exploratory-autoresearch
Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move.
npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Exploratory Autoresearch Loop This loop runs hot. Like the standard `ml-autoresearch`, every experiment is followed by a diagnostic analysis pass. **Unlike** it, the *type* of change at each iteration is set by a **temperature scheduler**, not the agent's intuition: it forces wide, diverse swings early (full rewrites, fundamentally different architectures and training regimes), then drops into an adaptive phase that chooses between **swing** (a fresh wild approach), **merge** (combine two registered approaches), or **exploit** (a focused tweak of the best). A **stagnation guard** bans exploit once it has run `<stagnation_limit>` times in a row, forcing a pivot back to swing or merge so the loop never gets stuck hill-climbing. The feedback signal is `<metric>` read from the run log; an `approaches.md` registry and a `move_type` per iteration are what make the scheduler work. You are the researcher. Do not pause to ask for permission once the loop is running. ## When to use Use for an open-ended ML campaign where you want forced breadth before refinement — the scheduler guarantees you sample several distinct families before converging, and the stagnation guard prevents endless smal
- When to use
- Setup
- Initialise the sandbox
- The loop (LOOP FOREVER — until interrupted)
- The scheduler (step 2 — this is the loop's identity)
- Counter update (step 11)
- The three moves (step 3)
- Analysing (step 7 — MANDATORY; produces real artifacts)
- The registry (step 8 — approaches.md, swing and merge only)
- Ledger
- Constraints
- Stops
What does the exploratory-autoresearch skill do?
Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move.
How do I install it?
Run `npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From gaasher/Agent-Loop-Skills, a repository with 146 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.