deep-researcher
Skill0 starsChanged 4 months agoMITView on GitHub
Многошаговый ресёрч с оценкой источников и синтезом
4 other projects use a version of this.
Adopted by
Most recently taken up by
- yanzyuyu/min-toktheir own version, first seen Nov 8, 2026
- Karanjot786/agent-skills-clitheir own version, first seen Oct 13, 2026
- nimbalyst/skillstheir own version, first seen Feb 16, 2026
- JohnJBoren/claude-skills-ecosystemtheir own version, first seen Dec 26, 2025
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- Karanjot786/agent-skills-cli★ 182same name
- nimbalyst/skills★ 28same name
- JohnJBoren/claude-skills-ecosystem★ 2same name
- yanzyuyu/min-tok★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository31 other files it gives its agents.
- api-and-interface-designSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- context-engineeringSkill
- debugging-and-error-recoverySkill
- deprecation-and-migrationSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- idea-refineSkill
- incremental-implementationSkill
- interview-meSkill
- delivery-quality-gateSkill
- fact-checkerSkill
- priority-scorerSkill
- prompt-injection-detectorSkill
- report-formatterSkill
- secret-leak-scannerSkill
- task-decomposerSkill
- observability-and-instrumentationSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- using-agent-skillsSkill
The file
Files
Deep Researcher
Назначение
Проводит многошаговый ресёрч: формулировка запросов → поиск → оценка → выявление пробелов → повторный поиск → синтез.
Алгоритм
- Декомпозиция вопроса — разбить тему на 3-5 аспектов
- Первичный поиск — по 2-3 запроса на аспект (web_search.py или Fetch MCP)
- Оценка источников — авторитетность, свежесть, релевантность
- Выявление пробелов — что не покрыто? какие вопросы остались?
- Углублённый поиск — целевые запросы по пробелам
- Синтез — структурированный отчёт с цитатами
Формат отчёта
# [Тема]
## Ключевые находки
1. [факт] — [источник]
2. [факт] — [источник]
## Открытые вопросы
- [вопрос]
## Источники
- [URL] — [оценка качества]Инструменты
- web_search.py — поиск (ddgs)
- Fetch MCP — загрузка страниц
- security_scanner.py — проверка URL перед загрузкой
- key_rotator.py — LLM для суммаризации (если нужно)
Лимиты
- Максимум 10 поисковых запросов на ресёрч
- Максимум 5 страниц через Fetch
- Проверять каждый URL через security_scanner
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.