Not in the top 1,000 by GitHub stars
AlekseiUL/agentforge-openclaw
Create production-ready skills and agents for OpenClaw. 4-level memory, auto-improvement, 22 battle-tested pitfalls.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → aa1895cebd81
No earlier version was observed for comparison.
examples/code-reviewer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → aa1895cebd81
No earlier version was observed for comparison.
examples/content-planner/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → aa1895cebd81
No earlier version was observed for comparison.
examples/meeting-prep/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → aa1895cebd81
No earlier version was observed for comparison.
examples/task-tracker/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → aa1895cebd81
No earlier version was observed for comparison.
examples/weather-bot/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aa1895cebd81
No earlier version was observed for comparison.
Heat
1.5- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- agent-forge
/ - code-reviewer
examples/code-reviewer - content-planner
examples/content-planner - meeting-prep
examples/meeting-prep - task-tracker
examples/task-tracker - weather-bot
examples/weather-bot
How it works
agent-forge
When your agent uses it
Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
6,221 tokensWhen the skill is activated
Reference documents
7,256 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Быстрый старт
- Режим A: СКИЛЛ
- Режим B: АГЕНТ
- Режим C: УЛУЧШЕНИЕ СУЩЕСТВУЮЩЕГО
- ⛔ Когда НЕ создавать
- ⚠<U+FE0F> Грабли
- Примеры из нашей системы
- Материалы
Scripts executed separately
scripts/install.pytests/test_installer.py
Files
.github/DEPENDENCIES.mddoc384 bytes.github/dependabot.ymlasset273 bytes.github/workflows/offline-regression.ymlasset577 bytes.github/workflows/repository-quality.ymlasset3,263 bytesLICENSEasset1,083 bytesNOTICE.mddoc667 bytesOFFLINE-VERIFICATION.mddoc709 bytesREADME.mddoc16,018 bytesSECURITY.mddoc1,004 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesSKILL.mdcore28,680 bytesbanner.jpgasset125,685 bytesreferences/agent-templates.mddoc13,388 bytesscripts/install.pyruns1,274 bytestests/test_installer.pyruns2,005 bytes
Read SKILL.md
# AgentForge 🔧
Создание и улучшение скиллов и агентов OpenClaw. Лучшие практики + боевой опыт с десятками скиллов и агентов. Агенты: от базового (5 мин) до полноценного рабочего (с памятью, автоулучшением, командой).
**Шаблоны файлов агента:** `references/agent-templates.md`
---
## Быстрый старт
### Скилл за 5 минут:
1. `mkdir skills/<имя>/` → создать `SKILL.md` с frontmatter (name, description) + алгоритм + 2 примера
2. Готово. Скилл подхватится автоматически (hot-reload)
View the complete source on GitHubcode-reviewer
When your agent uses it
Ревью кода: находит баги, проблемы безопасности, предлагает улучшения. Triggers: 'ревью кода', 'проверь код', 'code review', 'посмотри код', 'review this'.
What it loads into context
Frontmatter
57 tokensAlways available to the agent
SKILL.md
628 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Роль
- Правила ревью
- Примеры
- Чего НЕ делать
Files
SKILL.mdcore3,153 bytes
Read SKILL.md
# Code Reviewer
Ты - опытный код-ревьюер. Проверяешь код на баги, безопасность, читаемость и best practices. Тип: **Role**.
## Роль
Ревьюер с 10+ годами опыта. Прямой, конкретный, без воды. Не хвалишь ради приличия - если код хорош, говоришь "ок". Если плох - объясняешь почему и как исправить.
## Правила ревью
### Приоритеты проверки (от важного к мелочам)
1. **Баги** - логические ошибки, off-by-one, null reference, race conditions
2. **Безопасность** - SQL injection, XSS, утечка данных, хардкод секретов
3. **Архитектура** - нарушение SRP, сильная связанность, дублированиеView the complete source on GitHubcontent-planner
When your agent uses it
Планирование контента: идеи, календарь, форматы, адаптация под платформы. Triggers: 'контент-план', 'план контента', 'что постить', 'content plan', 'идеи для контента', 'календарь постов'.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
711 tokensWhen the skill is activated
Reference documents
348 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Роль
- Алгоритм создания контент-плана
- Примеры
- Чего НЕ делать
Files
SKILL.mdcore3,548 bytesreferences/style-guide.mddoc1,738 bytes
Read SKILL.md
# Content Planner
Ты - контент-стратег. Помогаешь планировать, генерировать идеи и составлять календарь публикаций. Тип: **Гибрид** (Role + Workflow).
## Роль
Опытный контент-стратег. Знаешь особенности разных платформ. Предлагаешь конкретные идеи, не абстракции. Думаешь о аудитории, не о количестве.
Правила стиля и тона - в `references/style-guide.md`. Прочитай при первом вызове.
## Алгоритм создания контент-плана
### Шаг 1. Сбор контекста
Спроси (по одному):View the complete source on GitHubmeeting-prep
When your agent uses it
Подготовка к встречам и звонкам: agenda, вопросы, заметки, follow-up. Triggers: 'подготовка к встрече', 'meeting prep', 'agenda', 'готовлюсь к звонку', 'план встречи'.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
716 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Алгоритм
- Примеры
Files
SKILL.mdcore3,388 bytes
Read SKILL.md
# Meeting Prep
Помогает подготовиться к встречам: agenda, ключевые вопросы, шаблон заметок, follow-up. Тип: **Workflow** с Progressive Disclosure.
## Алгоритм
### Шаг 1. Контекст встречи
Спроси (по одному):
1. С кем встреча? (клиент / коллега / инвестор / партнёр)
2. Тема/цель?
3. Сколько времени? (15 мин / 30 мин / 60 мин)
4. Первая встреча или повторная?
View the complete source on GitHubtask-tracker
When your agent uses it
Управление задачами: добавить, завершить, показать список, приоритеты. Triggers: 'задача', 'задачи', 'todo', 'добавь задачу', 'что сделать', 'список дел', 'task'.
What it loads into context
Frontmatter
64 tokensAlways available to the agent
SKILL.md
536 tokensWhen the skill is activated
Reference documents
98 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Где данные
- Алгоритм
- Как обновлять данные
- Примеры
Files
SKILL.mdcore2,520 bytesdata/tasks.mddoc367 bytes
Read SKILL.md
# Task Tracker
Простой трекер задач с хранением в файле. Тип: **Data-driven**.
## Где данные
Задачи хранятся в `data/tasks.md`. Читай этот файл при каждом вызове. Обновляй после каждого изменения.
## Алгоритм
### Добавить задачу
1. Запиши в `data/tasks.md` в формате: `- [ ] [приоритет] задача (дата добавления)`
2. Приоритеты: `[!]` высокий, `[~]` средний, `[.]` низкий. По умолчанию средний
3. Подтверди: "Добавил: [задача]"View the complete source on GitHubweather-bot
When your agent uses it
Погода и прогноз для любого города. Triggers: 'погода', 'weather', 'прогноз', 'температура', 'какая погода в'.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
358 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Алгоритм
- Примеры
- Ограничения
Files
SKILL.mdcore1,659 bytes
Read SKILL.md
# Weather Bot
Показывает текущую погоду и прогноз. Тип: **Workflow** (простой).
## Алгоритм
1. Определи город из запроса. Если не указан - спроси
2. Получи погоду: `curl "wttr.in/<город>?format=j1"`
3. Покажи результат в формате:
```
<Город>, <страна>
Сейчас: <температура>°C, <описание>
Ветер: <скорость> км/чView the complete source on GitHubSkills included
- agent-forge
- code-reviewer
- content-planner
- meeting-prep
- task-tracker
- weather-bot
Repository facts
- License
- MIT
- Created
- Mar 9, 2026
- Last pushed
- Oct 29, 2026
- Forks
- 7
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 9 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 24 network referencesin 4 files: README.md:13 SECURITY.md:7 weather-bot/SKILL.md:12 and 1 more
- No hidden or obfuscated text
- 1 instruction override signalin 1 file: OFFLINE-VERIFICATION.md:13
- 2 executable scriptsin 2 files: scripts/install.py:1 tests/test_installer.py:1
- No access to secrets
- No requests to vote in Hot
Show all 27 signals by file
NOTICE.md
- Network accessline 7
Canonical source: https://github.com/AlekseiUL/agentforge-openclaw
OFFLINE-VERIFICATION.md
- Instruction override signalline 13
Review the commit diff and use a new checkout of the pre-change commit for source rollback. Keep user data and live installations untouched. A source rollback is not permission to restore unsafe network exposure or bypass approval.
README.md
- Network accessline 13
- YouTube: https://youtube.com/@alekseiulianov - Network accessline 14
- Telegram channel - Sprut AI: https://t.me/Sprut_AI - Network accessline 15
- Telegram chat - Sprut AI: https://t.me/+eH-qNIDmud8zNDZi - Network accessline 16
- AI Операционка: https://t.me/tribute/app?startapp=sJyg - Network accessline 20
This project is maintained by Aleksei Ulianov / Sprut_AI. Original repository: https://github.com/AlekseiUL/agentforge-openclaw - Network accessline 21
Original repository: https://github.com/AlekseiUL/agentforge-openclaw - Network accessline 177
- 🎬 YouTube: [@alekseiulianov](https://youtube.com/@alekseiulianov) - Network accessline 178
- 📱 Telegram: [@Sprut_AI](https://t.me/Sprut_AI) - Network accessline 184
👉 [**AI ОПЕРАЦИОНКА** — join](https://t.me/tribute/app?startapp=sAFx) - Network accessline 334
- 🎬 YouTube: [@alekseiulianov](https://youtube.com/@alekseiulianov) - Network accessline 335
- 📱 Telegram: [@Sprut_AI](https://t.me/Sprut_AI) - Network accessline 341
👉 [**AI ОПЕРАЦИОНКА** — подписка](https://t.me/tribute/app?startapp=sAFx) - Network accessline 353
- 📺 YouTube: [youtube.com/@alekseiulianov](https://youtube.com/@alekseiulianov) - Network accessline 354
- 📱 Telegram: [t.me/Sprut_AI](https://t.me/Sprut_AI) - Network accessline 355
- 🔥 AI ОПЕРАЦИОНКА (Premium): [Подписка](https://t.me/tribute/app?startapp=sJyg) — продвинутые материалы, скиллы, агенты, поддержка - Network accessline 356
- 💻 GitHub: [github.com/AlekseiUL](https://github.com/AlekseiUL)
SECURITY.md
- Network accessline 7
Preferred public coordination path: - Canonical repository: https://github.com/AlekseiUL/agentforge-openclaw - Network accessline 8
- Canonical repository: https://github.com/AlekseiUL/agentforge-openclaw - Network accessline 10
- Telegram channel: https://t.me/Sprut_AI - Network accessline 25
Where redistribution is permitted by the applicable license, redistributed copies should preserve the license, copyright notice, and canonical repository link: https://github.com/AlekseiUL/agentforge-openclaw - Network accessline 26
https://github.com/AlekseiUL/agentforge-openclaw
examples/weather-bot/SKILL.md
scripts/install.py
- Executable scriptline 1
Executable file
tests/test_installer.py
- Executable scriptline 1
Executable file
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 27 facts
- Network access in prose of documentationNOTICE.md:7Low confidence
- Instruction override signal in prose of documentationOFFLINE-VERIFICATION.md:13Low confidence
- Network access in prose of documentationREADME.md:13Low confidence
- Network access in prose of documentationREADME.md:14Low confidence
- Network access in prose of documentationREADME.md:15Low confidence
- Network access in prose of documentationREADME.md:16Low confidence
- Network access in prose of documentationREADME.md:20Low confidence
- Network access in prose of documentationREADME.md:21Low confidence
- Network access in prose of documentationREADME.md:177Low confidence
- Network access in prose of documentationREADME.md:178Low confidence
- Network access in prose of documentationREADME.md:184Low confidence
- Network access in prose of documentationREADME.md:334Low confidence
- Network access in prose of documentationREADME.md:335Low confidence
- Network access in prose of documentationREADME.md:341Low confidence
- Network access in prose of documentationREADME.md:353Low confidence
- Network access in prose of documentationREADME.md:354Low confidence
- Network access in prose of documentationREADME.md:355Low confidence
- Network access in prose of documentationREADME.md:356Low confidence
- Network access in prose of documentationSECURITY.md:7Low confidence
- Network access in prose of documentationSECURITY.md:8Low confidence
- Network access in prose of documentationSECURITY.md:10Low confidence
- Network access in prose of documentationSECURITY.md:25Low confidence
- Network access in prose of documentationSECURITY.md:26Low confidence
- Network access in prose of the SKILL.mdweather-bot/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdweather-bot/SKILL.md:13Low confidence
- Executable script in prose of a file that runsscripts/install.py:1Low confidence
- Executable script in code of a testtests/test_installer.py:1Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.