agentleFS
cybertronaicybertronai/SutroYaro/.claude/skills/sutro-context/SKILL.md

sutro-context

Skill16 starsChanged 6 months agoUnlicenseView on GitHub

Use before any research task, experiment, or PR review. Loads current project state from DISCOVERIES.md, open questions, and recent Telegram discussion.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read these in order. Stop and report if anything is unexpected.

    line 12
  2. Distinctive:

    Read the last 10 messages from priority Telegram topics:

    line 21
  3. Distinctive:

    Check GitHub for open work:

    line 36
  4. Very specific:

    Check research/search_space.yaml for allowed parameter ranges

    line 56
  5. Very specific:

    Check research/questions.yaml for the dependency graph of open questions

    line 57
  6. Very specific:

    Run checks/env_check.py to verify environment

    line 58
  7. Very specific:

    Run checks/baseline_check.py if baselines may differ on your machine

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sutro Research Context

Load this before doing any research work, running experiments, or reviewing PRs.

Step 1: Read core files

Read these in order. Stop and report if anything is unexpected.

  1. CLAUDE.md -- project context, current best methods, constraints
  2. DISCOVERIES.md -- what's proven, what failed, open questions (bottom of file)
  3. AGENT.md -- machine-executable experiment loop (if running autonomous)
  4. LAB.md -- experiment protocol, rules (especially rule #9: metric isolation)

Step 2: Check recent activity

Read the last 10 messages from priority Telegram topics:

import json
for f in ['chat-yad.json', 'chat-yaroslav.json', 'challenge-1-sparse-parity.json']:
    path = f'src/sparse_parity/telegram_sync/{f}'
    try:
        msgs = json.load(open(path))
        print(f'\n=== {f} (last 3) ===')
        for m in msgs[:3]:
            print(f"  [{m['date'][:10]}] {m['sender']}: {m['text'][:150]}")
    except FileNotFoundError:
        print(f'{f} not found -- run: bun run sync_telegram.ts')

Check GitHub for open work:

gh pr list --repo cybertronai/SutroYaro --state open
gh issue list --repo cybertronai/SutroYaro --state open

Step 3: Know the current state

FactValue
Best methodGF(2) Gaussian elimination, 509us, ARD ~500
Best energy proxyDMC (Data Movement Complexity, Ding et al.)
Experiments done33+ (see research/log.jsonl)
Open questionsBottom of DISCOVERIES.md (Q7, Q11-Q13 still open)
Next milestoneEnergy-efficient nanoGPT training ("final exam")
Meeting cadenceMondays 18:00 at South Park Commons

Step 4: Before writing code

  • Check research/search_space.yaml for allowed parameter ranges
  • Check research/questions.yaml for the dependency graph of open questions
  • Run checks/env_check.py to verify environment
  • Run checks/baseline_check.py if baselines may differ on your machine

For contributors using other tools

This context applies regardless of which AI tool you use. The key files are plain markdown and YAML. Read them before starting work. The experiment protocol in LAB.md and AGENT.md defines the loop: hypothesis, code, run, measure, record.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.