Rycen7822/Kvasir-agent

analysis-campaign

Use when a quest needs one or more follow-up runs such as ablations, robustness checks, error analysis, or failure analysis after a main experiment.

baseline

Use when a quest needs to attach, import, reproduce, repair, verify, compare, or publish a baseline and its metrics.

decision

Use when the quest needs an explicit go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition with reasons and evidence.

experiment-execution

Execute Kvasir-agent quest experiment command documents with durable ka_* logging, manifest validation, and cautious baseline-gate handling.

experiment

Use when a quest is ready for a concrete implementation pass or a main experiment run tied to a selected idea and an accepted baseline.

finalize

Use when the quest is ready to consolidate final claims, limitations, recommendations, summary state, and graph exports before stopping or archiving.

idea

Use when a quest needs concrete hypotheses, limitation analysis, candidate directions, or a selected idea relative to the active baseline.

intake-audit

Use when a quest does not start from a blank state and the agent must first audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials before choosing the next anchor.

optimize

Use when an algorithm-first quest should manage candidate briefs, optimization frontier, branch promotion, or fusion-aware search instead of the paper-oriented default loop.

paper-reliability-verification

Verify paper reliability through the bundled Kvasir-agent verifier workflow before using papers as evidence.

quest-handoffs

Create durable Kvasir-agent quest handoff documents, AGENTS.md files, researcher packages, and verified sync artifacts.

rebuttal

Use when a quest already has a paper, draft, or review package and the task is to map reviewer feedback into experiments, manuscript deltas, and a durable rebuttal / revision response.

review

Run a skeptical evidence-grounded Kvasir-agent review pass for drafts, paper-like reports, claim scope, and follow-up routing.

scout

Use when a quest needs problem framing, literature scouting, dataset or metric clarification, or baseline discovery before deeper work.

write

Use when a quest has enough evidence to draft or refine a paper, report, or research summary without inventing missing support.

writing-plans

Write Kvasir-agent-aware implementation, experiment-roadmap, code-only, and formal-command plans with TDD and durable quest outputs.

analysis-campaign

Use when a quest needs one or more follow-up runs such as ablations, robustness checks, error analysis, or failure analysis after a main experiment.

baseline

Use when a quest needs to attach, import, reproduce, repair, verify, compare, or publish a baseline and its metrics.

decision

Use when the quest needs an explicit go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition with reasons and evidence.

experiment-execution

Execute Kvasir-agent project experiment command documents with durable ka_* logging, manifest validation, and cautious baseline-gate handling.

experiment

Use when a quest is ready for a concrete implementation pass or a main experiment run tied to a selected idea and an accepted baseline.

finalize

Use when the quest is ready to consolidate final claims, limitations, recommendations, summary state, and graph exports before stopping or archiving.

idea

Use when a quest needs concrete hypotheses, limitation analysis, candidate directions, or a selected idea relative to the active baseline.

intake-audit

Use when a quest does not start from a blank state and the agent must first audit, trust-rank, and reconcile existing baselines, results, drafts, or review materials before choosing the next anchor.

optimize

Use when an algorithm-first quest should manage candidate briefs, optimization frontier, branch promotion, or fusion-aware search instead of the paper-oriented default loop.

paper-fetch

Use when a Kvasir-agent project needs project-local paper retrieval, arXiv/OpenReview PDF reading, or official resource verification without clipping into llm-wiki.

quest-handoffs

Create durable Kvasir-agent project handoff documents, AGENTS.md files, researcher packages, and verified sync artifacts.

review

Run a skeptical evidence-grounded Kvasir-agent review pass for drafts, paper-like reports, claim scope, and follow-up routing.

scout

Use when a quest needs problem framing, literature scouting, dataset or metric clarification, or baseline discovery before deeper work.

write

Use when a quest has enough evidence to draft or refine a paper, report, or research summary without inventing missing support.

writing-plans

Write Kvasir-agent-aware implementation, experiment-roadmap, code-only, and formal-command plans with TDD and durable quest outputs.

kvasir-agent-manual-init

Create minimal project state only when the user explicitly supplies this manual and requests initialization.

kvasir-agent

Run reproducible research experiments and inspect project-local evidence with Kvasir-agent.

figure-polish

Use when a quest needs a polished milestone chart, paper-facing figure, appendix figure, or a mandatory render-inspect-revise pass before treating a figure as final.

paper-reliability-verification

Verify paper reliability through the bundled Kvasir-agent verifier workflow before using papers as evidence.

paper-reliability-verifier

Verify scholarly-paper reliability for AI-scientist agents by checking citation counts, venue level, journal level, publication type, and retraction/update status.

openreview-accepted-venue

Use when paper-reliability-verifier needs to verify acceptance and presentation type for OpenReview-hosted venues such as ICLR, TMLR, COLM, or related workshops before local rank lookup.

strict-research

Strict literature research mode for Kvasir-agent projects: broad candidate scouting first, reliability verification, conservative filtering, project-local PDF download, then iterative bibliography reading notes before answering/writing.