From deep-research
This skill should be used when the user asks 'how do I do deep research', 'show me research skills', 'help me research a topic', 'what research methodology should I use', or at the start of any structured web research task. Provides the index of all deep research principle skills and the /research command.
npx claudepluginhub oborchers/fractional-cto --plugin deep-researchThis skill uses the workspace's default tool permissions.
Structured deep research transforms ad-hoc web searches into a repeatable, hallucination-resistant research pipeline. Without deliberate structure, research agents gravitate toward the first sources found, fail to verify claims, and produce confident reports built on unreliable foundations.
Generates design tokens/docs from CSS/Tailwind/styled-components codebases, audits visual consistency across 10 dimensions, detects AI slop in UI.
Records polished WebM UI demo videos of web apps using Playwright with cursor overlay, natural pacing, and three-phase scripting. Activates for demo, walkthrough, screen recording, or tutorial requests.
Delivers idiomatic Kotlin patterns for null safety, immutability, sealed classes, coroutines, Flows, extensions, DSL builders, and Gradle DSL. Use when writing, reviewing, refactoring, or designing Kotlin code.
Structured deep research transforms ad-hoc web searches into a repeatable, hallucination-resistant research pipeline. Without deliberate structure, research agents gravitate toward the first sources found, fail to verify claims, and produce confident reports built on unreliable foundations.
This plugin provides 4 methodology skills and the /research command for orchestrated multi-agent research sessions.
Use the Skill tool to invoke any skill by name. When invoked, follow the skill's guidance directly.
| Skill | Triggers On |
|---|---|
deep-research:research-methodology | Starting any research task — query analysis, decomposition strategies, effort scaling, dynamic replanning, stopping criteria |
deep-research:source-evaluation | Evaluating sources — credibility ranking (T1-T6 tiers), multi-provider search strategy, SEO spam detection, domain-specific source selection |
deep-research:hallucination-prevention | Any research output — hallucination taxonomy, citation verification rules, circuit breaker patterns, confidence scoring, cascading prevention |
deep-research:synthesis-and-reporting | Combining findings — deduplication, conflict resolution, narrative construction, citation formatting, report quality assessment |
Invoke a skill when there is even a small chance the work touches one of these areas:
research-methodology to plan decomposition and effort scalingsource-evaluation to assess what you findhallucination-prevention to verify before statingsynthesis-and-reporting to merge and cite properlyFor full orchestrated research sessions, use /research. The command:
research-worker agents (Sonnet) — each writes findings with a Verifiable Claims Tableresearch-verifier agents (Sonnet) — each re-fetches sources and checks claims independentlyresearch-synthesizer agent (Opus) — applies corrections, merges findings, writes final document with Confidence AssessmentAll research skills rest on three foundations:
Every claim needs a source — No unsourced assertions. If it cannot be cited, it cannot be stated as fact. Flag uncertainty explicitly.
Source quality determines output quality — 57% of research errors originate in early retrieval. Front-load high-quality sources. Prefer primary sources (T1-T2) over secondary sources.
Verify before synthesizing — Treat each agent's output as untrusted input. Cross-reference claims between sources. Use deterministic validation where possible.