#177 by GitHub stars

davebcn87/pi-autoresearch

Autonomous experiment loop extension for pi

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/autoresearch-create/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Instructions only → After Network or broad shell

04b8a50dac7e → 04b8a50dac7e

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → 04b8a50dac7e

No earlier version was observed for comparison.

Compare on GitHub

skills/autoresearch-finalize/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Network or broad shell

04b8a50dac7e → 04b8a50dac7e

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 04b8a50dac7e

No earlier version was observed for comparison.

Compare on GitHub

skills/autoresearch-hooks/SKILL.md

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

04b8a50dac7e → 04b8a50dac7e

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 04b8a50dac7e

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit 04b8a50dac7efe80ffc91648bd00ed9b022e24c2

8.2kGitHub stars
14stars in 7 days
3skills in this repository
3commits in 30 days

Heat

5.1
  • Star growth, last 7 daysAhead of 52% of tracked repositories
  • Star growth, last 24 hoursAhead of 70% of tracked repositories
  • Rank movement, last 7 daysAhead of 58% of tracked repositories
  • Commits, last 30 daysAhead of 64% of tracked repositories
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Aug 2, 2026Nov 6, 20268,220

Individual skills in this repository

How it works

autoresearch-create

When your agent uses it

Set up and run an autonomous experiment loop for any optimization target. Gathers what to optimize, then starts the loop immediately. Use when asked to "run autoresearch", "optimize X in a loop", "set up autoresearch for X", or "start experiments".

What it loads into context

Frontmatter

63 tokens

Always available to the agent

SKILL.md

2,115 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Tools
  2. Session files
  3. Setup
  4. Loop Rules
  5. Ideas Backlog
  6. User Messages During Experiments

Files

  • SKILL.mdcore9,157 bytes
  • SKILL.mdcore9,157 bytes
  • SKILL.mdcore9,157 bytes
  • SKILL.mdcore9,157 bytes
Read SKILL.md

# Autoresearch

Autonomous experiment loop: try ideas, keep what works, discard what doesn't, never stop.

## Tools

- **`init_experiment`** — configure session (name, metric, unit, direction). Call again to re-initialize with a new baseline when the optimization target changes.
- **`run_experiment`** — runs command, times it, captures output.
- **`log_experiment`** — records result. `keep` auto-commits. `discard`/`crash`/`checks_failed` auto-reverts code changes (autoresearch files preserved). Always include secondary `metrics` dict. Dashboard: ctrl+shift+t.

## Session files

All session files live in a single `.auto/` subfolder at the working directory root. This keeps everything in one place — easy to preserve across reverts, gitignore, and clean up.
View the complete source on GitHub

Skills included

  • autoresearch-create
  • autoresearch-finalize
  • autoresearch-hooks

Repository facts

License
MIT
Created
Mar 11, 2026
Last pushed
Oct 7, 2026
Forks
469
Open issues
5
Project activity
Active

Rank over the last 12 weeks

Now #177 · best #148 · down 17 in 30 days

  1. #171 from Oct 28 to Oct 29
  2. #173 on Oct 30
  3. #174 on Oct 31
  4. #175 from Nov 1 to Nov 2
  5. #176 from Nov 3 to Nov 4
  6. #177 since Nov 5
54 earlier periods
  1. #145 on Aug 2
  2. #145 from Aug 7 to Aug 8
  3. #143 on Aug 9
  4. #147 from Aug 10 to Aug 12
  5. #149 on Aug 13
  6. #151 from Aug 14 to Aug 17
  7. #152 from Aug 18 to Aug 19
  8. #151 from Aug 20 to Aug 21
  9. #149 on Aug 22
  10. #150 on Aug 23
  11. #149 from Aug 24 to Aug 29
  12. #148 from Aug 30 to Aug 31
  13. #149 on Sep 1
  14. #148 on Sep 2
  15. #150 on Sep 3
  16. #148 on Sep 4
  17. #150 on Sep 5
  18. #149 on Sep 6
  19. #151 from Sep 7 to Sep 9
  20. #152 on Sep 10
  21. #151 on Sep 11
  22. #154 on Sep 12
  23. #155 on Sep 13
  24. #156 from Sep 14 to Sep 15
  25. #155 on Sep 16
  26. #156 on Sep 17
  27. #158 on Sep 18
  28. #156 on Sep 19
  29. #158 from Sep 20 to Sep 21
  30. #157 on Sep 22
  31. #158 on Sep 23
  32. #157 from Sep 24 to Sep 25
  33. #158 from Sep 26 to Sep 27
  34. #159 on Sep 28
  35. #160 on Sep 29
  36. #158 on Sep 30
  37. #160 from Oct 1 to Oct 2
  38. #158 on Oct 3
  39. #157 on Oct 4
  40. #159 from Oct 5 to Oct 6
  41. #161 on Oct 7
  42. #160 on Oct 8
  43. #161 on Oct 9
  44. #160 on Oct 10
  45. #161 from Oct 11 to Oct 12
  46. #162 from Oct 13 to Oct 14
  47. #161 on Oct 15
  48. #159 on Oct 16
  49. #163 on Oct 17
  50. #165 on Oct 18
  51. #166 on Oct 19
  52. #167 from Oct 21 to Oct 22
  53. #168 from Oct 23 to Oct 24
  54. #170 on Oct 25

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 2, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 10 notes
  • skills/autoresearch-create/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-create/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-create/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-finalize/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-finalize/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-hooks/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-hooks/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-hooks/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-hooks/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/autoresearch-hooks/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 20 signals by file

skills/autoresearch-finalize/finalize.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Dangerous shell operationline 42
    cleanup_data() { if [ -d "${DATA_DIR:-}" ]; then rm -rf "$DATA_DIR"; fi; }
  • Dangerous shell operationline 408
    echo "  rm -r .auto    # session folder (current layout)"
  • Dangerous shell operationline 409
    echo "  rm -f autoresearch.jsonl autoresearch.sh autoresearch.md autoresearch.ideas.md    # legacy flat files, if any"

skills/autoresearch-hooks/examples/README.md

  • Network accessline 19
    | --- | --- | | [`external-search.sh`](before/external-search.sh) | Mine agent notes for a query and fetch external material via your search tool of choice. | | [`qmd-search.sh`](before/qmd-search.sh) | Same shape, but targets a local [`qmd
  • Network accessline 20
    | [`external-search.sh`](before/external-search.sh) | Mine agent notes for a query and fetch external material via your search tool of choice. | | [`qmd-search.sh`](before/qmd-search.sh) | Same shape, but targets a local [`qmd`](https://www
  • Network accessline 21
    | [`qmd-search.sh`](before/qmd-search.sh) | Same shape, but targets a local [`qmd`](https://www.npmjs.com/package/qmd) BM25 / vector / rerank index over your project's markdown. |

skills/autoresearch-hooks/examples/after/auto-tag-winners.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/autoresearch-hooks/examples/after/learnings-journal.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/autoresearch-hooks/examples/after/macos-notify.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/autoresearch-hooks/examples/before/anti-thrash.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/autoresearch-hooks/examples/before/context-rotation.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/autoresearch-hooks/examples/before/external-search.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Network accessline 2
    # Infers a query from the agent's natural notes and fetches external material. # Swap the search-cli call for any tool you have: an MCP client, a CLI over # a documentation index, a curl to a search API, a web-search wrapper.
  • Network accessline 4
    # a documentation index, a curl to a search API, a web-search wrapper.

skills/autoresearch-hooks/examples/before/hypothesis-reflection.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/autoresearch-hooks/examples/before/idea-rotator.sh

  • Executable scriptline 1
    #!/usr/bin/env bash

skills/autoresearch-hooks/examples/before/qmd-search.sh

  • Executable scriptline 1
    #!/usr/bin/env bash
  • Network accessline 6
    # # One-time setup: qmd collection add <path> --name <name> # See https://www.npmjs.com/package/qmd
  • Network accessline 8
    # See https://www.npmjs.com/package/qmd

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 20 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeCompatibleStandard SKILL.md skills/autoresearch-create/SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md skills/autoresearch-create/SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/autoresearch-create/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/autoresearch-create/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/autoresearch-create/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/autoresearch-create/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

davebcn87/pi-autoresearch: #177 on hotskills, 8.2k stars

[![davebcn87/pi-autoresearch on hotskills](https://hotskills.dev/badge/davebcn87-pi-autoresearch.svg)](https://hotskills.dev/skill/davebcn87-pi-autoresearch/)