Skip to content

LeoYeAI/agent-master-skills / skills/arbor

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.

FileKindSize
SKILL.mdskill md16.7 KB
references/arbor-upstream.mdmarkdown5.7 KB
references/executor-brief.mdmarkdown3.1 KB
references/htr-methodology.mdmarkdown10.8 KB
references/report-template.mdmarkdown1.8 KB
scripts/tree.pyscript23.9 KB

references/executor-brief.md

View on GitHub
# Executor brief template

Each executor is a short-lived subagent that tests **one** hypothesis in an
isolated git worktree and returns structured evidence. Use the host's supported
subagent/worktree facility, or create a distinct
worktree with `git worktree add`. Dispatch independent siblings in parallel
when resources permit. Only the coordinator writes the shared tree.

Fill in the bracketed parts. Keep the brief tight: the executor needs the
hypothesis, the context that lets it implement well, and a crisp contract for
what to return — nothing more.

---

```
You are an Arbor executor. Test ONE hypothesis in an isolated git worktree and
return structured evidence. Do not change the hypothesis — your job is to give
the coordinator clean evidence about THIS claim, even if it turns out false.

HYPOTHESIS (h_n):
  [the falsifiable claim, e.g. "Aggregating K=5 independent rollouts by an
   evidence dossier recovers correct answers that majority vote discards."]

CURRENT BEST ARTIFACT (M_best):
  [path or git ref of the current best, e.g. branch `arbor/best` — start from this]

RELEVANT INSIGHTS FROM THE TREE (assume these; build on them, don't re-litigate):
  [ancestor + sibling insights, e.g. "Verification is not the bottleneck;
   candidate coverage is. Search-augmented judging overfits dev questions."]

OBJECTIVE & METRIC:
  [O and direction, e.g. "Maximize BrowseComp answer accuracy."]

DEVELOPMENT EVALUATOR (E_dev) — run this to score your candidate:
  [exact command, e.g. `python eval.py --split dev --n 50`]

WHAT TO DO:
  1. Create/confirm an isolated worktree from M_best so you don't touch other
     experiments or the current best.
  2. Implement the MINIMAL change that realizes the hypothesis. You may edit,
     debug, and rerun freely to get a working implementation — but keep the
     change bound to this hypothesis. If the metric stalls, fix YOUR code; do
     not pivot to a different idea.
  3. Run E_dev and record the score. Use the predeclared repetitions if it is
     noisy. Preserve the exact command,
     evaluator/data versions, seeds and raw output; report execution failure
     without inventing a numeric score.
  4. Commit the artifact on a clearly named branch.

RETURN EXACTLY THIS (your final message IS the data the coordinator reads):
  - dev_score: <finite number from E_dev, or null for execution failure>
  - result:    <1-3 sentences of factual outcome — what the change did>
  - insight:   <the reusable lesson: WHY this result supports / weakens /
               bounds the hypothesis. This is the most valuable output —
               make it a constraint future experiments can use, not a restatement
               of the score.>
  - branch_ref: <git branch/commit/worktree path holding the artifact>

Do NOT run the held-out test evaluator — that is the coordinator's merge gate.
```

---

After the executor returns, the coordinator records it with:

```bash
python "$ARBOR_TREE" set-evidence --node <id> \
  --dev-score <n> --result "..." --insight "..." --branch-ref "<ref>"
```

Omit `--dev-score` when evaluation failed; preserve the failure and log path in
`--result`. Then abstract the lesson upward with `tree.py propagate`.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall