메뉴
Run an autonomous research or optimization loop with literature-grounded, verifiable long-term memory. Use for measurable optimization and for ranked research-plan ideation.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Run the continuous experiment loop, including idea tournament, best-first tree expansion, mandatory literature cadence, bold swings, automatic commits, and memory write-back.
Gather literature, extract structured claims, and verify their sources and codebase relevance as one trust-preserving pipeline.
Generate grounded novel hypotheses from contradictions, complementary claims, and cross-domain mechanism transfers using the unified synthesize tool.
Produce the autoresearch report with full idea lineage — paper → claim → hypothesis → patch → metric change → status → memory update. Use to summarize an autoresearch run into an auditable, human-readable report at .autoresearch-vkf/session/report.md.
| name | autoresearch-vkf |
| description | Run an autonomous research or optimization loop with literature-grounded, verifiable long-term memory. Use for measurable optimization and for ranked research-plan ideation. |
Confirm the goal, metric/command, scope, and budget once. Then call init_research.
With the default continuous autonomy, keep working without asking between
iterations. Valid stops are exactly: the iteration budget, the STOP file,
target_value reached, or a blocker requiring user-only action. An empty idea
pool means gather more literature, not stop.
The workspace has a transient .autoresearch-vkf/session/ and durable,
git-committed .autoresearch-vkf/memory/. Trust moves explicitly from candidate
to source-verified and locally tested; never silently promote a claim.
recall_memory before rediscovering prior work.autoresearch-vkf-knowledge to gather, extract, and verify claims.synthesize for contradictions, compositions, and cross-domain transfers.autoresearch-vkf-hypothesis-loop: plan_next_step, implement,
vkf_run_experiment, vkf_log_experiment, repeat.REQUIRED gather directive and [BOLD — mandatory] pick.research_update and continue in the same turn.autoresearch-vkf-research-report.Initialize without command/metric_name. Recall, run 2–4 rounds of
knowledge gathering and synthesize, record promising derived claims, then
call draft_research_plan. The deliverable is session/research_plan.md.
init_research, remember_claim, verify_claim, recall_memory,
plan_next_step, set_research_mode, research_update, synthesize,
draft_research_plan, vkf_run_experiment, vkf_log_experiment,
promote_to_global, export_dashboard, research_status, research_graph,
WebSearch, and WebFetch.
Keep web fetches small, measurement output quiet, and recover after compaction
from session/prompt.md, state.json, experiments.json, and recall_memory.