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.

Langue du texte source : anglais

baseline

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

Langue du texte source : anglais

decision

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

Langue du texte source : anglais

experiment-execution

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

finalize

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

Langue du texte source : anglais

idea

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

paper-reliability-verification

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

Langue du texte source : anglais

quest-handoffs

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

review

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

Langue du texte source : anglais

scout

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

Langue du texte source : anglais

write

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

Langue du texte source : anglais

writing-plans

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

baseline

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

Langue du texte source : anglais

decision

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

Langue du texte source : anglais

experiment-execution

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

finalize

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

Langue du texte source : anglais

idea

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

quest-handoffs

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

Langue du texte source : anglais

review

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

Langue du texte source : anglais

scout

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

Langue du texte source : anglais

write

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

Langue du texte source : anglais

writing-plans

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

Langue du texte source : anglais

kvasir-agent-manual-init

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

Langue du texte source : anglais

kvasir-agent

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

paper-reliability-verification

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

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais

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.

Langue du texte source : anglais