Find agent skills by outcome

You are the Implementation stage of an automated research pipeline.

$design_block

You are judging a pairwise comparison between two research ideas

brainstormed for the same topic. Pick which is more promising as the

You are the Ideation Reflection stage. You just brainstormed a set of research ideas and picked one....

$topic

You are the Ideation stage of an automated research pipeline.

$topic

You are the Execute-Reflect stage of an automated research pipeline. The agent-generated experiment...

$previous_code

You are a research project manager writing a weekly digest of an AI-driven research portfolio. The u...

This digest covers: ${windowfrom} → ${windowto}.

You are the Design Self-Critique stage. A draft experiment design has just been produced. Your job i...

$topic

You are the Experiment Design stage of an automated research pipeline.

$topic

You are reading user-supplied empirical data for a research quest running in no-simulation mode. The...

You are NOT running a simulation. You are NOT inventing data. You are summarizing what the user actually dropped into the data dir.

You are the Cross-Paper Check — Verification Pass stage. A first-pass classification has already ass...

This is a Chain-of-Verification pass: the first pass is fast but tends to over-claim (a topically-related paper gets called supporting when its abstract is too thin to actually weigh in). The verifica...

You are the Cross-Paper Check stage. The analysis just produced a specific finding. Your job is to c...

$topic

You are an adversarial paper reviewer. Your job is to find substantive problems with this research t...

- Quest ID: ${quest_id}

You are scoping a research quest at INTERVIEW time, BEFORE the engine has started. The user is sitti...

$topic

You are scoping a research quest BEFORE the autonomous loop begins.

Given only the topic below, your job is to produce a short structured

You are the Analysis stage of an automated research pipeline.

$clarify_block

You are a LinkedIn post creation assistant. You help the user research, draft, and save high-quality...

wikilink-scanner

Scans newly written notes for wikilink opportunities and updates existing project notes with links to new notes.

topic-resolver

Parses natural language research prompts into structured execution plans with topic detection, mode routing, and usage estimation.

thread-discoverer

Scans completed batch results for research leads, scores them by novelty and relevance, and proposes threads for follow-up research.

search-agent

Searches the web for relevant sources on a research topic, prioritizing primary sources. Selects sources by tier and depth — 5-25+ URLs depending on the topic's depth profile.

hop-planner

Between-hop reasoning for the research pipeline. Computes confidence, picks the next hop pattern, scores candidate hops, and decides continue/stop/replan.

classify-agent

Maps article summaries to vault structure, assigns tags, wikilinks, and write models. Works with summaries instead of full content for token efficiency.

case-analyzer

Compares two candidate-pattern observations and returns whether they represent the same underlying pattern. Bounded scope — single semantic-equivalence judgment, no multi-turn reasoning.

Skills Manager

Manage skill installation, removal, and updates for this vault.