Obsidian Experiment Log
SkillDocs & knowledgeUse this skill when the user discusses experiment design, ablations, training runs, evaluation, baselines, metrics, failures, or result interpretation that should be logged into Obsidian experiment and result notes.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Obsidian Experiment Log skill
What this skill tells your AI
The instructions your AI receives, as published by brycewang-stanford/auto-empirical-research-skills in skills/33-Galaxy-Dawn-claude-scholar/skills/obsidian-experiment-log/SKILL.md and read by ahel’s review.
Use this skill whenever project work changes the experimental state.
Role in the workflow
This is a supporting skill under obsidian-project-memory.
It should help maintain canonical experiment and result notes, not create note sprawl.
Default outputs
- the relevant canonical note in
Experiments/ - the relevant canonical note in
Results/, if a durable finding exists - links from today's
Daily/note - relevant hub or plan references only when project state materially changes
Main rules
- Prefer updating an existing experiment note over creating a sibling note for the same experiment line.
- Prefer updating an existing result note over creating a parallel result page for the same durable finding.
- Raw logs, metric dumps, and temporary analysis fragments should usually stay in
Daily/until they are interpreted. - A result note should exist only when the outcome is stable enough to reference later.
Minimum experiment sections
- Goal / hypothesis
- Code or config entrypoint
- Dataset / split
- Metrics
- Status (
planned,running,done,failed) - Findings / notes
- Next step
Minimum result sections
- Linked experiment
- Main observation
- Key numbers
- Evidence
- Interpretation
- Decision: keep / iterate / discard
Linking rule
Link experiments and results directly to each other, and link both back to 00-Hub.md, 01-Plan.md, or Daily/ only when those references improve the main working surface.
Research path handoff
Treat experiment notes as the bridge between Papers/ and Results/:
- paper-derived hypotheses, baselines, and ablations should land here,
- stable findings should be promoted from here into
Results/, - when a result becomes claim-worthy, update
Writing/rather than leaving the chain unfinished.
Signals
- GitHub stars
- 4k
- Forks
- 531
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
obsidian-experiment-log- Source
- github.com/brycewang-stanford/auto-empirical-research-skills
github.com/brycewang-stanford/auto-empirical-research-skills
Related picks
Skill · agricidaniel
The pick for Markdownmarkdown-formatter
Skill · nvidia
The pick for Markdownhandoff
Skill · mattpocock
More in Docs & knowledgecanvas-design
Skill · anthropics
More in Docs & knowledgedoc-coauthoring
Skill · anthropics
More in Docs & knowledgewriting-for-agents
Skill · mattpocock
More in Docs & knowledge