Skill Autoresearch
Route reusable skill-improvement work into one bounded repo-local ratcheting packet: ratchet elig…
by akillness
The skill
Route reusable skill-improvement work into one bounded repo-local ratcheting packet: ratchet eligibility, benchmark readiness, loop charter freeze, baseline scoring, one-change mutation, support-surface sync, or final keep/revert report. Use when an existing `SKILL.md`, SOP, prompt, or workflow doc may need sharper triggers, clearer instructions, better support files, or cleaner discovery wording and you want a frozen evaluation harness, append-only experiment logs, and explicit keep-or-revert decisions instead of ad hoc rewriting. Also use when you need to prove that no ratchet is justified yet. Not for GPU-bound Karpathy `autoresearch` runs or hosted app-scale eval / observability platforms such as LangSmith, Braintrust, Weave, or Promptfoo.
This skill's licence does not allow redistribution, so the store does not show its text. Read it at the source.
Use this skill
Connect your agent to the Skill Store MCP server and ask for it by ref: akillness/skill-autoresearch-64151908038.
Details
- Publisher
- akillness
- Category
- AI & Agents › Skill & prompt authoring
- Updated
- 2026-10-17
References
More from akillness
- A2A Protocol Agent-to-Agent horizontal messaging — Linux Foundation AAIF 2026 standard.
- Academic Research Full academic research pipeline from discovery to publication — 4 reference pipelines, 27 modes,…
- Agent Benchmarking Map agent capabilities to standard benchmarks (SWE-bench, WebArena, OSWorld, GAIA, TauBench) plus…
- Agent Guardrails Layered agent safety — prompt-injection defense, data exfiltration prevention, tool-misuse blocki…