where to search; short-lived **executor** subagents test one hypothesis each in isolated git worktrees and report back. A **held-out merge gate** admits a change only when it improves on a *test* evaluator executors do not optimize against. This is what turns trial-and-error into cumulative, auditable research.\n\nUse the `scripts\u002Ftree.py` state manager for all the bookkeeping (creating nodes, writing evidence, propagating insights, pruning, the merge gate, the Observe projection). It records scores and decisions; it does **not** run evaluators, create worktrees, verify Git refs, or merge Git branches. Only the coordinator writes shared state, serially; executors return evidence. The helper has no multi-writer locking. Its JSON schema is separate from upstream Arbor checkpoints.\n\n## When to use this skill\n\nReach for Arbor when the task is **iterative improvement of a concrete artifact under an evaluator**:\n- Model training: optimizer\u002Farchitecture\u002Frecipe changes to lower loss or hit a target in fewer steps.\n- Harness\u002Fagent engineering: raising pass rate or accuracy of an agent loop, search harness, or tool-use scaffold.\n- Data synthesis: improving a generation\u002Ffiltering pipeline judged by downstream model behavior.\n- Benchmark optimization: MLE-bench \u002F Kaggle-style \"improve the submission\" tasks.\n- Prompt\u002Fsystem optimization where you can score outputs automatically.\n\nThe distinguishing signals: there's an **artifact you can modify**, an **objective**, a way to **score** candidates, and you expect to run **many experiments**. If the user only wants a single fix or a one-shot answer, this is overkill — just do the work directly. If they want open-ended ideation with no evaluator, use `hypothesis-generation` or `scientific-brainstorming` instead.\n\n## The AO setup — pin this down first\n\nBefore any experiments, establish the task tuple `(M_0, O, E_dev, E_test)`. Record the resolved setup, using the user's existing instructions; clarify only missing decisions:\n\n- **M_0 — initial material**: the artifact to improve (a repo, a script, a config, a prompt). Make sure it's under git and currently runs.\n- **O — objective**: the natural-language goal and the metric *direction* (maximize accuracy? minimize loss\u002Fsteps?).\n- **E_dev — development evaluator**: a command you can run freely during search to score a candidate. Fast, repeatable.\n- **E_test — held-out test evaluator**: a *separate* evaluation protocol (held-out examples or predeclared independent seeds) used only at the merge gate. It must not be used as a search oracle — that's the whole point.\n\nFreeze the evaluator, dataset split, and metric before search, and record their\nversions with each score. Repeated merge decisions on the same held-out set can\nstill adapt the search to that set; a fresh worktree prevents file contamination,\nnot statistical leakage. Keep a final untouched evaluation set for the final claim,\nor disclose that the reported result was selected using repeated gate feedback.\n\nIf the user hasn't given you a clean dev\u002Ftest split, **construct one and say so**. The dev\u002Ftest separation is the mechanism that catches overfitting: a candidate that wins on dev but not on test isn't a success, it's a warning that you're exploiting the feedback signal. A larger run on the same examples is not an independent holdout. If no defensible holdout exists, label results as development-only.\n\nSet `ARBOR_TREE` to the absolute path of this skill's `scripts\u002Ftree.py`, then work from the experiment project directory. The following commands illustrate one run; evaluator commands, scores and refs must be replaced with actual measured evidence. Initialize the run:\n\n```bash\npython \"$ARBOR_TREE\" init \\\n  --objective \"Improve BrowseComp answer accuracy on the search harness\" \\\n  --dev-eval \"python eval.py --split dev --n 50\" \\\n  --test-eval \"python eval.py --split test --n 300\" \\\n  --material \".\" --metric-direction max --branching 3 --max-depth 2 --budget 12\n```\n\nEvaluate `M_0` on the fixed gate protocol before search and record its commit and score:\n\n```bash\npython \"$ARBOR_TREE\" baseline --test-score 45.33 --branch-ref \"baseline-commit\"\n```\n\nThe coordinator is responsible for freezing protocols and evaluating the baseline; these are procedural steps, not automated checks. The baseline command only records evidence supplied by the coordinator, once. `merge` refuses an unscored baseline and non-finite scores. Existing runs with no incumbent need this step; start a new run if the baseline\u002Fevaluator changes. Keep raw evaluator output, seeds, split IDs and evaluator version alongside `.arbor\u002F`.\n\n`--branching` is how many sibling hypotheses you propose per parent; `--max-depth 2` keeps directions at depth 1 and concrete interventions at depth 2 (the paper's default); `--budget` is the number of coordinator cycles. Start small (10–20 cycles). These helper settings are advisory: branching is recorded, depth overruns warn, and the cycle counter can exceed the budget. The coordinator must enforce the agreed stopping limits.\n\n## The coordinator loop\n\nYou run repeated cycles of six steps. This is the heart of HTR; do not collapse it into ad-hoc editing. Run `python \"$ARBOR_TREE\" cycle` once per cycle to track the budget.\n\n### 1. Observe\nBegin every cycle by re-grounding in the tree, not in your memory of the conversation:\n\n```bash\npython \"$ARBOR_TREE\" observe\n```\n\nThis prints the objective, global insights, the active frontier (selectable hypotheses), executed nodes with their evidence, pruned lessons (negative constraints), and the current best artifact. Treating the tree as the source of truth is what keeps you coherent over a long run, after context compression has thrown away the details.\n\n### 2. Ideate\nPick a promising parent and propose a few child hypotheses under it. **Condition on the tree's evidence** — this is the difference between Arbor and random search:\n- Validated insights are assumptions you can build on.\n- Pruned nodes are dead ends to avoid.\n- A \"half-right\" result is a *starting point for a sharper hypothesis*, not a reason to abandon the direction.\n\nEach hypothesis should be a **falsifiable claim about how changing the artifact will move the metric**, not a vague intention. Depth-1 nodes are broad directions (\"the search harness loses correct answers it already retrieved\"); depth-2 nodes are concrete, executable interventions (\"run K=5 independent rollouts and aggregate by evidence dossier instead of majority vote\").\n\n```bash\npython \"$ARBOR_TREE\" add-node --parent n0 --hypothesis \"Verification, not retrieval, is the bottleneck: candidates are found but discarded\"\npython \"$ARBOR_TREE\" add-node --parent n1 --hypothesis \"Aggregate independent rollouts by evidence dossier to recover minority answers\"\npython \"$ARBOR_TREE\" add-node --parent n1 --hypothesis \"Search-augment the judge to verify discarded candidates\"\n```\n\n### 3. Select\nChoose which pending leaves to run next. **Selection is not pure score-maximization** — pick a hypothesis because it has strong prior evidence, because it would resolve an ambiguity its siblings exposed, or because its failure would clarify an important assumption. Frontier control under delayed feedback rewards informative experiments, not just promising ones.\n\n### 4. Dispatch\nRun each selected hypothesis as an **executor subagent in an isolated worktree** (use the host's supported isolation facility, or create distinct worktrees with `git worktree add`). Isolation matters: parallel experiments must not clobber each other or the current best, and exploratory changes stay quarantined until they pass the merge gate.\n\nDispatch siblings **in parallel** (through the host's available subagent tools) when they're independent — comparative evidence within one direction is exactly what makes later pruning and abstraction possible.\n\nGive each executor a tight, **hypothesis-bound** brief. See `references\u002Fexecutor-brief.md` for the full template. The contract that makes HTR work: **the executor may not change the hypothesis when the metric stalls.** It repairs its own code and reruns, but `h_n` is fixed — otherwise the returned score is no longer evidence about the assigned node and the tree's semantics break. The executor returns exactly four things:\n- **dev_score** — a finite dev evaluator result (for selection), or null for an execution failure;\n- **result** — a factual summary of what happened;\n- **insight** — the distilled, reusable lesson (*why* the result supports, weakens, or bounds the hypothesis);\n- **branch_ref** — the git branch\u002Fcommit\u002Fworktree path holding the artifact.\n\nMark a node `running` before dispatch (`tree.py set-status --node n2 --status running`) so the Observe projection stays accurate.\n\n### 5. Backpropagate\nWhen an executor returns, write its report into the node, then **abstract the lesson upward**:\n\n```bash\npython \"$ARBOR_TREE\" set-evidence --node n2 --dev-score 70.0 \\\n  --result \"K=5 dossier aggregation recovers answers in minority rollouts\" \\\n  --insight \"Correct answers often appear in a minority of rollouts; aggregation beats majority vote\" \\\n  --branch-ref \"wt\u002Fn2\"\n\npython \"$ARBOR_TREE\" propagate --node n2 \\\n  --insight \"Candidate coverage, not verification, limits this direction\" --to-root\n```\n\nThis is the step that makes the tree more than a log. A leaf-level observation (\"data-interface mismatch\") should become a direction-level constraint and, if it generalizes, a global prior that shapes future ideation. **Insight propagation was critical in the reported ablation** — in the paper's MLE-Bench Lite ablation with Claude Opus 4.6, a tree *without* insight feedback scored even lower than a flat experiment queue with no tree at all (54.5% vs. 63.6% any-medal, against 81.8% for the full system). Hierarchy alone isn't enough: the semantic memory is what matters. So spend real thought on the abstraction; don't just copy the leaf insight upward verbatim.\n\n### 6. Decide\nDecide what to do with the new evidence: keep expanding a direction, prune a falsified subtree, or attempt to merge a candidate.\n\n- **Prune** dead ends, recording *why* — the reason becomes a negative constraint:\n  ```bash\n  python \"$ARBOR_TREE\" prune --node n3 --reason \"search-augmented judge overfits dev questions; no test transfer\"\n  ```\n- **Merge gate** — promote a candidate to the new best **only if it improves on `E_test`**. Run the test evaluator on the exact candidate commit in a *fresh* worktree to prevent uncommitted development artifacts from affecting the result, then:\n  ```bash\n  python \"$ARBOR_TREE\" merge --node n2 --test-score 67.67 --branch-ref \"wt\u002Fn2\"\n  ```\n  A passing command changes bookkeeping only; it does not verify evaluator output or the supplied artifact ref. Preserve the verified candidate on a named branch, and perform any authorized Git promotion separately; re-evaluate the resulting commit if integrating it changes the artifact. The helper compares strict improvement, without a noise model or significance threshold, so agree on repetitions and the acceptance rule before search.\n\n  If the gate rejects it, that's informative: a high-dev \u002F low-test candidate is evidence the direction may be exploiting the dev signal rather than producing a transferable improvement. Record that lesson; don't quietly promote it anyway.\n\nRepeat until the budget is spent, the frontier is exhausted, or progress has clearly stalled.\n\n## Finishing the run\n\nWhen you stop, produce a short report (see `references\u002Freport-template.md`) covering:\n- the final best artifact, its test score, and its delta over `M_0`;\n- the tree (`python \"$ARBOR_TREE\" status`) as the audit trail of what was tried;\n- the main hypothesis shifts — how task understanding deepened across the run (early nodes test broad mechanisms; later nodes find their limits; ancestor insights compress these into the constraints behind the final design);\n- merged vs. explored: many nodes improve dev, far fewer pass the test gate — report that gap honestly rather than overstating dev wins.\n\nAlways leave `M_best` as a real, runnable artifact on a named branch, and tell the user how to check it out.\n\n## Principles that make this work (not rote rules)\n\nThese come from the paper's analysis; understanding *why* matters more than following them mechanically.\n\n- **The tree is the memory; conversation is not.** Over a long horizon your context gets compressed. Re-Observe each cycle so decisions rest on durable evidence, not a lossy summary.\n- **Structured search, not more sampling.** Arbor's gains come from how the budget is *organized* — maintaining competing hypotheses, comparing siblings, carrying lessons forward — not from spending more tokens. Don't fan out aimlessly; each experiment should be conditioned on what the tree already knows.\n- **Dev guides, test admits.** Use dev feedback freely to steer exploration, but never let a dev win into the final artifact without test confirmation. The dev\u002Ftest disagreement is itself a signal worth reading.\n- **Executors are hypothesis-bound.** Local engineering flexibility (edit, debug, rerun) is fine; silently changing the hypothesis to chase a better number is not — it destroys the meaning of the evidence.\n- **Failures are constraints, not noise.** A falsified hypothesis tells you what the solution must avoid. Pruned-with-a-reason is more valuable than pruned-and-forgotten.\n\n## Verification scope\n\nThe bundled helper is tested with synthetic score\u002Fbranch records; no paper benchmarks or paid autonomous runs were reproduced. The upstream package and CLI were reviewed against `arbor-agent 0.1.4` and source commit `7cdaf1fa6d779b3d5e340052357bf3fe55dfed93`. See the upstream reference for exact current command\u002Fconfiguration boundaries.\n\n## Reference files\n\n- `references\u002Fhtr-methodology.md` — deeper explanation of HTR, the node structure, the six steps, and the paper's empirical lessons (ablations, transfer, cost). Read when you want the rationale behind a design choice.\n- `references\u002Fexecutor-brief.md` — the template for the brief you hand each executor subagent.\n- `references\u002Freport-template.md` — the final-report structure.\n- `references\u002Farbor-upstream.md` — how to install and run the standalone `arbor` CLI from RUC-NLPIR\u002FArbor instead of orchestrating it natively, and when to prefer each.\n\n## Citing Scientific Agent Skills\n\nThis skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a\nmanuscript, report, presentation, or code release, add the paper to the references or\nsoftware section and tell the user you did so:\n\n> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent\n> Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.\n> https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2609.00065\n\nAlways cite the current version. The DOI and https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 resolve to the\nlatest arXiv version, so never append a version suffix such as `v1`. When network access is\navailable, fetch https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 (or\nhttp:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2609.00065) before writing the reference and take\nthe author list, year, and version from that record. If the record lists a journal reference\nor publisher DOI, cite the published version instead.\n","# Arbor — Autonomous Optimization via Hypothesis Tree Refinement\n\n## Overview\n\nThis skill runs an **Autonomous Optimization (AO)** loop: starting from an existing artifact and a measurable objective, improve it through many rounds of experiment and evaluation — without step-by-step human supervision, while checking for overfitting to the development signal. It's the right tool when the bottleneck isn't writing one good change, but *organizing dozens of trials* so that lessons accumulate instead of evaporating.\n\nIt implements **Hypothesis Tree Refinement (HTR)** from *Arbor* (Jin et al., 2026). The key idea: keep the research state in a persistent **hypothesis tree** rather than in conversation history. Each node binds a hypothesis, the distilled insight it produced, and a pointer to the artifact version that realizes it. You play the long-lived **coordinator** that owns this tree and decides where to search; short-lived **executor** subagents test one hypothesis each in isolated git worktrees and report back. A **held-out merge gate** admits a change only when it improves on a *test* evaluator executors do not optimize against. This is what turns trial-and-error into cumulative, auditable research.\n\nUse the `scripts\u002Ftree.py` state manager for all the bookkeeping (creating nodes, writing evidence, propagating insights, pruning, the merge gate, the Observe projection). It records scores and decisions; it does **not** run evaluators, create worktrees, verify Git refs, or merge Git branches. Only the coordinator writes shared state, serially; executors return evidence. The helper has no multi-writer locking. Its JSON schema is separate from upstream Arbor checkpoints.\n\n## When to use this skill\n\nReach for Arbor when the task is **iterative improvement of a concrete artifact under an evaluator**:\n- Model training: optimizer\u002Farchitecture\u002Frecipe changes to lower loss or hit a target in fewer steps.\n- Harness\u002Fagent engineering: raising pass rate or accuracy of an agent loop, search harness, or tool-use scaffold.\n- Data synthesis: improving a generation\u002Ffiltering pipeline judged by downstream model behavior.\n- Benchmark optimization: MLE-bench \u002F Kaggle-style \"improve the submission\" tasks.\n- Prompt\u002Fsystem optimization where you can score outputs automatically.\n\nThe distinguishing signals: there's an **artifact you can modify**, an **objective**, a way to **score** candidates, and you expect to run **many experiments**. If the user only wants a single fix or a one-shot answer, this is overkill — just do the work directly. If they want open-ended ideation with no evaluator, use `hypothesis-generation` or `scientific-brainstorming` instead.\n\n## The AO setup — pin this down first\n\nBefore any experiments, establish the task tuple `(M_0, O, E_dev, E_test)`. Record the resolved setup, using the user's existing instructions; clarify only missing decisions:\n\n- **M_0 — initial material**: the artifact to improve (a repo, a script, a config, a prompt). Make sure it's under git and currently runs.\n- **O — objective**: the natural-language goal and the metric *direction* (maximize accuracy? minimize loss\u002Fsteps?).\n- **E_dev — development evaluator**: a command you can run freely during search to score a candidate. Fast, repeatable.\n- **E_test — held-out test evaluator**: a *separate* evaluation protocol (held-out examples or predeclared independent seeds) used only at the merge gate. It must not be used as a search oracle — that's the whole point.\n\nFreeze the evaluator, dataset split, and metric before search, and record their\nversions with each score. Repeated merge decisions on the same held-out set can\nstill adapt the search to that set; a fresh worktree prevents file contamination,\nnot statistical leakage. Keep a final untouched evaluation set for the final claim,\nor disclose that the reported result was selected using repeated gate feedback.\n\nIf the user hasn't given you a clean dev\u002Ftest split, **construct one and say so**. The dev\u002Ftest separation is the mechanism that catches overfitting: a candidate that wins on dev but not on test isn't a success, it's a warning that you're exploiting the feedback signal. A larger run on the same examples is not an independent holdout. If no defensible holdout exists, label results as development-only.\n\nSet `ARBOR_TREE` to the absolute path of this skill's `scripts\u002Ftree.py`, then work from the experiment project directory. The following commands illustrate one run; evaluator commands, scores and refs must be replaced with actual measured evidence. Initialize the run:\n\n```bash\npython \"$ARBOR_TREE\" init \\\n  --objective \"Improve BrowseComp answer accuracy on the search harness\" \\\n  --dev-eval \"python eval.py --split dev --n 50\" \\\n  --test-eval \"python eval.py --split test --n 300\" \\\n  --material \".\" --metric-direction max --branching 3 --max-depth 2 --budget 12\n```\n\nEvaluate `M_0` on the fixed gate protocol before search and record its commit and score:\n\n```bash\npython \"$ARBOR_TREE\" baseline --test-score 45.33 --branch-ref \"baseline-commit\"\n```\n\nThe coordinator is responsible for freezing protocols and evaluating the baseline; these are procedural steps, not automated checks. The baseline command only records evidence supplied by the coordinator, once. `merge` refuses an unscored baseline and non-finite scores. Existing runs with no incumbent need this step; start a new run if the baseline\u002Fevaluator changes. Keep raw evaluator output, seeds, split IDs and evaluator version alongside `.arbor\u002F`.\n\n`--branching` is how many sibling hypotheses you propose per parent; `--max-depth 2` keeps directions at depth 1 and concrete interventions at depth 2 (the paper's default); `--budget` is the number of coordinator cycles. Start small (10–20 cycles). These helper settings are advisory: branching is recorded, depth overruns warn, and the cycle counter can exceed the budget. The coordinator must enforce the agreed stopping limits.\n\n## The coordinator loop\n\nYou run repeated cycles of six steps. This is the heart of HTR; do not collapse it into ad-hoc editing. Run `python \"$ARBOR_TREE\" cycle` once per cycle to track the budget.\n\n### 1. Observe\nBegin every cycle by re-grounding in the tree, not in your memory of the conversation:\n\n```bash\npython \"$ARBOR_TREE\" observe\n```\n\nThis prints the objective, global insights, the active frontier (selectable hypotheses), executed nodes with their evidence, pruned lessons (negative constraints), and the current best artifact. Treating the tree as the source of truth is what keeps you coherent over a long run, after context compression has thrown away the details.\n\n### 2. Ideate\nPick a promising parent and propose a few child hypotheses under it. **Condition on the tree's evidence** — this is the difference between Arbor and random search:\n- Validated insights are assumptions you can build on.\n- Pruned nodes are dead ends to avoid.\n- A \"half-right\" result is a *starting point for a sharper hypothesis*, not a reason to abandon the direction.\n\nEach hypothesis should be a **falsifiable claim about how changing the artifact will move the metric**, not a vague intention. Depth-1 nodes are broad directions (\"the search harness loses correct answers it already retrieved\"); depth-2 nodes are concrete, executable interventions (\"run K=5 independent rollouts and aggregate by evidence dossier instead of majority vote\").\n\n```bash\npython \"$ARBOR_TREE\" add-node --parent n0 --hypothesis \"Verification, not retrieval, is the bottleneck: candidates are found but discarded\"\npython \"$ARBOR_TREE\" add-node --parent n1 --hypothesis \"Aggregate independent rollouts by evidence dossier to recover minority answers\"\npython \"$ARBOR_TREE\" add-node --parent n1 --hypothesis \"Search-augment the judge to verify discarded candidates\"\n```\n\n### 3. Select\nChoose which pending leaves to run next. **Selection is not pure score-maximization** — pick a hypothesis because it has strong prior evidence, because it would resolve an ambiguity its siblings exposed, or because its failure would clarify an important assumption. Frontier control under delayed feedback rewards informative experiments, not just promising ones.\n\n### 4. Dispatch\nRun each selected hypothesis as an **executor subagent in an isolated worktree** (use the host's supported isolation facility, or create distinct worktrees with `git worktree add`). Isolation matters: parallel experiments must not clobber each other or the current best, and exploratory changes stay quarantined until they pass the merge gate.\n\nDispatch siblings **in parallel** (through the host's available subagent tools) when they're independent — comparative evidence within one direction is exactly what makes later pruning and abstraction possible.\n\nGive each executor a tight, **hypothesis-bound** brief. See `references\u002Fexecutor-brief.md` for the full template. The contract that makes HTR work: **the executor may not change the hypothesis when the metric stalls.** It repairs its own code and reruns, but `h_n` is fixed — otherwise the returned score is no longer evidence about the assigned node and the tree's semantics break. The executor returns exactly four things:\n- **dev_score** — a finite dev evaluator result (for selection), or null for an execution failure;\n- **result** — a factual summary of what happened;\n- **insight** — the distilled, reusable lesson (*why* the result supports, weakens, or bounds the hypothesis);\n- **branch_ref** — the git branch\u002Fcommit\u002Fworktree path holding the artifact.\n\nMark a node `running` before dispatch (`tree.py set-status --node n2 --status running`) so the Observe projection stays accurate.\n\n### 5. Backpropagate\nWhen an executor returns, write its report into the node, then **abstract the lesson upward**:\n\n```bash\npython \"$ARBOR_TREE\" set-evidence --node n2 --dev-score 70.0 \\\n  --result \"K=5 dossier aggregation recovers answers in minority rollouts\" \\\n  --insight \"Correct answers often appear in a minority of rollouts; aggregation beats majority vote\" \\\n  --branch-ref \"wt\u002Fn2\"\n\npython \"$ARBOR_TREE\" propagate --node n2 \\\n  --insight \"Candidate coverage, not verification, limits this direction\" --to-root\n```\n\nThis is the step that makes the tree more than a log. A leaf-level observation (\"data-interface mismatch\") should become a direction-level constraint and, if it generalizes, a global prior that shapes future ideation. **Insight propagation was critical in the reported ablation** — in the paper's MLE-Bench Lite ablation with Claude Opus 4.6, a tree *without* insight feedback scored even lower than a flat experiment queue with no tree at all (54.5% vs. 63.6% any-medal, against 81.8% for the full system). Hierarchy alone isn't enough: the semantic memory is what matters. So spend real thought on the abstraction; don't just copy the leaf insight upward verbatim.\n\n### 6. Decide\nDecide what to do with the new evidence: keep expanding a direction, prune a falsified subtree, or attempt to merge a candidate.\n\n- **Prune** dead ends, recording *why* — the reason becomes a negative constraint:\n  ```bash\n  python \"$ARBOR_TREE\" prune --node n3 --reason \"search-augmented judge overfits dev questions; no test transfer\"\n  ```\n- **Merge gate** — promote a candidate to the new best **only if it improves on `E_test`**. Run the test evaluator on the exact candidate commit in a *fresh* worktree to prevent uncommitted development artifacts from affecting the result, then:\n  ```bash\n  python \"$ARBOR_TREE\" merge --node n2 --test-score 67.67 --branch-ref \"wt\u002Fn2\"\n  ```\n  A passing command changes bookkeeping only; it does not verify evaluator output or the supplied artifact ref. Preserve the verified candidate on a named branch, and perform any authorized Git promotion separately; re-evaluate the resulting commit if integrating it changes the artifact. The helper compares strict improvement, without a noise model or significance threshold, so agree on repetitions and the acceptance rule before search.\n\n  If the gate rejects it, that's informative: a high-dev \u002F low-test candidate is evidence the direction may be exploiting the dev signal rather than producing a transferable improvement. Record that lesson; don't quietly promote it anyway.\n\nRepeat until the budget is spent, the frontier is exhausted, or progress has clearly stalled.\n\n## Finishing the run\n\nWhen you stop, produce a short report (see `references\u002Freport-template.md`) covering:\n- the final best artifact, its test score, and its delta over `M_0`;\n- the tree (`python \"$ARBOR_TREE\" status`) as the audit trail of what was tried;\n- the main hypothesis shifts — how task understanding deepened across the run (early nodes test broad mechanisms; later nodes find their limits; ancestor insights compress these into the constraints behind the final design);\n- merged vs. explored: many nodes improve dev, far fewer pass the test gate — report that gap honestly rather than overstating dev wins.\n\nAlways leave `M_best` as a real, runnable artifact on a named branch, and tell the user how to check it out.\n\n## Principles that make this work (not rote rules)\n\nThese come from the paper's analysis; understanding *why* matters more than following them mechanically.\n\n- **The tree is the memory; conversation is not.** Over a long horizon your context gets compressed. Re-Observe each cycle so decisions rest on durable evidence, not a lossy summary.\n- **Structured search, not more sampling.** Arbor's gains come from how the budget is *organized* — maintaining competing hypotheses, comparing siblings, carrying lessons forward — not from spending more tokens. Don't fan out aimlessly; each experiment should be conditioned on what the tree already knows.\n- **Dev guides, test admits.** Use dev feedback freely to steer exploration, but never let a dev win into the final artifact without test confirmation. The dev\u002Ftest disagreement is itself a signal worth reading.\n- **Executors are hypothesis-bound.** Local engineering flexibility (edit, debug, rerun) is fine; silently changing the hypothesis to chase a better number is not — it destroys the meaning of the evidence.\n- **Failures are constraints, not noise.** A falsified hypothesis tells you what the solution must avoid. Pruned-with-a-reason is more valuable than pruned-and-forgotten.\n\n## Verification scope\n\nThe bundled helper is tested with synthetic score\u002Fbranch records; no paper benchmarks or paid autonomous runs were reproduced. The upstream package and CLI were reviewed against `arbor-agent 0.1.4` and source commit `7cdaf1fa6d779b3d5e340052357bf3fe55dfed93`. See the upstream reference for exact current command\u002Fconfiguration boundaries.\n\n## Reference files\n\n- `references\u002Fhtr-methodology.md` — deeper explanation of HTR, the node structure, the six steps, and the paper's empirical lessons (ablations, transfer, cost). Read when you want the rationale behind a design choice.\n- `references\u002Fexecutor-brief.md` — the template for the brief you hand each executor subagent.\n- `references\u002Freport-template.md` — the final-report structure.\n- `references\u002Farbor-upstream.md` — how to install and run the standalone `arbor` CLI from RUC-NLPIR\u002FArbor instead of orchestrating it natively, and when to prefer each.\n\n## Citing Scientific Agent Skills\n\nThis skill is part of Scientific Agent Skills by K-Dense. If it materially contributed to a\nmanuscript, report, presentation, or code release, add the paper to the references or\nsoftware section and tell the user you did so:\n\n> Kassis, T., Agarwal, V., He, Y., Patel, D., & Brueckner, A. M. (2026). Scientific Agent\n> Skills: A Library of Procedural Knowledge for Research Agents. arXiv:2609.00065.\n> https:\u002F\u002Fdoi.org\u002F10.48550\u002FarXiv.2609.00065\n\nAlways cite the current version. The DOI and https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 resolve to the\nlatest arXiv version, so never append a version suffix such as `v1`. When network access is\navailable, fetch https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.00065 (or\nhttp:\u002F\u002Fexport.arxiv.org\u002Fapi\u002Fquery?id_list=2609.00065) before writing the reference and take\nthe author list, year, and version from that record. If the record lists a journal reference\nor publisher DOI, cite the published version instead.\n",{"name":5,"license":24,"metadata":25,"description":7,"allowed-tools":30,"compatibility":31},"MIT license",{"version":26,"skill-author":27,"last-reviewed":28,"upstream-version":29},"1.6","K-Dense Inc.","2026-09-30","arbor-agent 0.1.4","Read Write Edit Bash Agent","Requires Python 3.10+ for the bundled state manager and Git for experiment worktrees. The optional arbor-agent CLI needs a separate installation; autonomous model calls need provider credentials and network access.","master","fd76f882a04e445e899d5cfb2732f2105ea054ee","skills\u002Fawesome-skills\u002Farbor",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill arbor",{"tool":48,"command":49},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill arbor",{"tool":51,"command":52},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill arbor","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fawesome-skills\u002Farbor\u002FSKILL.md",true,[],[57,65,72,79,86,93],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":64},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":64},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":64},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":64},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":64},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":64},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]