Research

> Synthesize accumulated observations into actionable insights when evidence is sufficient.

> Capture observations, friction patterns, and learnings for future synthesis.

Parses error messages, traces execution flow through stack traces, correlates log entries, and applies systematic hypothesis-driven methodology to isolate and resolve bugs.

Designs chaos experiments, creates failure injection frameworks, and facilitates game day exercises for distributed systems with runbooks, experiment manifests, and rollback procedures.

Synthesize performance findings into evidence-backed recommendations and decisions

Coordinate multiple enhancement analyzers in parallel and produce unified report

Audit skill configurations for correctness and freshness

Search Semantic Scholar for academic papers on a given topic

Focused research analysis on a specific topic with sources

Scan and summarize recent academic papers from Semantic Scholar

Capture and catalog new ideas from conversations and research

Track and report on progress toward defined goals

Multi-agent web research with mandatory URL verification, confidence-tagged output, and four depth modes (quick to deep investigation). USE WHEN research, do research, quick research, extensive research, deep investigation, find information, investigate, extract alpha, analyze content, retrieve content, AI trends, enhance content, extract knowledge, web scraping, YouTube extraction, map landscape, competitive analysis, find it, find this, find this product, identify this, what is this, what's...

Curated aphorism collection with CRUD — content-based matching, themed search, thinker research, DB maintenance. Quotes organized by author/theme/context/usage to prevent repetition. Four workflows: FindAphorism, AddAphorism, ResearchThinker, SearchAphorisms. Themes: Stoicism, Wisdom, Truth-seeking, Excellence, Resilience, Curiosity. USE WHEN aphorism, quote, find a quote, research thinker, add aphorism, quote for newsletter, what did X say about, quote bank. NOT FOR creative writing or socia...

Execute the implementation planning workflow using the plan template

Manages the Protocol 128 multi-phase closure sequence including Technical Seal and Soul Persistence. Executes automatically when a session ends or work is complete.

Convert raw plugin analysis results into actionable improvement recommendations for agent-scaffolders and agent-skill-open-specifications. Trigger with "synthesize learnings", "generate improvement recommendations", "what should we improve in our scaffolders", "update our meta-skills based on these findings", or after completing a plugin analysis.

Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.

Review and rewrite Traditional Chinese text to remove Europeanized (歐化) writing patterns that arise from over-literal translation of Western sentence structures. Applies a 25-item checklist covering passive voice, abstract subjects, clause ordering, 的/們/性/地 overuse, calque prepositions, weak verbs, pronoun/tense overuse, long pre-modifiers, and more. Works on markdown files or inline text. Triggers on "/dewesternise", "去歐化", "太歐化了", "翻譯腔", "remove Europeanized patterns", "去翻譯腔", "改掉西化", "西化中文".

TRIGGER when user asks to add or modify a metric, counter, gauge, or histogram, or to track/measure an operation. Affects intermediate.go, manifest.yaml. Do NOT manually define metrics - this skill wires up recorders and OpenTelemetry names.

End-to-end pipeline for writing ML/AI research papers — from

Search scientific literature and research papers using FlowSearch to find relevant academic articles and publications.

Use before plan submission, major plan revision, and major stage transitions. Verify alignment, feasibility, rigor, completeness, and prevent unjustified regressions to earlier workflow phases.

Use when the workflow hits contradictions, missing evidence, failed runs, design flaws, or resource shifts. Diagnose the failure class, choose the narrowest safe correction, and escalate to the user when the core plan changes.