From the author
Autonomously improve a real artifact (code, training recipe, agent harness, data pipeline, prompt) against an objective and an evaluator, using Hypothesis Tree Refinement (HTR) from the Arbor paper. Use this whenever someone wants to iteratively optimize something over many experiments without overfitting — e.g. "get my model's eval score up", "improve this agent/harness", "tune this pipeline", "beat the baseline on this benchmark", "run a search over approaches and keep the best", "do an MLE-bench / Kaggle-style optimization", or any long-horizon "make this artifact better and don't just memorize the dev set" task. Trigger it even when the user doesn't say "Arbor" or "hypothesis tree" but describes repeated experiment-and-evaluate loops, branching exploration of competing ideas, or worries about a dev/test gap. Runs Claude itself as the coordinator with subagent executors in isolated git worktrees; for the standalone `arbor` CLI tool see references/arbor-upstream.md.
Install
npx skills add KalarisLabs/research-agent-skills --skill arbor -a claude-code
Installs to .claude/skills/arbor/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
Want your agent to suggest skills while you type? See how to use skills from your IDE.
Safety checks on SKILL.md
- Ships scripts we have not reviewedLow
Why 76
aiqbench computes the trust score from public signals. It is not a security audit, so read a skill before you install it.
Similar skills
Closest to this one by what they do and when they are used.
- reflectsneg55/agent-starterPer-project self-improvement - reads the .harness ledger and feedback memories, then proposes gated rule/threshold/ADR changes so the project stops repeating mistakes. Run periodically.Other★ 74
- meta-harness001TMF/harness-forgeRun a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto frontier of quality vs cost — using native Agent / Workflow / loop tools instead of a standalone Python harness. Use this whenever the user wants to optimize, evolve, tune, distill, or search over a harness, scaffold, prompt system, memory or retrieval policy, context-assembly code, or summarizer while keeping the model fixed; whenever they mention Meta-Harness, harness optimization, scaffold evolution, automatic prompt/memory optimization, an evolutionary or Pareto search over candidate implementations, or "make the harness/agent better without retraining"; and whenever the gain must come from the code AROUND the model rather than the model weights. Reproduces the Meta-Harness paper's method nativScience★ 81
- reflect-and-improveShaishavMaisuria/research-paper-lifecycle-skillsThe reflection agent. Use it right after another skill produces an artifact such as a rewrite from polish-prose, a rebuttal, an abstract, a preflight fix, or a tailored draft to critique that output against the stated goal, the paper's .paper-memory/profile.yml, the relevant rubric, and past .paper-memory/lessons.md, then decide whether it actually improved. Trigger words include reflect, self-critique, did this get better, did my edit help, regression check, review my own output, iterate, refine, second pass, sanity-check the rewrite, and "is the new version actually better". Runs a bounded self-refine / Reflexion loop, guards against regressions, and appends durable, deduplicated, dated lessons to .paper-memory/lessons.md via a stdlib script so the toolkit gets sharper each paper. Reflection adds cost; it only pays off when there is a measurable target.Science★ 55
- autoresearchgithub/awesome-copilotAutonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.Testing★ 40.5K
- hk-refinedeepklarity/harness-kitIteratively improve any output by running a structured observe-hypothesize-change-rerun loop. Uses an organized scratch directory to prevent context blowup — the conversation stays thin while iterations accumulate on disk. Use when an output (reflection, plan, prompt, pipeline result) isn't good enough and needs systematic refinement. Triggers on: 'close the loop', 'this output isn't good enough', 'iterate on this', 'refine this output', 'improve this reflection', or /hk-refine.Planning★ 102
- explore-codelllllllama/RigorPilot-SkillsRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated branch or worktree to transplant modules, adapt a backbone, add LoRA or adapter layers, replace a head, or stitch together meaningful low-risk migration ideas with rollback-aware records in `explore_outputs/`. Do not use for end-to-end exploration orchestration on top of `current_research`, trusted baseline reproduction, conservative debugging, environment setup, verified contribution claims, or default repository analysis.Engineering★ 484
Ratings & reviews
—
no reviews
Tried this skill? Rate it to help others. Sign in
Discussion
Join the discussion. Sign in