Use when asked to research deeply, compare options or vendors, fact-check a claim, investigate an unfamiliar topic, prepare a report or briefing, build a knowledge base or reference doc, or trace a claim to its primary source.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Deep Research
Verified: 2026-09-08
Primary sources over blog rewrites. Every claim traceable, every gap named. "Could not find X" is a valid result — never fabricate to close one.
## Workflow
Scope (question, audience, depth, query budget) → outline (items, fields, success criteria) → pick retrieval tool → gather tiers 1→4, never start at 4 → verify per protocol → date-check staleness/version → apply stop criteria → compile output format.
## Retrieval tool
| Need | Use |
|---|---|
| Library/API/framework docs | Docs-index tool (e.g. Context7-style MCP) — version-scoped, current, far fewer queries |
| Fetch returns empty/JS shell | Headless-browser fetch — plain HTTP misses client-rendered content |
| Many sources at once | Bulk-crawler — one dispatch vs. N fetches, spares budget |
| 403/challenge on a known-live site | Retry browser-capable before writing it off; fingerprinting blocks curl, not the site |
| Everything else | Web search + `search-techniques.md` |
## Query budget
…
The line at the top of this page pins the label git:20260929.c1f17bd, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_sv7ymfn4eh62a5xt
GET https://markdownregistry.com/api/v1/resolve?ref=sergeyizmailov/knowledge-delta-skills/deep-research
GET https://markdownregistry.com/api/v1/blob/e74b207a7ad8f8f8cf3efe308ccdd58c5ec37af426a50a04eaea200cbe969b8e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
sergeyizmailov/knowledge-delta-skills · skills/engineering/knowledge-delta-skill-architect/SKILL.md · Triggers: write a skill for X, improve/shrink this skill, is this skill worth its tokens, my skill never triggers, port…
sergeyizmailov/knowledge-delta-skills · skills/frontend/design-stack-picker/SKILL.md · Use when building or restyling frontend UI and choosing building blocks — icon sets, fonts, component/block libraries…
sergeyizmailov/knowledge-delta-skills · skills/frontend/normcore-web/SKILL.md · Use when building or restyling a website that should look like ordinary, long-running commercial web rather than a…
sergeyizmailov/knowledge-delta-skills · skills/frontend/responsive-adapter/SKILL.md · Make an existing landing page, admin panel, dashboard, or any non-responsive page work at every viewport from 320px to…
sergeyizmailov/knowledge-delta-skills · skills/meta/measurement-experimentation-ops/SKILL.md · Gatekeeper for 'is this result real before scaling' on Meta/Facebook buys: SRM, peeking, contamination, lag and…
sergeyizmailov/knowledge-delta-skills · skills/meta/meta-ads/SKILL.md · Meta (Facebook/Instagram) Ads theory and diagnostics for the policy-compliant (clean) lane: 'why is CPA up', 'CBO vs…
sergeyizmailov/knowledge-delta-skills · skills/meta/meta-grey-ops/SKILL.md · Launches, monitors and operates Meta (Facebook/Instagram) ads for any vertical and offer through the metaops CLI…
sergeyizmailov/knowledge-delta-skills · skills/meta/senior-buyer-ops/SKILL.md · Senior buyer operations for Meta (FB/IG): portfolio-level decisions on what to kill, watch or scale across accounts…
sergeyizmailov/knowledge-delta-skills · skills/security/js-obfuscation/SKILL.md · Use when obfuscating JavaScript, building anti-detection layers, evading Google Safe Browsing, hiding payloads from…
affaan-m/ecc · .agents/skills/deep-research/SKILL.md · Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited…
affaan-m/ecc · .kiro/skills/deep-research/SKILL.md · Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited…
bytedance/deer-flow · skills/public/deep-research/SKILL.md · Use this skill instead of WebSearch for ANY question requiring web research. Trigger on queries like "what is X"…
imbad0202/academic-research-skills · deep-research/SKILL.md · Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 8 modes: full…
thu-maic/openmaic · skills/agent-runtime/deep-research/SKILL.md · Courses whose content rests on current, external or real-world facts that must be verified against live sources before…
davidondrej/skills · skills/research-and-web/deep-research/SKILL.md · Run deep research through DeepAPI and save a report with sources. Use when asked for deep research, DeepAPI research…
