Results for “autoresearch”
19 skills
georgeqle autoresearch-prep
Scaffolds a program.md research program for autoresearch by auto-detecting codebase signals and interviewing for missing details.
1 · bundle
sinhoneyy setup
Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator. Use when the user runs /ar:setup or asks to start optimizing a file with the autoresearch loop.
11
georgeqle autoresearch
Autonomous experiment loop — iteratively mutate code, measure a metric, keep only improvements (hill-climbing ratchet)
1 · bundle
levalencia setup
Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.
3
jarbitechture setup
Set up a new autoresearch experiment interactively. Collects domain, target file, eval command, metric, direction, and evaluator.
0 · bundle
More results
github autoresearch
Guides users through defining goals, metrics, and scope, then runs an autonomous loop of code changes, testing, measuring, and keeping or discarding results for any programming task with a measurable outcome.
36.2k
sinhoneyy run
Run a single experiment iteration. Edit the target file, evaluate, keep or discard. Use when the user runs /ar:run or asks for one manual autoresearch iteration.
11
michaelschecht autoresearch
Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.
0
affaan-m search-first
Research existing tools, libraries, and patterns before writing custom code by invoking a researcher agent.
226k
azusagasaku search-first
研究优先于编码的工作流程。在编写自定义代码之前，搜索现有的工具、库和模式。调用研究员代理。
0
micsapp rethink
Challenge system assumptions against accumulated evidence. Triages observations and tensions, detects patterns, generates proposals. The scientific method applied to knowledge systems. Triggers on "/rethink", "review observations", "challenge assumptions", "what have I learned".
3 · bundle
sinhoneyy resume
Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating. Use when the user runs /ar:resume or asks to pick up a previously started autoresearch experiment.
11
lambenthan refine
通用多轮迭代改进：对任意研究制品反复调用 /review → 解析反馈 → 修复 → 更新 wiki，直到达标
77
mhassan0000 search-first
Guides the agent to research existing tools, libraries, and patterns before writing custom code, using parallel searches across package registries, MCP servers, skills, and GitHub, then evaluating and deciding to adopt, extend, or build.
1
sakamoto-family-smile search-first
Guides a research-before-coding workflow, searching existing tools, libraries, and patterns before writing custom code, with decision matrices and integration with agent workflows.
0
joshuashepherd agent-rag
Build or modify a RAG retrieval pipeline with vector store search, corpus routing, citation rendering, and book fidelity enforcement.
1
jarbitechture reason
Understand through recursive decomposition and modular reconstruction of simple operations to reproduce emergent complexity. Use this skill whenever reasoning is required. Framework for [[#parse|parsing]], [[#branch|branching]], [[#reduce|reducing]], [[#ground|grounding]] and [[#emit|emitting]]. Employs metacognitive reasoning epistemology, leveraging first principles through recursive decomposition[^1]. Self-referential and scale-invariant.
0
nous-hermeshub run
Run a single experiment iteration. Edit the target file, evaluate, keep or discard. Use when the user runs /ar:run or asks for one manual autoresearch iteration.
1
sinhoneyy loop
Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly). Uses CronCreate for scheduling. Use when the user runs /ar:loop or asks to run an autoresearch experiment continuously on a schedule.
11