Agent skill

Dbrain Processor

by smixs in smixs/agent-second-brain

Personal assistant for processing daily voice/text entries from Telegram.

MITAuto-check passedKnowledge Management

Install Dbrain Processor

skills CLI
$ npx skills add smixs/agent-second-brain --skill dbrain-processor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install smixs/agent-second-brain dbrain-processor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/smixs/agent-second-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/vault/.claude/skills/dbrain-processor .claude/skills/dbrain-processor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dbrain-processor
GitHub stars
392
Token cost
~3.3k tokens
SKILL.md length
1,215 words
Files
12 (incl. references)
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Personal assistant for processing daily voice/text entries from Telegram.

  • Works in 4 steps: ALWAYS return HTML report — even if… → ALWAYS use the template below — no… → NEVER use markdown syntax (**, ##, , -) → …
  • /process command
  • SKILL.md covers CRITICAL: Output Format, Processing Flow, ОБЯЗАТЕЛЬНО: Логирование в… and Evolve MEMORY.md (Step 9 Detail), plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dbrain Processor is an agent skill from smixs/agent-second-brain. Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.

Its SKILL.md is about 3.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `phases/capture.md`, `phases/execute.md` and `phases/reflect.md`).

It sits in Knowledge Management, covering Scheduled and recurring tasks. It works with Telegram and Obsidian. The repository describes itself as: An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vault. Runs 24/7 on the Claude subscription you already have. The licence is MIT.

When your agent uses it

  • /process command
  • Daily 21:00 cron

Example prompts

  • “/dbrain-processor”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. ALWAYS return HTML report — even if entries already processed
  2. ALWAYS use the template below — no free-form text
  3. NEVER use markdown syntax (**, ##, , -)
  4. NEVER explain what you did in plain text — put it in HTML report

What it can do on your machine

Read from SKILL.md and the folder at commit 7828ed6. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are html and markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dbrain Processor loads about 3.3k tokens when it runs, and up to ~8.7k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 1,215 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~72
When it runs · the whole SKILL.md, loaded when a task matches
~3.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from smixs/agent-second-brain at commit 7828ed6, republished under its MIT licence (© smixs). 1,215 words, ~3,342 tokens.

Download SKILL.mdSave it as .claude/skills/dbrain-processor/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
dbrain-processor
description
Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.
type
note
depends_on
autograph

d-brain Processor

Process daily entries → thoughts (Obsidian) + HTML report (Telegram).

Integrates with Your Business data for business context.

CRITICAL: Output Format

ALWAYS return RAW HTML. No exceptions. No markdown. Ever.

Your final output goes directly to Telegram with parse_mode=HTML.

Rules:

  1. ALWAYS return HTML report — even if entries already processed
  2. ALWAYS use the template below — no free-form text
  3. NEVER use markdown syntax (**, ##, ```, -)
  4. NEVER explain what you did in plain text — put it in HTML report

WRONG:

html
<b>Title</b>

CORRECT: <b>Title</b>

Processing Flow

  1. Load personal context — Read goals/1-yearly, goals/2-monthly, goals/3-weekly
  2. Load business context:
    • Read business/_index.md — Your Business (клиенты, проекты, CRM)
    • Read projects/_index.md — личные проекты (если релевантно)
  3. Read daily — daily/YYYY-MM-DD.md
  4. Process entries — Classify → task or thought, detect business mentions
  5. Create cards (autograph) — new entities/thoughts become vault cards per the autograph template (type, description-as-snippet, tags, status); tasks become checklist entries in the daily note / project notes
  6. Build links — Connect notes with [[wiki-links]], link to business entities
  7. Generate HTML report — business activity + day summary
  8. Log actions to daily — append action log entry (see below)
  9. Evolve MEMORY.md — update long-term memory if needed (see below)
  10. Capture observations — record friction signals to handoff.md (see below)

ОБЯЗАТЕЛЬНО: Логирование в daily/

После ЛЮБЫХ изменений в vault — СРАЗУ пиши в daily/YYYY-MM-DD.md:

Формат:

## HH:MM [text]
{Описание действий}

**Создано/Обновлено:**
- [[path/to/file|Name]] — описание

Что логировать:

  • Создание файлов в thoughts/
  • Обновление business/ или projects/
  • Добавление task-записей в daily/проекты
  • Синхронизация с внешними системами

Пример:

## 14:30 [text]
Обработка ежедневных записей

**Создано задач:** 2
- [ ] Follow-up Acme Corp (due: завтра, p2)
- [ ] Подготовить КП Unilever (due: пятница, p2)

**Сохранено мыслей:** 1
- [[thoughts/ideas/product-launch|Product Launch]] — идея запуска

Зачем: Audit trail + контекст для будущих обработок.

Evolve MEMORY.md (Step 9 Detail)

ЦЕЛЬ: Поддерживать MEMORY.md актуальным. Не добавлять, а ЭВОЛЮЦИОНИРОВАТЬ.

Когда обновлять MEMORY.md

Проверь после обработки entries — есть ли информация достойная долгосрочной памяти?

Write Rules: Что достойно MEMORY.md

ПИСАТЬ:

  • ✅ Key decisions с impact (pivot, tool choice, architecture change)
  • ✅ Изменения в pipeline (новый лид, закрытая сделка, изменение статуса)
  • ✅ Финансовые изменения (оплаты получены, долги, новые контракты)
  • ✅ Новые паттерны/инсайты (learnings)
  • ✅ Изменения в Active Context (новый ONE Big Thing, Hot Projects)
  • ✅ Новые ключевые контакты (с context)

НЕ ПИСАТЬ:

  • ❌ Ежедневные мелочи (встречи, звонки без impact)
  • ❌ Временные заметки (оставить в daily/)
  • ❌ Дубликаты того что уже есть
  • ❌ Детали проектов (оставить в business/crm/, projects/)
  • ❌ Тривиальные задачи
Как обновлять (evolve, не append)

Принцип: Новое ЗАМЕНЯЕТ устаревшее, не добавляется рядом.

СитуацияДействие
Новое противоречит старомуЗАМЕНИТЬ старую информацию
Новое дополняет староеДобавить в существующую секцию
Информация устарелаУдалить или архивировать

Пример 1 — Изменение статуса проекта:

Old: "| Acme Corp NCP Meals | p1 | Активная разработка | $XXK |"
New info: "Acme Corp NCP Meals сдан клиенту"
→ ЗАМЕНИТЬ на: "| Acme Corp NCP Meals | ✅ | Завершён | $XXK |"

Пример 2 — Новое решение:

Добавить в Key Decisions таблицу:
| 2026-02-01 | Отказ от X в пользу Y | причина | impact |

Пример 3 — Изменение в pipeline:

Old: "| LogisticsLead | Hot | $XXK |"
New info: "LogisticsLead подписал контракт"
→ Удалить из Pipeline
→ Добавить в Hot Projects или Financial Context
Секции MEMORY.md для обновления
СекцияКогда обновлять
Active ContextИзменение ONE Big Thing, Hot Projects, Pipeline
Key DecisionsНовое решение с impact
Financial ContextОплаты, долги, контракты
Key PeopleНовый важный контакт
LearningsНовый паттерн/инсайт
Current CrisisИзменение в текущей критической ситуации
Формат Edit

Используй Edit tool для точечных изменений:

Edit MEMORY.md:
old_string: "| LogisticsLead | Hot | $XXK |"
new_string: "| LogisticsLead | ✅ Signed | $XXK |"
В отчёте

Если обновил MEMORY.md, добавь секцию:

html
<b>🧠 MEMORY.md обновлён:</b>
• Active Context → Hot Projects updated
• Key Decisions → +1 новое решение

Capture Observations (Step 10 Detail)

ЦЕЛЬ: Записывать friction signals, паттерны и идеи для улучшения системы.

Когда записывать

После обработки проверь — были ли проблемы или наблюдения?

ТипКогда
[friction]mcp-cli errors, timeouts, empty daily, broken links, unexpected data
[pattern]Повторяющийся паттерн (задачи всегда overdue, daily пустой по выходным)
[idea]Идея для улучшения pipeline, schema, отчёта
Формат

Append в vault/.session/handoff.md секцию ## Observations:

markdown
## Observations
- [friction] YYYY-MM-DD: transcription timeout 3x — retry спас, но -60 сек
- [pattern] YYYY-MM-DD: daily без entries 2 дня подряд — выходные?
- [idea] YYYY-MM-DD: CRM карточки без deal_deadline = невидимые дедлайны
Правила
  • Одна строка на наблюдение (конкретика, не абстракции)
  • Дата обязательна
  • Не повторять уже записанные observations
  • Когда observations ≥10 → сигнал для system improvement session
В отчёте

Если записаны observations, добавь:

html
<b>👁 Observations:</b>
• [friction] mcp-cli timeout 3x

Entry Format

HH:MM [type]

Content

Types: [voice], [text], [forward from: Name], [photo]

Business Context Integration

ТОЧКА ВХОДА: business/_index.md — читай для понимания бизнес-контекста.

Структура:
business/
├── _index.md       ← Статистика, обзор
├── crm/            ← ВСЁ: компании + сделки + проекты в одном файле
├── network/        ← Структура холдинга
└── events/         ← Мероприятия
Распознавание упоминаний

При обработке entries ищи упоминания клиентов и проектов:

ПаттернДействие
"звонил [Client]"Найти business/crm/{client}.md, добавить связь
"по проекту [Client]"Найти business/crm/{client}.md
"встреча с [Client]"Создать задачу + связать с business/crm/{client}.md
"отправил КП для [Client]"Связать с business/crm/{client}.md
Поиск клиента по имени
  1. Имя → kebab-case: "Acme Corp" → acme-corp, "Bi Group" → bi-group
  2. Искать: business/crm/{kebab-case}.md
  3. Если не найден — fuzzy search по grep -l "{name}" business/crm/
Создание связей

Когда упомянут клиент/проект, добавляй wiki-links:

В задачу:

"Follow-up [[business/crm/acme-corp|Acme Corp]] по снекам"

В thought:

Связано с: [[business/crm/techco|TechCo]], [[business/crm/phonebrand-smm|PhoneBrand SMM]]
Приоритет задач с бизнесом
УсловиеПриоритет
Клиент с priority: High + deadlinep1
Активный проект (In progress)p2
Клиент с priority: Highp2
Клиент с priority: Midp3
Prospect без срочностиp4

Classification

task → checklist entry in daily/project notes idea/reflection/learning → thoughts/ (see references/classification.md) client/project mention → link to Business/Projects + create task if actionable

Projects Context Integration

Точка входа: projects/_index.md

Структура:
projects/
├── _index.md       # Clients overview
├── clients/        # Clients
└── leads/          # Leads
Распознавание упоминаний
ПаттернФайл
"[Client A]"projects/clients/{client-a}.md
"[Client B]"projects/clients/{client-b}.md
"AI обучение", "воркшоп"projects/ контекст
Отличие от Business
  • Business = основной бизнес
  • Projects = личные проекты (консалтинг, обучение)

Если entry упоминает AI/ML обучение — ищи в projects/ сначала.

Contacts Context Integration

Точка входа: contacts/_index.md

Show full SKILL.md (486 more words)Show less
Распознавание имён в entries

Ищи паттерны:

  • "созвонился с [Contact] из [Client]"
  • "встреча с @username"
  • "Имя Фамилия написал"
Классификация
ИндикаторКатегорияVault Link
Known business clientsbusinessbusiness/crm/{client}
AI/обучение expertise, known leadsprojectsprojects/leads/{name}
Остальныеpersonal—
В отчёте

Если в entries упомянуты люди, добавь секцию:

html
<b>👤 Упомянуто контактов:</b>
• [Contact Name] (business → [[business/crm/acme-corp]])
• [Contact Name] (personal)

Priority Rules

p1 — Client deadline, urgent p2 — Aligns with ONE Big Thing or monthly priority p3 — Aligns with yearly goal p4 — Operational, no goal alignment

Process Goals Preference

When creating tasks, prefer PROCESS over OUTCOME formulations.

Outcome (less effective):

  • "Закрыть сделку с X"
  • "Запустить продукт"
  • "Подготовить программу"

Process (more effective):

  • "Отправить follow-up клиенту X" (actionable, controllable)
  • "2h deep work на MVP" (time-bounded)
  • "Показать драфт программы коллеге" (checkpoint)

When to transform:

  • Entry sounds vague/outcome-focused → make it specific/process-focused
  • User says "нужно сделать X" → create actionable next step, not X itself
  • Goal mentioned → create task that MOVES TOWARD goal, not goal itself

See: references/process-goals.md for patterns and examples.

Thought Categories

💡 idea → thoughts/ideas/ 🪞 reflection → thoughts/reflections/ 🎯 project → thoughts/projects/ 📚 learning → thoughts/learnings/

HTML Report Template

Output RAW HTML (no markdown, no code blocks):

📊 <b>Обработка за {DATE}</b>

<b>🎯 Текущий фокус:</b> {ONE_BIG_THING}

<b>📓 Сохранено мыслей:</b> {N} • {emoji} {title} → {category}/

<b>✅ Создано задач:</b> {M} • {task} <i>({priority}, {due})</i>

<b>🏢 Business Activity:</b> • {client} — {action} • {project} — {status update} <i>Упомянуто клиентов: {N} | Проектов: {M}</i>

<b>📋 Process Goals:</b> • {process goal 1} → {status} • {process goal 2} → {status} {N} активных | {M} требуют внимания <i>Создано новых: {K}</i>

<b>📅 Загрузка на неделю:</b> Пн: {n} | Вт: {n} | Ср: {n} | Чт: {n} | Пт: {n} | Сб: {n} | Вс: {n}

<b>⚠️ Требует внимания:</b> • {overdue or stale goals}

<b>🔗 Новые связи:</b> • [[Note A]] ↔ [[Note B]]

<b>⚡ Топ-3 приоритета:</b>

  1. {task}
  2. {task}
  3. {task}

<b>📈 Прогресс:</b> • {goal}: {%} {emoji}

<b>🧠 MEMORY.md:</b> • {section} → {change description} <i>(если обновлено)</i>


<i>Обработано за {duration}</i>

If Already Processed

If all entries have <!-- ✓ processed --> marker, return status report:

📊 <b>Статус за {DATE}</b>

<b>🎯 Текущий фокус:</b> {ONE_BIG_THING}

<b>📋 Process Goals:</b> • {process goal 1} → {status} • {process goal 2} → {status} {N} активных | {M} требуют внимания

<b>📅 Загрузка на неделю:</b> Пн: {n} | Вт: {n} | Ср: {n} | Чт: {n} | Пт: {n} | Сб: {n} | Вс: {n}

<b>⚠️ Требует внимания:</b> • {overdue count} просроченных • {today count} на сегодня

<b>⚡ Топ-3 приоритета:</b>

  1. {task}
  2. {task}
  3. {task}

<i>Записи уже обработаны ранее</i>

Allowed HTML Tags

<b> — bold (headers) <i> — italic (metadata) <code> — commands, paths <s> — strikethrough <u> — underline <a href="url">text</a> — links

FORBIDDEN in Output

NO markdown: **, ##, -, *, backticks NO code blocks (triple backticks) NO tables NO unsupported tags: div, span, br, p, table

Max length: 4096 characters.

References

Read these files as needed:

  • references/about.md — User profile, decision filters
  • references/classification.md — Entry classification rules
  • references/goals.md — Goal alignment logic
  • references/process-goals.md — Process vs outcome goals, transformation patterns
  • references/links.md — Wiki-links building
  • references/rules.md — Mandatory processing rules
  • references/report-template.md — Full HTML report spec
  • references/business.md — Business client/project context, search patterns
  • references/contacts.md — Contacts search and classification

Business Quick Reference

Точка входа: business/_index.md

Поиск клиента:

grep -l "Acme Corp" business/crm/
→ business/crm/acme-corp.md

Активные сделки:

grep -l "deal_status:" business/crm/

High priority клиенты:

grep -l "priority: High" business/crm/

Frontmatter полей:

  • type: crm
  • industry, priority, status, region, owner, responsible
  • deal_status, deal_deadline (для активных сделок)
  • updated

Relevant Skills

  • [[vault/.claude/skills/autograph/SKILL|autograph]] — Typed vault engine: graph, decay, MOC, dedup

© smixs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (references) in vault/.claude/skills/dbrain-processor of smixs/agent-second-brain.

  • SKILL.md
  • phases/capture.md
  • phases/execute.md
  • phases/reflect.md
  • references/about.md
  • references/business-context.md
  • references/classification.md
  • references/contacts.md
  • references/goals.md
  • references/links.md
  • references/report-template.md
  • references/rules.md

Open the folder on GitHubat commit 7828ed6

Compare with similar skills

Dbrain Processor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dbrain Processor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dbrain Processor this skillsmixs/agent-second-brain392—~3.3kAutomated safety check: PassMIT
Cascading Goal Trackerballred/obsidian-claude-pkm1.9k—~1.5kAutomated safety check: PassMIT
Literature Discovery PipelineYuan1z0825/nature-skills46k2 repos~1.2kAutomated safety check: PassMIT
Setupjdpolasky/ai-chief-of-staff104—~3.5kAutomated safety check: PassMIT
Daily UpdateAr9av/obsidian-wiki3.5k—~2.4kAutomated safety check: NotesMIT
Preserveiurykrieger/claude-bedrock105—~14kAutomated safety check: NotesMIT

Similar skills

  • Cascading Goal Tracker

    ballred/obsidian-claude-pkm

    Tracks three-year, yearly, monthly, and weekly goals in linked Markdown files, calculating completion percentages and flagging stalled goals.

    1.9k GitHub stars~1.5k tokensUpdated 7 mo ago
    Knowledge ManagementAuto-check passed
  • Literature Discovery Pipeline

    Yuan1z0825/nature-skills

    Runs a daily literature pipeline: multi-source search, six-dimension scoring, fine reading, formatted delivery to a chat channel and archival of the notes.

    46k GitHub starsUsed in 2 repos~1.2k tokens
    Research & ScienceAuto-check passed
  • Setup

    jdpolasky/ai-chief-of-staff

    First-time setup for the Chief of Staff system. An agent skill from jdpolasky/ai-chief-of-staff.

    104 GitHub stars~3.5k tokensUpdated 5 days ago
    Knowledge ManagementAuto-check passed
  • Daily Update

    Ar9av/obsidian-wiki

    Run or configure the daily wiki maintenance cycle: check source freshness, refresh the index and hot.md, and manage its scheduled 9 AM launchd/systemd/cron reminder.

    3.5k GitHub stars~2.4k tokensUpdated today
    Productivity & AutomationAuto-check: notes
  • Preserve

    iurykrieger/claude-bedrock

    Single write point for the vault. An agent skill from iurykrieger/claude-bedrock.

    105 GitHub stars~14k tokensUpdated 5 mo ago
    Knowledge ManagementAuto-check: notes
  • Grasshopper Voicemail Monitor

    hewi333/Mom-n-Pop-Skills

    Turn voicemail-drop emails from a virtual phone provider (Grasshopper — or any service that emails transcribed voicemails) into CRM leads and Telegram notifications.

    122 GitHub stars~2.4k tokensUpdated 26 days ago
    Productivity & AutomationAuto-check: notes

More from smixs/agent-second-brain

  • Autograph

    smixs/agent-second-brain

    Schema-as-code enforcement for any Obsidian vault. An agent skill from smixs/agent-second-brain.

    392 GitHub stars~3.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Migrate Doctor

    smixs/agent-second-brain

    Diagnose and repair a broken or non-standard agent-second-brain install/migration.

    392 GitHub stars~904 tokensUpdated 2 mo ago
    Auto-check: notes
  • Cron

    smixs/agent-second-brain

    Управление собственным расписанием — напоминания, рутины, периодические задачи.

    392 GitHub stars~856 tokensUpdated 2 mo ago
    Auto-check passed

Questions about Dbrain Processor

What does Dbrain Processor do?

Personal assistant for processing daily voice/text entries from Telegram. Dbrain Processor is an agent skill from smixs/agent-second-brain. Personal assistant for processing daily voice/text entries from Telegram.

When should I use Dbrain Processor?

Dbrain Processor fits situations like: /process command; daily 21:00 cron.

How do I install Dbrain Processor in Claude Code?

Run `npx skills add smixs/agent-second-brain --skill dbrain-processor -a claude-code`. Or copy the skill folder (vault/.claude/skills/dbrain-processor in smixs/agent-second-brain) into .claude/skills/dbrain-processor in your project. Claude Code loads it when a task matches its description.

How do I install Dbrain Processor in Codex?

Run `npx skills add smixs/agent-second-brain --skill dbrain-processor -a codex`. Or copy the skill folder (vault/.claude/skills/dbrain-processor in smixs/agent-second-brain) into .agents/skills/dbrain-processor in your project. Codex loads it when a task matches its description.

Can I use Dbrain Processor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add smixs/agent-second-brain --skill dbrain-processor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dbrain-processor, .gemini/skills/dbrain-processor, .github/skills/dbrain-processor and .opencode/skills/dbrain-processor in your project.

What does Dbrain Processor need to run?

SKILL.md names no scripts, command-line tools or credentials: Dbrain Processor is instructions for the agent only.

Does Dbrain Processor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dbrain Processor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Dbrain Processor use?

Dbrain Processor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dbrain Processor use?

About 3.3k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.

What are the alternatives to Dbrain Processor?

Skills that share tags, products or a category with Dbrain Processor: Cascading Goal Tracker (ballred/obsidian-claude-pkm, 1.9k stars), Literature Discovery Pipeline (Yuan1z0825/nature-skills, 46k stars), Setup (jdpolasky/ai-chief-of-staff, 104 stars) and Daily Update (Ar9av/obsidian-wiki, 3.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dbrain Processor?

smixs (a GitHub user) maintains it in smixs/agent-second-brain, which has 392 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on August 5, 2026.

Source: smixs/agent-second-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.