Not in the top 1,000 by GitHub stars
serejaris/personal-corp-os
Personal Corp OS — управление личной компанией через AI-агентов: задачи вне головы, отделы вместо памяти, недельное ретро. Открытые скиллы для Claude Code и Codex
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
archive/skills/paperclip-api/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
experimental/skills/daily-retro/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/art-director/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/audit-agent-rules/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/avatar/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/benchmark/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/cc-analytics/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/ceo-council/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/claude-md-writer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/claude-sessions-sync/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/corp-doctor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/corp-new/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/daily/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/fable-ruki-agenty/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/gh-issues/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/grill-me/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/harness/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/html-draft/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/idea/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/it-ram-doctor/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/make-3d/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/make-landing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/manager/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/meeting-copilot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/readme-generator/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/retro/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/safe-public-release/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/sdlc-milestones/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6f3983e45b13
No earlier version was observed for comparison.
skills/tg-bot-ops/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/to-issues/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/to-prd/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/weekly-planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
skills/weekly-retro/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
templates/department/skills/daily/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
templates/department/skills/planning/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
templates/department/skills/retro/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
784fcdeb6f43 → 6f3983e45b13
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 784fcdeb6f43
No earlier version was observed for comparison.
Verified commit 6f3983e45b13fcce8ebe1c4523983beb6174326e
git clone --filter=blob:none --no-checkout https://github.com/serejaris/personal-corp-os.git .hotskills/serejaris-personal-corp-os && git -C .hotskills/serejaris-personal-corp-os checkout --detach 6f3983e45b13fcce8ebe1c4523983beb6174326e
# Copy each selected skill directory from .hotskills/serejaris-personal-corp-os into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/serejaris/personal-corp-os.git .hotskills/serejaris-personal-corp-os && git -C .hotskills/serejaris-personal-corp-os checkout --detach 6f3983e45b13fcce8ebe1c4523983beb6174326e
# Copy each selected skill directory from .hotskills/serejaris-personal-corp-os into .agents/skills/<skill-name>/Heat
3.0- 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
- paperclip-api
archive/skills/paperclip-api - daily-retro
experimental/skills/daily-retro - art-director
skills/art-director - audit-agent-rules
skills/audit-agent-rules - avatar
skills/avatar - benchmark
skills/benchmark - cc-analytics
skills/cc-analytics - ceo-council
skills/ceo-council - claude-md-writer
skills/claude-md-writer - claude-sessions-sync
skills/claude-sessions-sync - corp-doctor
skills/corp-doctor - corp-new
skills/corp-new - daily
skills/daily - fable-ruki-agenty
skills/fable-ruki-agenty - gh-issues
skills/gh-issues - grill-me
skills/grill-me - harness
skills/harness - html-draft
skills/html-draft - idea
skills/idea - it-ram-doctor
skills/it-ram-doctor - make-3d
skills/make-3d - make-landing
skills/make-landing - manager
skills/manager - meeting-copilot
skills/meeting-copilot - readme-generator
skills/readme-generator - retro
skills/retro - safe-public-release
skills/safe-public-release - sdlc-milestones
skills/sdlc-milestones - tg-bot-ops
skills/tg-bot-ops - to-issues
skills/to-issues - to-prd
skills/to-prd - weekly-planning
skills/weekly-planning - weekly-retro
skills/weekly-retro - daily
templates/department/skills/daily - planning
templates/department/skills/planning - retro
templates/department/skills/retro
How it works
paperclip-api
When your agent uses it
Use when managing Paperclip AI agent companies - creating tasks, managing agents, approving hires, running heartbeats, or any Paperclip control-plane operations via CLI or REST API. Triggers on "paperclip", "задача агенту", "одобри найм", "heartbeat", "запусти агента".
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
2,403 tokensWhen the skill is activated
Reference documents
841 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Когда использовать
- Конфигурация инстанса
- CLI — быстрые команды
- REST API — эндпоинты
- Файлы инструкций
- Типичные сценарии
- Чего пока нет
- Ссылки
Files
../../../.claude-plugin/marketplace.jsonasset812 bytes../../../.claude-plugin/plugin.jsonasset985 bytesREADME.mddoc1,485 bytesREADME.ru.mddoc2,159 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesSKILL.mdcore9,912 bytesassets/illustration.pngasset503,427 bytes
Read SKILL.md
# Paperclip API
Управление компаниями AI-агентов через CLI и REST API. Без интерфейса.
## Когда использовать
- Создать/обновить задачу для агента
- Посмотреть статус агентов, задач, расходов
- Одобрить найм или стратегию
- Запустить heartbeat вручную
- Изменить промпт, модель или бюджет агента
- Прокомментировать задачу
## Конфигурация инстансаView the complete source on GitHubdaily-retro
When your agent uses it
Experimental. Daily retro from your agents' own logs: reads today's Claude Code and Codex sessions on this machine, groups them by project, adds git state (commits, uncommitted files, unpushed commits) and lists the tails — what was done and what was left open. Then closes the tails the way the manager skill does: issue comment, commit or a conscious "drop". Runs by itself every evening as an automation. Triggers on "/daily-retro", "дневное ретро", "что сегодня сделали агенты", "подбей хвосты", "daily retro".
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
977 tokensWhen the skill is activated
Reference documents
362 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- What it reads
- Steps
- Automation
- Boundaries
Scripts executed separately
scripts/collect.py
Files
README.mddoc665 bytesREADME.ru.mddoc1,083 bytesSKILL.mdcore3,986 bytesautomation/daily-retro.plistasset719 bytesautomation/daily-retro.serviceasset150 bytesautomation/daily-retro.timerasset125 bytesscripts/collect.pyruns8,739 bytes
Read SKILL.md
# Daily retro (experimental)
Part of the Personal Corp framework. Weekly retro answers "what did the week give". Daily retro answers a smaller question every evening: what did my agents do today, and what did they leave half-done. You do not remember twenty sessions in five repos; the logs do.
Experimental means: the shape may change, it is not in the plugin's active skill list, you copy it by hand (see README).
## What it reads
Only local files, nothing leaves the machine:
| Harness | Logs |
|---|---|
| Claude Code (CLI and desktop) | `~/.claude/projects/<project>/<session>.jsonl` |
| Codex | `~/.codex/sessions/YYYY/MM/DD/rollout-*.jsonl` |View the complete source on GitHubart-director
When your agent uses it
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
2,648 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
- Default Output Shape
- Workflow
- Iteration Cluster Contract
- Dagre Rendering Contract
- HTML Preview Rules
- Feedback Loop
- Branch Planning Rules
- Selection Rules
- Privacy And Source Rules
- Validation
Files
SKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesSKILL.mdcore11,571 bytesassets/illustration.pngasset506,844 bytesassets/style-search-map-template.htmlasset11,000 bytes
Read SKILL.md
# Art Director
Use this skill when the work is an art-direction search for a media production workspace.
The skill coordinates this loop:
```text
brief -> references -> generation branches -> HTML preview -> feedback -> next branches -> selected direction
```
For single-image production, use the host repo's image-generation or media-run instructions. For comic pages, albums, storyboards, or platform-specific assets, use the host repo's format-specific playbook when one exists.
## Default Output Shape
View the complete source on GitHubaudit-agent-rules
When your agent uses it
Audits the agent rules in the current folder (AGENTS.md, nested AGENTS.md files) and the skill descriptions the agent sees at start, then reports what to cut, move or rewrite and edits only after the user says yes. Use on «аудит правил», «проверь AGENTS.md», «почему агент не слушается правил», «проверь скиллы».
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
2,804 tokensWhen the skill is activated
Reference documents
1,209 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Что проверяется
- Четыре мерила
- Порядок работы
- Шаблон отчёта
- Границы
- Источники
Scripts executed separately
scripts/scan.py
Files
SKILL.mdcore14,802 bytesreferences/where-lines-go.mddoc6,212 bytesscripts/scan.pyruns18,776 bytes
Read SKILL.md
# Аудит правил агента
Скилл проверяет файлы правил агента в текущей папке и каталог скиллов, который агент видит на старте. Отдаёт отчёт таблицей: что не так и как сделать лучше. Файлы меняет только после «да» человека.
Скилл обычно зовёт человек без опыта в программировании: он ведёт папку с агентом для своей работы. Отчёт пиши простыми словами, на языке человека; термин объясняй один раз через то, что он меняет в работе агента.
## Что проверяется
- `AGENTS.md` в текущей папке и во всех её подпапках. Его читают Claude Code, Codex, Cursor и другие агенты, поэтому аудит строится вокруг него.
- `CLAUDE.md`, `CLAUDE.local.md` и `.claude/rules/` попадают в отчёт одной находкой, если в них свой текст: тогда Claude Code читает одни правила, остальные агенты другие. Разбирать их построчно не нужно.
- Скиллы из `.agents/skills` и `.claude/skills` этой папки (и папок выше до корня git-репозитория), `~/.agents/skills`, `~/.codex/skills`, `~/.claude/skills`.
## Четыре мерила
View the complete source on GitHubavatar
When your agent uses it
Робот агента Personal Corp. Агент делает себе голову робота из набора деталей, хранит её в штабе в stack/avatars.json и кладёт в штаб страницу avatar/robot.html, где робот стоит за партой своего штаба и вокруг видны отделы, без сервера и интернета. На уроке по ссылке входа с экрана урока робот входит в живой класс и горит маячком, пока агент работает. Триггеры /avatar, /avatar <ссылка входа>, сделай себе аватар, покажи своего робота, приди на урок.
What it loads into context
Frontmatter
139 tokensAlways available to the agent
SKILL.md
2,747 tokensWhen the skill is activated
Reference documents
6,320 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Кто я
- 2. Робот уже есть?
- 3. Голова по характеру
- 4. Собрать робота и посмотреть
- 5. Прийти на урок
- 6. Весь урок: маячок и голос
- Набор
Scripts executed separately
avatar.pypc3live.py
Files
SKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesSKILL.mdcore13,045 bytesTHIRD_PARTY_NOTICES.mddoc29,348 bytesavatar.pyruns27,806 bytespc3live.pyruns10,218 bytesrobot.htmlasset1,355,857 bytes
Read SKILL.md
# /avatar: робот агента
Тело робота это харнес. Голову модель делает себе сама: цвет и глаза. Весь робот одного цвета палитры, мелкие детали того же цвета темнее. На теле стикер с логотипом компании модели, на лбу лента с именем модели. Рядом с этим файлом два скрипта и страница: `avatar.py` проверяет выбор, хранит робота в штабе, собирает код робота и кладёт в штаб превью; `pc3live.py` входит в живой класс урока и зажигает маячок; `robot.html` это плеер превью, его копирует `avatar.py`. Нужен Python 3, на Windows команда `python` вместо `python3`. Ниже `A` это путь к `avatar.py`, например `.agents/skills/avatar/avatar.py`, а `L` это путь к `pc3live.py` в той же папке.
Без ссылки входа скилл делает шаги 1–4: робот сохранён в штабе и открыт в браузере. Ссылка входа есть: дальше шаги 5 и 6.
## 1. Кто я
Харнес записан в `stack/harness.md`, строка Харнес. Нет файла: определи сам по таблице.
<!-- харнесы: live/sync.mjs -->
| Харнес | `--harness` |
|---|---|
| Claude Code | `claude-code` |View the complete source on GitHubbenchmark
When your agent uses it
Use when choosing between engines or models for an agent pipeline and the answer must come from measurement on your own data, not from marketing pages: speech recognition for meeting recordings, the model that turns a transcript into notes, the critic model that checks it. Runs every variant in an isolated container, measures time, cost per hour of input (USD and RUB, with price source and date) and quality (WER/CER and course terms for ASR; code checks plus a judge of a different model for LLM steps), writes results.json/csv and one static analytics page. Triggers on "бенчмарк", "сравни движки", "сколько стоит час записи", "какую модель взять для пайплайна", "benchmark the pipeline", "compare ASR engines".
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
1,863 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
- When to use
- Rules
- Steps
- Engines and providers
- Metrics
- Bias checklist (write it into the method note)
- Container
- Files
Scripts executed separately
examples/adapter_example.pyscripts/asr.pyscripts/claude_step.pyscripts/common.pyscripts/llm.pyscripts/report.pyscripts/score.py
Files
SKILL.mdcore7,510 bytesSKILL.mdcore7,510 bytesSKILL.mdcore7,510 bytesSKILL.mdcore7,510 bytesexamples/adapter_example.pyruns5,061 bytesprices.example.jsonasset3,373 bytesscripts/asr.pyruns11,018 bytesscripts/claude_step.pyruns5,933 bytesscripts/common.pyruns2,187 bytesscripts/llm.pyruns4,117 bytesscripts/report.pyruns10,687 bytesscripts/score.pyruns14,919 bytestask.example.jsonasset1,786 bytes
Read SKILL.md
# Benchmark
Measure a pipeline on your own input before you pick an engine. One task file lists the variants; the scripts run them one by one in an isolated container and write numbers you can defend: time, cost per hour of input with a dated price source, quality against a reference.
Shape of a pipeline this skill knows:
`input (recording) → ASR engine → transcript → author model (notes, chapters) → code checks → judge model`
Each arrow is a slot. A variant fills one slot and keeps the rest fixed.
## When to use
- «ElevenLabs, Whisper or a Russian engine: what does an hour of our meetings cost and who makes fewer mistakes»;
- «move the notes step from Claude to GLM: does quality hold»;View the complete source on GitHubcc-analytics
When your agent uses it
Use when user asks for Claude Code usage stats, weekly analytics, project activity summary, or wants to see what projects were worked on. Triggers on "аналитика", "статистика claude", "cc stats", "weekly report", "что делал"
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
1,702 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
- Data Sources
- Output
- Generation Script
- HTML Template
- Bar Chart Generation
- Usage
- Customization
Files
SKILL.mdcore6,946 bytesSKILL.mdcore6,946 bytesSKILL.mdcore6,946 bytesassets/illustration.pngasset472,425 bytes
Read SKILL.md
# Claude Code Analytics
Generate HTML report of Claude Code usage from `~/.claude/history.jsonl`.
## Data Sources
- **History:** `~/.claude/history.jsonl` — prompts with timestamps and project paths
- **Git:** Remote URLs and commit counts per project
## Output
Single HTML file with terminal aesthetic:
- ASCII art header
- Summary stats (projects, prompts, commits, days)View the complete source on GitHubceo-council
When your agent uses it
Use when needing strategic project analysis from multiple independent expert perspectives. Triggers on business decisions, growth strategy, product direction, competitive analysis, or any situation where diverse C-level opinions reduce blind spots
What it loads into context
Frontmatter
48 tokensAlways available to the agent
SKILL.md
1,263 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
- Critical: How to Launch Experts
- Step 1: Scan Project Context
- Step 2: Assemble the Council
- Step 3: Gather Current Data
- Step 4: Generate Expert Prompts
- Step 5: Execute
- Step 6: Synthesize
- Common Mistakes
Files
SKILL.mdcore5,586 bytesSKILL.mdcore5,586 bytesassets/illustration.pngasset466,231 bytes
Read SKILL.md
# CEO Council — Independent Strategic Analysis
Launch parallel sub-agents as isolated C-level experts. Each analyzes the same project data from their perspective. No coordination between experts — isolation produces genuine diversity of opinion. Then synthesize consensus and disagreements.
## Critical: How to Launch Experts
**MUST use the Task tool** with `subagent_type: "general-purpose"` and `model: "opus"`.
```
Task(
subagent_type: "general-purpose",
model: "opus",
prompt: "<expert prompt with data>",
description: "CFO analysis"View the complete source on GitHubclaude-md-writer
When your agent uses it
Use when creating or refactoring CLAUDE.md files - enforces best practices for size, structure, and content organization
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
1,741 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
- Golden Rules
- Memory Hierarchy
- 3-Tier Documentation System
- Structure Template
- Conditional Rules (Path-Specific)
- Workflow: New Project
- Workflow: Refactor Existing
- What Goes Where
- Import Syntax
- CLAUDE.local.md
- Common Mistakes
- Quality Checklist
- Useful Commands
- Sources
Files
SKILL.mdcore6,539 bytesassets/illustration.pngasset599,239 bytes
Read SKILL.md
# CLAUDE.md Writer
Creates and refactors CLAUDE.md files following official Anthropic best practices (2025).
## Golden Rules
| Rule | Why |
|------|-----|
| **CLAUDE.md < 200 lines** | Loads on EVERY request, costs tokens |
| **Rules files < 500 lines each** | Official recommendation per file |
| **Critical rules FIRST** | Top = highest priority |
| **Modular rules → `.claude/rules/`** | Conditional loading, organized |
| **Use `paths:` frontmatter** | Load rules only for matching files |
| **No linting rules** | Use ESLint/Prettier/Biome instead |View the complete source on GitHubclaude-sessions-sync
When your agent uses it
Sync Claude Code session records between two Anthropic accounts in the Claude desktop app on macOS. Use when switching accounts (for example when one hits usage limits) and old sessions disappear from the picker, or to mirror records before/after a switch.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
1,034 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
- Procedure
- Script (edit FIRST/SECOND, app closed)
- Gotchas
Files
SKILL.mdcore4,093 bytesSKILL.mdcore4,093 bytes
Read SKILL.md
# Claude sessions sync (between desktop-app accounts)
How it works (verified 2026-10-01…07, Claude Code 2.1.286, macOS):
- Session records live in `~/Library/Application Support/Claude/claude-code-sessions/<accountUuid>/<orgUuid>/local_*.json`. The second path level is the **organization** UUID; the app lists only the current account+org pair, which is why switching accounts hides the other side's sessions.
- Transcripts live in `~/.claude/projects/` and are shared across all accounts — never touch them. A record points at its transcript through the `cliSessionId` field.
- Active account: `~/Library/Application Support/Claude/config.json` → `lastKnownAccountUuid`. The active org folder is the one holding the freshest record (mtime).
- Account switches may leave empty race folders `<old-account>/<new-org>` — ignore them.
## Procedure
1. The app must be fully closed: `pgrep -f "/Applications/Claude.app/Contents/MacOS"` is empty; otherwise `osascript -e 'quit app "Claude"'` and wait. Copying while the app is alive can be rolled back by its in-memory list cache (`LSS-cached-sessions`) and record rewrites.
2. Identify both working folders: under each account UUID take the subfolder with the most `local_*.json` records (or the freshest one).
3. Run a bidirectional newest-wins sync of `local_*.json` — the script below. A one-way copy leaves drift: sessions you continued on one side go stale on the other.View the complete source on GitHubcorp-doctor
When your agent uses it
Use when a Personal Corp operating loop needs setup, repair, a new department, or task routing: HQ files and agent rules, GitHub issue workflow, corp-* owner map, department repositories, or deciding which repo an issue belongs to. Triggers: "corp doctor", "почини контур", "заведи отдел", "куда положить задачу", "настрой штаб", "проверь операционку". Replaces corp-init, corp-new and task-routing.
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
1,804 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
- Phase 0 — Меню
- 1. Диагностика
- 2. Починить
- 3. Новый отдел
- 4. Маршрут задачи
- 5. Собрать с нуля
- Границы
- Условия остановки
- Связанные скиллы
Files
SKILL.mdcore10,629 bytes
Read SKILL.md
# Corp Doctor
Один вход во все операции над контуром Personal Corp: диагностика, ремонт, новый отдел, маршрутизация задачи.
Скилл не собирает систему вслепую. Сначала он выясняет, что уже есть, потом чинит недостающее.
## Phase 0 — Меню
Первое действие: показать меню и дождаться явного выбора. До ответа человека ничего не читать и не создавать.
```text
Что делаем?
1. Диагностика — посмотреть контур и показать расхождения без правокView the complete source on GitHubcorp-new
When your agent uses it
Создаёт новый отдел штаба: папку `corp-<слово>` рядом со штабом, файл правил, папку скиллов, папку задач `tasks/` и связь со штабом в правилах в обе стороны. Если штаба ещё нет, сначала ставит его из agent-starter. Применять по /corp-new, «создай отдел», «новый отдел», «заведи отдел <домен>».
What it loads into context
Frontmatter
110 tokensAlways available to the agent
SKILL.md
4,068 tokensWhen the skill is activated
Reference documents
3,855 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Найти штаб
- 2. Штаба нет: поставить из agent-starter
- 3. Имя отдела
- 4. Каркас отдела
- 5. Репозиторий на GitHub: только по желанию
- 6. Связь со штабом в правилах
- 7. Проверка и отчёт
- 8. Скилл отдела: как добавить
Scripts executed separately
templates/corp-it/skills/device-inventory/scripts/snapshot-linux.shtemplates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh
Files
SKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesSKILL.mdcore18,719 bytesassets/illustration-en.svgasset6,080 bytesassets/illustration.svgasset6,755 bytestemplates/common/CONTEXT.mddoc602 bytestemplates/common/gitignoreasset472 bytestemplates/corp-it/AGENTS.mddoc5,887 bytestemplates/corp-it/CONTEXT.mddoc3,241 bytestemplates/corp-it/agents/engineer.mddoc3,200 bytestemplates/corp-it/devices/README.mddoc2,339 bytestemplates/corp-it/skills/device-inventory/SKILL.md.tmplasset5,060 bytestemplates/corp-it/skills/device-inventory/scripts/snapshot-linux.shruns7,401 bytestemplates/corp-it/skills/device-inventory/scripts/snapshot-macos.shruns7,233 bytestemplates/corp-it/skills/device-inventory/template.mddoc3,049 bytestemplates/corp-it/skills/machine-access/SKILL.md.tmplasset4,432 bytestemplates/corp-research/AGENTS.mddoc3,370 bytestemplates/corp-research/INDEX.mddoc124 bytestemplates/corp-research/skills/corp-research/SKILL.md.tmplasset1,409 bytestemplates/corp-research/tags.mddoc0 bytes
Read SKILL.md
# corp-new: новый отдел штаба
Штаб это главная папка работы с агентом: файл правил, `me.md`, карта отделов. Отдел это соседняя папка штаба со своим файлом правил, словарём, скиллами и задачами, например `corp-sales` или `corp-learn`. Отдел знает свой штаб, штаб знает свои отделы: связь записана в правилах с обеих сторон.
Скилл идёт по шагам и отвечает таблицей ✓/✗. Правила отдела за человека он не пишет: ставит каркас с пустыми местами, их человек заполняет сам или вместе с агентом через /mp-grill-me. Исключение — готовые отделы из `templates/` (шаг 3): их правила уже заполнены. Чужие файлы не трогает, незакоммиченную работу не выбрасывает. GitHub не нужен: отдел живёт в локальной папке.
Команды даны для macOS и Linux (zsh, bash). На Windows агент делает то же средствами PowerShell.
## 1. Найти штаб
Штаб узнаётся так же, как в скилле `hq` (шаг 1): папка с `me.md` или `stack/harness.md`. Где искать, по порядку:
```sh
for d in . ./hq .. ../hq ~/Documents/GitHub/hq ~/hq; doView the complete source on GitHubdaily
When your agent uses it
Дневной фокус штаба — что делать сегодня по открытым задачам всех отделов. Применять по «что сегодня» и в утреннем запуске по расписанию.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
1,257 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
- Шаги
- Файл дня
- Ответ в чат
- Границы
Files
SKILL.mdcore6,570 bytes
Read SKILL.md
# Daily
**Отдел** — единица штаба со своими задачами: папка или репозиторий, на который ссылается файл правил штаба. Если в файле правил штаба они названы проектами, это те же отделы.
Каждый запуск читает задачи заново из источников. Файл дня — срез со ссылками; задача живёт в своём источнике.
## Шаги
1. Определи сегодняшнюю дату из системного времени.
2. Прочитай файл правил штаба (`CLAUDE.md` или `AGENTS.md` в корне штаба). Найди:
- строки, где лежат задачи отделов, например `Обучение: ../corp-learn. Задачи отдела лежат в ../corp-learn/tasks/.` или `Задачи всех отделов — GitHub Project 3, owner my-handle.`;
- раздел «Правила приоритета»: что важнее, сколько дел брать на день, какие колонки или лейблы значат «ждёт решения человека».
3. Строк о том, где лежат задачи, нет: остановись, скажи об этом и предложи дописать по строке на отдел в формате выше. Дальше иди только по путям, которые записаны в файле правил.
4. Прочитай задачи каждого отдела из его источника:View the complete source on GitHubfable-ruki-agenty
When your agent uses it
Фейбл руки-агенты — ручной режим оркестрации, где Fable не пишет код, а пишет спеки в тела GH issues и раздаёт готовые задачи рукам: кодинг, код-ревью, gh-операции, CLI-механика, DoD-верификация и укладка файлов — Codex; разведка, чтение и скауты — Grok-воркеры через Orca. Вызывается пользователем явно, не моделью.
What it loads into context
Frontmatter
136 tokensAlways available to the agent
SKILL.md
7,176 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
- Зачем этот режим
- Жёсткие запреты
- Codex-руки (кодинг и ревью)
- Orca-руки (внешние воркеры-терминалы)
- Конвейер
- Дисциплина общения
- Происхождение внешних правил
Files
SKILL.mdcore37,852 bytesSKILL.mdcore37,852 bytesSKILL.mdcore37,852 bytesSKILL.mdcore37,852 bytesassets/illustration.pngasset1,405,344 bytes
Read SKILL.md
# Фейбл руки-агенты
## Зачем этот режим
Токены Fable — самый дорогой ресурс сессии (лимиты урезаны). Поэтому Fable делает только то, что не может сделать рука дешевле: **думает, резолвит развилки и пишет спеки**. Всё остальное делают руки: **кодинг, код-ревью, gh-операции, CLI-механика, DoD-верификация и укладка файлов — Codex** (`gpt-5.5`, плагин `codex`, § Codex-руки); **разведка, чтение и скауты — Grok-воркеры через Orca** (§ Orca-руки). Каждый tool call, который могла сделать рука, — сожжённый лимит.
Sonnet и Haiku не использовать ни для каких ролей (решение founder 04.07.2026).
Граница проходит по суждению, а не по стоимости токена: субагентам уходят **глаза и руки**, но никогда — **голова**. Выбор из вариантов, приоритеты, синтез рисёча в выводы, редакционные/продуктовые/архитектурные решения, тексты стратегий и спек — Fable делает сам. Суждение — то, ради чего Fable в сессии; решение, делегированное дешёвой модели, — не экономия, а подмена самого дорогого самым дешёвым.
## Жёсткие запреты
1. **Не писать код и не править файлы репо. Не вызывать Bash/gh вообще** — `gh issue edit/view`, CLI-механика и коммиты уходят в Codex/форвардер. Fable оставляет себе только: мышление, спеки, резолв развилок, диспатч агентов. Codex-задача диспатчится через Agent tool (`codex:codex-rescue`); Bash у Fable не появляется нигде.
2. **Не читать кодовую базу самому.** Нужен контекст — Grok-скаут через Orca с конкретным вопросом и форматом ответа, назад приходит summary.View the complete source on GitHubgh-issues
When your agent uses it
Use when creating, searching, updating, or managing GitHub issues via CLI. Triggers: "issue", "create issue", "gh issue", "task tracking", "context", "handoff", "resume task", "session context", "save progress", "active tasks", "in-progress", "my tasks", "open issues". Covers: gh commands, bulk operations, JSON/jq, search filters, issue-to-PR workflow, AI session context storage, task workflow with labels.
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
2,026 tokensWhen the skill is activated
Reference documents
559 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Table of Contents
- Quick Reference
- JSON Output Patterns
- Advanced Search Filters
- Bulk Operations
- Issue to PR Workflow
- Milestones via API
- AI Session Context
- Task Workflow
- Examples
- Common Mistakes
Files
SKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesSKILL.mdcore7,221 bytesassets/illustration.pngasset499,874 bytesreferences/context-template.mddoc2,194 bytes
Read SKILL.md
# GitHub Issues CLI
Efficient GitHub Issues management via `gh` CLI with AI session context storage.
## Table of Contents
1. [Quick Reference](#quick-reference)
2. [JSON Output](#json-output-patterns)
3. [Search Filters](#advanced-search-filters)
4. [Bulk Operations](#bulk-operations)
5. [Issue to PR Workflow](#issue-to-pr-workflow)
6. [Milestones](#milestones-via-api)
7. [AI Session Context](#ai-session-context)
8. [Task Workflow](#task-workflow)View the complete source on GitHubgrill-me
When your agent uses it
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
122 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
Files
SKILL.mdcore635 bytes
Read SKILL.md
Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.
Ask the questions one at a time.
If a question can be answered by exploring the codebase, explore the codebase instead.View the complete source on GitHubharness
When your agent uses it
Режим управления агентом одной шапкой в начале сообщения — роль (оркестратор, исполнитель, критик), модель субагентов, эффорт и лимит субагентов. Триггеры — "/harness", шапка с полями "режим:", "модель:", "эффорт:", "макс:". Применяется до конца сессии или до новой шапки.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
739 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
- Поля
- Как применять
Files
SKILL.mdcore4,537 bytes
Read SKILL.md
# /harness — режим работы агента
Человек задаёт, как агент работает в этой сессии, шапкой из четырёх строк. Модель каждый ставит свою: ту, что есть в его подписке и харнесе.
```
/harness
режим: оркестратор, критик
модель: <модель>
эффорт: низкий
макс: 3 субагента
```
Любую строку можно пропустить — тогда действует значение по умолчанию.
View the complete source on GitHubhtml-draft
When your agent uses it
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on "/html-draft", "сделай blueprint", "технический чертёж", "архитектурная схема", "инженерная схема", "blueprint diagram", "engineering blueprint", "technical spec sheet", "architecture diagram", "system flow diagram".
What it loads into context
Frontmatter
134 tokensAlways available to the agent
SKILL.md
3,161 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
- Design philosophy
- Visual rules
- Hard requirements
- Output template
- Reusable component snippets
- D3 patterns
- Composition guide
- Quality bar
- When input is incomplete
- Source
Files
SKILL.mdcore11,666 bytesSKILL.mdcore11,666 bytesSKILL.mdcore11,666 bytesSKILL.mdcore11,666 bytesassets/illustration.pngasset470,779 bytes
Read SKILL.md
# html-draft — Flat Engineering Blueprint Diagrams
Generate one HTML page that renders a technical diagram in a strict flat-blueprint aesthetic — the look of a printed engineering specification sheet, not a marketing landing.
**Stack:** Tailwind v4 via `@tailwindcss/browser` CDN for layout + utilities, D3 v7 via jsDelivr CDN for SVG-based diagrams (nodes, connectors, layouts, animations).
**Use this when** the user wants an architecture diagram, system flow, technical spec sheet, or component map as a standalone HTML artifact (suitable for slides, reports, exports).
**Don't use this for:**
- Inline schemas inside markdown documents — use a mermaid renderer instead
- Newspaper / reading-first single-column pages with monospace ink-on-cream feel
- Multi-section interactive explainers with pill navigation
## Design philosophyView the complete source on GitHubidea
When your agent uses it
Use when capturing ONE new idea the user voices and wants recorded — "save this idea", "I have an idea", "log this idea", "/idea", "idea: ...". Creates a provenance-tracked folder (one folder per idea) in your ideas repo, dedups against an index, optionally mirrors to a GitHub Project view filtered by label:idea. NOT for mining ideas out of transcripts/meetings (use a dedicated extraction skill) and NOT for dated work tasks (use an issue tracker / the manager skill). Triggers also in Russian: «запиши идею», «у меня идея», «зафиксируй идею».
What it loads into context
Frontmatter
151 tokensAlways available to the agent
SKILL.md
2,604 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
- What this skill is NOT for
- Setup
- One question — max
- Status enum (in `idea.md` frontmatter)
- Provenance formats (rows in `sources.md`)
- Steps
- Template files
- INDEX.md regeneration
- Project mirror (optional — only if `mirror_enabled: true`)
- Failure without the skill → rule
- Red flags — stop
- Cross-references
Files
SKILL.mdcore10,343 bytesSKILL.mdcore10,343 bytesSKILL.mdcore10,343 bytesSKILL.mdcore10,343 bytesSKILL.mdcore10,343 bytesSKILL.mdcore10,343 bytesSKILL.mdcore10,343 bytesSKILL.mdcore10,343 bytes
Read SKILL.md
# Idea — fast capture of a single idea
Part of the Personal Corp framework — running a one-person business through AI agents.
One pipeline: your voice → a provenance-tracked folder in your ideas repo → (optional) an issue mirror on a GitHub Project view. The folder is the source of truth; everything else is a pointer to it.
This skill is **self-contained** — it inlines the folder structure, status enum, and provenance formats below. You don't need any external canon file.
## What this skill is NOT for
- **Mining ideas out of a transcript / meeting / thread** — that's bulk extraction from a source. Use a separate extraction skill for that. This skill captures ONE idea the user is voicing right now.
- **A dated work task with a deadline** — use an issue tracker / the `manager` skill. Ideas have no deadline; they're seeds.
## SetupView the complete source on GitHubit-ram-doctor
When your agent uses it
Process tails that hold memory for nothing: finds them and, on the owner's word, kills them. Use on "slow", "swap", "low memory", "kill the tails", "clean up memory", "ram doctor", and after closing heavy apps.
What it loads into context
Frontmatter
65 tokensAlways available to the agent
SKILL.md
1,184 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
- When memory is short
- Procedure
- Off limits
Scripts executed separately
scripts/tails-linux.shscripts/tails-macos.sh
Files
SKILL.mdcore4,483 bytesSKILL.mdcore4,483 bytesSKILL.mdcore4,483 bytesSKILL.mdcore4,483 bytesSKILL.mdcore4,483 bytesSKILL.mdcore4,483 bytesscripts/tails-linux.shruns5,871 bytesscripts/tails-macos.shruns12,758 bytes
Read SKILL.md
# it-ram-doctor
The snapshot only reads; step 4 kills, and only on the owner's word.
## When memory is short
"13 of 16 GB used" and the swap size do not show load: macOS keeps memory busy with cache and compression, and swap does not shrink until a reboot. Memory is short when any of these holds:
- pressure: `sysctl kern.memorystatus_vm_pressure_level` is 4 or stays at 2 for long ([threshold](https://github.com/anthropics/claude-code/issues/73834): on Apple silicon 2 appears under ordinary compression); `memory_pressure | tail -1` shows less than 25–30% free;
- `Swapouts` in `vm_stat` grow between two readings a minute apart;
- swap grows three readings in a row.
No signs: clean only on a direct request. Measure a process by `top -o mem` or `footprint`; `ps` understates the compressed part.
View the complete source on GitHubmake-3d
When your agent uses it
Делает 3D-модель для сцены (предмет, комната, робот, офис) через несколько вариантов: каждый вариант строит свой исполнитель в копии сцены, все сдают одинаковые листы, человек выбирает по картинкам, выбранный вариант переезжает в канон на настоящих данных. Применять по /make-3d, «сделай варианты модели», «как это может выглядеть в 3D», «нарисуй варианты предмета».
What it loads into context
Frontmatter
116 tokensAlways available to the agent
SKILL.md
1,248 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
- Шаги
- Данные человека на сцене
Files
SKILL.mdcore7,293 bytesSKILL.mdcore7,293 bytes
Read SKILL.md
# make-3d: 3D-модель через варианты
Скилл про форму работы, а не про решение. На входе уже известно, какая модель нужна, какие у неё состояния и 2–3 кандидата формы. Если это ещё не решено, сначала разбери с человеком через `/mp-grill-me` и возвращайся сюда.
**Вариант** — одна форма модели, построенная целиком одним исполнителем. **Лист** — снимок варианта по общему шаблону. **Канон** — исходник сцены, который видит человек; до выбора его не трогает никто.
## Шаги
1. **Сцена.** Найди исходник сцены, команду сборки, где рисуются объекты, откуда берутся данные и адрес живой страницы. Сними, как сцена выглядит сейчас, и покажи снимок в чате картинкой. Готово: знаешь файлы объектов, команду сборки и живой адрес. Правила сцены (что где стоит, что нельзя закрывать, стиль) читай в её каноне (`DESIGN.md`, `CONTEXT.md`, README) и неси в бриф.
2. **Демо-данные.** Один набор на все варианты, где встречается каждое состояние модели и крайние случаи: ноль, один, много, каждый цвет. Готово: по набору можно проверить любое правило состояния.
3. **Копии сцены.** У каждого варианта своя папка-копия вне канона (`node_modules` симлинком на оригинал), свой порт и свой кеш сборщика. Папку для листов заведи постоянную, в репозитории человека (например `artifacts/<дата>-<модель>/<вариант>/`), чтобы листы пережили перезапуск сессии.
View the complete source on GitHubmake-landing
When your agent uses it
Создаёт несколько вариантов дизайна 2D-поверхности (лендинг, герой, обложка, слайды): свой визуальный референс и автор на вариант, полный design.md с UTC/SHA-256 до кода, проверка в браузере, галерея, картинки в чат, выбор человека и второй раунд смешения победителей. Применять по /make-landing, «варианты дизайна», «несколько вариантов лендинга на выбор», «редизайн».
What it loads into context
Frontmatter
117 tokensAlways available to the agent
SKILL.md
2,278 tokensWhen the skill is activated
Reference documents
1,162 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Общий бриф
- 2. Референсы и матрица направлений
- 3. Папки и исполнители
- 4. Полный design.md до кода
- 5. Реализация и проверка
- 6. Галерея и показ
- 7. Выбор, второй раунд и канон
Scripts executed separately
scripts/freeze_concept.py
Files
SKILL.mdcore14,585 bytesSKILL.mdcore14,585 bytesSKILL.mdcore14,585 bytesreferences/author.mddoc2,557 bytesreferences/design-template.mddoc4,677 bytesscripts/freeze_concept.pyruns2,444 bytes
Read SKILL.md
# make-landing: дизайн через варианты
**Вариант** — самостоятельное направление с визуальным референсом, полным контрактом и рабочим preview. **Канон** — исходная поверхность проекта, куда после выбора переезжает результат. До выбора авторы работают в своих папках.
Подходит для лендинга, героя, обложки и слайдов. Размеры и формат результата берутся из задачи. Если направление уже выбрано, выполняй обычную реализацию по его контракту.
## 1. Общий бриф
Найди исходник, текущую страницу, команду запуска и правила проекта. При редизайне сними исходную страницу и покажи картинкой в чате. Сохрани `brief.md`: аудитория, задача поверхности, проверенные тексты/оффер/CTA, обязательные секции, доступные ассеты, формат результата, ограничения и критерии готовности. При существенном пробеле проверь публичные первоисточники; приватный контекст остаётся локально. Источники фактов у всех авторов общие.
Число вариантов N возьми из запроса. Если его нет, уточни; предложи 6–10 для широкого поиска. Решение человека определяет N. При лимите исполнителей запускай волнами с полным scope до готового preview.
При запрете менять текст сохрани текстовый канон и список разрешённых фактических корректировок. Каждый автор использует его дословно. Композицию и порядок можно менять; полноту исходных смысловых секций проверяй отдельно. Дизайнерские заметки остаются в документах процесса.
View the complete source on GitHubmanager
When your agent uses it
Связывает сессию с задачами штаба в файлах tasks/ или в GitHub issues. Запись — «синкни сессию»: итог сессии в задачу и файл дня. Чтение — «что по <задаче>»: текущее состояние задачи.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
2,409 tokensWhen the skill is activated
Reference documents
17,224 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Развилка: где лежат задачи
- Уровень 1: задачи в файлах
- Уровень 2: задачи в GitHub issues
- Настройка: Manager Config
- Железные инварианты
Files
SKILL.mdcore12,618 bytesagents/openai.yamlasset337 bytesassets/illustration.pngasset487,308 bytesreferences/crm.mddoc1,755 bytesreferences/mistakes.mddoc9,623 bytesreferences/modes.mddoc13,000 bytesreferences/output.mddoc6,200 bytesreferences/parent-epic.mddoc13,408 bytesreferences/read-mode.mddoc7,546 bytesreferences/search.mddoc7,014 bytesreferences/templates.mddoc7,258 bytesreferences/titles.mddoc6,176 bytesreferences/w-labels.mddoc5,154 bytesreferences/write-mode.mddoc16,137 bytes
Read SKILL.md
# Manager
Два режима: **запись** переносит итог сессии в задачу, **чтение** отвечает, что с задачей сейчас.
## Развилка: где лежат задачи
Сначала прочитай файл правил штаба и файл правил отдела (`AGENTS.md` или `CLAUDE.md`).
- Задачи лежат в файлах (`tasks/`): работай по разделу «Уровень 1», остальной документ не нужен.
- Задачи в GitHub issues: работай с раздела «Уровень 2: задачи в GitHub issues».
- Строки о том, где лежат задачи, нет: предложи её дописать, например «Задачи отдела лежат в `tasks/`», и спроси человека до первой записи.
## Уровень 1: задачи в файлах
View the complete source on GitHubmeeting-copilot
When your agent uses it
Use when preparing for, running, or closing a live meeting with an AI assistant dashboard. Triggers on "meeting copilot", "live copilot", "prepare for a call", "update copilot", "close the session", or requests to turn transcript chunks into meeting questions, topic maps, decisions, and follow-ups.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
1,283 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
- Modes
- CREATE
- UPDATE
- Question Design
- Topic Map
- CLOSE
- Privacy Rules
- Quality Bar
Files
SKILL.mdcore5,605 bytesSKILL.mdcore5,605 bytesSKILL.mdcore5,605 bytesSKILL.mdcore5,605 bytesSKILL.mdcore5,605 bytesassets/illustration.pngasset466,622 bytes
Read SKILL.md
# Meeting Copilot
Create and maintain a local HTML dashboard for a live meeting. The dashboard gives the user a second-screen view of context, questions, topic progress, decisions, risks, and follow-ups while the call is happening.
This skill is designed for private workspaces. Do not publish raw transcripts, client names, personal notes, or generated meeting artifacts unless the user explicitly asks for a sanitized export.
## Modes
Use one of three modes:
| Mode | When | Output |
| --- | --- | --- |
| CREATE | Before the meeting | A local dashboard app with prepared context and questions |
| UPDATE | During the meeting | Updated questions, topics, decisions, risks, and follow-ups from transcript chunks |View the complete source on GitHubreadme-generator
When your agent uses it
Use when creating or rewriting README.md for projects. Triggers on "write README", "create README", "update README". Creates human-focused documentation with proper structure.
What it loads into context
Frontmatter
41 tokensAlways available to the agent
SKILL.md
1,138 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
- When to Use
- Process
- Step 1: Research
- Step 2: Analyze Project
- Step 3: Identify Project Type
- Step 4: README Structure
- Writing Style
- Related Skills Section
- Quick Reference
- Common Mistakes
- Example Structure (Full-stack App)
Files
SKILL.mdcore4,843 bytesSKILL.mdcore4,843 bytesassets/illustration.pngasset466,648 bytes
Read SKILL.md
# README Generator
Generate human-focused README files following current best practices.
**Core principle:** README is for humans, not agents. Research → Analyze → Write.
**Model recommendation:** Use `Task` tool with `model: haiku` for README generation — faster and cheaper for documentation tasks.
## When to Use
- Creating README for new project
- Rewriting outdated README
- User asks "write/create/update README"
View the complete source on GitHubretro
When your agent uses it
Ретро недели для штаба. Читает задачи всех отделов, собирает что сделано, что застряло и что повторяется, пишет tasks/retro-<ГГГГ>-W<NN>.md в штабе. Применять по «ретро», «что было за неделю», «итоги недели», «retro».
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
862 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
- Правило данных
- Шаги
- Файл ретро
- Ответ в чат
- Запрещено
Files
SKILL.mdcore4,594 bytes
Read SKILL.md
# Retro
Запускается из штаба. Смотрит назад на неделю по задачам всех отделов.
## Правило данных
Каждый запуск читает файлы задач заново. Своей копии задач не держи и неделю из памяти чата не восстанавливай. Файл ретро это срез со ссылками, источник правды остаётся в задачах отделов.
## Шаги
1. Определи текущую ISO-неделю и её даты из системного времени. Если человек назвал другую неделю, возьми её.
2. Прочитай файл правил штаба (`CLAUDE.md` или `AGENTS.md`). Найди строки, где лежат задачи отделов, например:
`Обучение: ../corp-learn. Задачи отдела лежат в ../corp-learn/tasks/.`
3. Если таких строк нет, остановись. Скажи, что в правилах штаба не указано, где лежат задачи отделов, и предложи дописать по строке на отдел в формате выше. Пути не угадывай.View the complete source on GitHubsafe-public-release
When your agent uses it
Use when publishing, open-sourcing, exporting, sanitizing, or moving code, agent skills, prompts, templates, fixtures, datasets, workshop assets, or other artifacts from a private repository, vendor/runtime environment, or mixed working directory into a public repository or registry. Builds a provenance inventory, license/security review, explicit allowlist, clean staging package, approval dry run, and fresh public clone/install smoke. Triggers on "open source this", "publish these skills", "make this repo public", "export and sanitize", "подготовь публичный релиз", "выложи скиллы", "опенсорсни", "санитизируй и опубликуй". NOT for ordinary upstream bugfix PRs, vulnerability disclosure, or creating a corp-* department.
What it loads into context
Frontmatter
189 tokensAlways available to the agent
SKILL.md
2,906 tokensWhen the skill is activated
Reference documents
1,055 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Hard safety boundary
- What this skill is for
- What this skill is NOT for
- Setup
- Owner issue tree
- Status model
- Step 1 — Capture the release intent
- Step 2 — Inventory before copying
- Step 3 — Classify every file
- Step 4 — Provenance gate
- Step 5 — License gate
- Step 6 — Security and privacy gate
- Step 7 — Build an explicit allowlist
- Step 8 — Documentation gate
- Step 9 — Release dry run
- Step 10 — Publish from the clean package
- Step 11 — Verify the public boundary
- Step 12 — Record evidence and maintenance
- Failure without the skill → rule
- Final response
Files
SKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesSKILL.mdcore13,580 bytesreferences/release-checklist.mddoc4,815 bytesreferences/release-manifest.example.yamlasset1,900 bytes
Read SKILL.md
# Safe Public Release
Turn a private, vendor-provided, runtime-generated, or mixed artifact into a public package without leaking secrets, private state, or material that cannot be redistributed.
One pipeline:
`intent → owner issue tree → inventory → provenance → license → security/privacy → allowlist → clean package → approval → publish → fresh public verification → maintenance`
The skill is **allowlist-first**. Never copy a whole runtime/private directory and hope denylist cleanup finds everything.
## Hard safety boundary
Publishing is an outward mutation. Before creating a public repository, changing visibility, pushing a release, or publishing to a registry:
View the complete source on GitHubsdlc-milestones
When your agent uses it
Вехи разработки по плейбуку Anthropic «AI-native SDLC» поверх оркестрации агентов — шесть стадий (Plan, Design, Build, Test, Deploy, Maintain), на каждой коммит артефакта (intent.md, spec.md, plan.md, дифф с выводом проверки, PR с ревью, инцидент) и ворота, кто его принимает. Применять при старте фичи или изменения кода, перед наймом исполнителя, перед PR и вливанием, при инциденте, по «зафиксируй веху», «на какой стадии задача», «intent.md», «spec.md», «plan.md», /sdlc-milestones.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
3,137 tokensWhen the skill is activated
Reference documents
10,798 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Роли
- Где лежат артефакты
- Шесть вех
- Фиксация вехи
- В оркестрации
- Как понять, что работает
Scripts executed separately
scripts/milestones.py
Files
../fable-ruki-agenty/SKILL.mddoc37,852 bytes../grill-me/SKILL.mddoc635 bytes../harness/SKILL.mddoc4,537 bytes../manager/SKILL.mddoc12,618 bytesSKILL.mdcore15,981 bytesSKILL.mdcore15,981 bytesscripts/milestones.pyruns4,503 bytestemplates/intent.mddoc578 bytestemplates/plan.mddoc480 bytestemplates/spec.mddoc579 bytes
Read SKILL.md
# Вехи AI-native SDLC
Источник: [The AI-Native SDLC Playbook](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6aba736348bdf4f08183f463_AI%20Native%20SDLC%20Playbook_designv2%20(1).pdf), Louis Claxton, Anthropic. Ниже пересказ, приложенный к работе с агентами; за формулировками и примерами идите в оригинал.
Скилл не говорит, как нанимать агентов: это делает ваш режим оркестрации (например, [harness](../harness/SKILL.md) или [fable-ruki-agenty](../fable-ruki-agenty/SKILL.md)). Он говорит, какой артефакт должен лечь в git до перехода к следующей стадии.
Главная мысль плейбука: каждая стадия кончается коммитом артефакта, который читает следующая стадия; цепочка коммитов и есть журнал аудита — кто попросил, что сделал агент, кто одобрил. Внимание человека стоит на воротах: он принимает артефакт, подготовленный агентом, и не начинает стадию с нуля.
## Роли
- **Владелец задачи** — человек, который ставит задачу и принимает ворота 1, 2 и 5 (вливание и прод).
- **Планировщик-лид** (вехи 1–3) — агент, который пишет intent.md, spec.md и plan.md, носит их владельцу на принятие, нанимает исполнителя только после закоммиченного plan.md и сверяет вехи скриптом. Отдельного агента нет — эту роль берёт оркестратор сессии или встроенный агент планирования харнеса (в Claude Code — `Plan`).
- **Исполнитель** — агент в своём worktree, работает по plan.md.
- **Ревьюер** (вехи 4–5) — агент, который не писал этот код: сверяет дифф с plan.md, требует вывод проверки в PR и порядок «падающий тест, потом починка», ставит одобрение, после которого PR видит владелец.View the complete source on GitHubtg-bot-ops
When your agent uses it
Use when operating, debugging, deploying, or monitoring a Telegram bot or Telegram-to-agent gateway. Triggers on "telegram bot down", "bot not responding", "debug bot", "check webhook", "polling vs webhook", "restart bot", "deploy bot", "bot logs", "agent gateway", "Telegram Bot API error", "send test message", "бот не отвечает", "проверь бота", "логи бота", "перезапусти бота". Covers health checks, logs, webhook/polling diagnostics, environment validation, safe restart/deploy checklists, Bot API smoke tests, forum topic delivery, privacy mode, gateway routing, and incident notes.
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
1,476 tokensWhen the skill is activated
Reference documents
698 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Public Safety
- Intake
- Diagnostic Flow
- Telegram-To-Agent Gateways
- Bot API vs Telethon / MTProto
- Webhook And Polling Checks
- Forum Topics And Privacy
- Restart / Deploy Gate
- Output Format
- Anti-Patterns
Files
SKILL.mdcore6,415 bytesSKILL.mdcore6,415 bytesSKILL.mdcore6,415 bytesassets/illustration.pngasset549,586 bytesreferences/hermes-gateway.mddoc3,112 bytes
Read SKILL.md
# Telegram Bot Ops
Use this skill when the real question is whether a Telegram bot is receiving
updates, processing them in the intended runtime, and sending visible responses
to the right chat, user, or forum topic.
## Public Safety
- Default to read-only diagnostics.
- Do not print tokens, `.env` values, connection strings, raw logs, private DMs,
payment payloads, session files, or full user records.
- Use placeholders in notes and examples: `<TELEGRAM_BOT_TOKEN>`,
`<TELEGRAM_USER_ID>`, `<CHAT_ID>`, `<TOPIC_ID>`, `<WEBHOOK_URL>`.
- Do not send Telegram messages, restart production services, change webhooks,View the complete source on GitHubto-issues
When your agent uses it
Break a plan, spec, or PRD into independently-grabbable task files using tracer-bullet vertical slices.
What it loads into context
Frontmatter
38 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
- Process
- What to build
- Acceptance criteria
- Depends on
Files
SKILL.mdcore3,159 bytesSKILL.mdcore3,159 bytes
Read SKILL.md
# To Issues
Break a plan into independently-grabbable task files using vertical slices (tracer bullets).
## Process
### 1. Gather context
Work from whatever is already in the conversation context. If `PRD.md` exists in the project folder root, read it in full. If the user points at another spec file, read that instead.
### 2. Explore the codebase (optional)
If you have not already explored the codebase, do so to understand the current state of the code. Task titles and descriptions should use the project's domain glossary vocabulary, and respect ADRs in the area you're touching.
View the complete source on GitHubto-prd
When your agent uses it
Turn the current conversation into a PRD file in the project folder — no interview, just synthesis of what you've already discussed.
What it loads into context
Frontmatter
40 tokensAlways available to the agent
SKILL.md
603 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
- Process
- Problem Statement
- Solution
- User Stories
- Implementation Decisions
- Testing Decisions
- Out of Scope
- Further Notes
Files
SKILL.mdcore2,882 bytes
Read SKILL.md
This skill takes the current conversation context and codebase understanding and produces a PRD. Do NOT interview the user — just synthesize what you already know.
## Process
1. Explore the repo to understand the current state of the codebase, if you haven't already. Use the project's domain glossary vocabulary throughout the PRD, and respect any ADRs in the area you're touching.
2. Sketch out the seams at which you're going to test the feature. Existing seams should be preferred to new ones. Use the highest seam possible. If new seams are needed, propose them at the highest point you can. The fewer seams across the codebase, the better - the ideal number is one.
Check with the user that these seams match their expectations.
3. Write the PRD using the template below, then save it as `PRD.md` in the root of the project folder (the folder you are working in for this demo or feature).
<prd-template>
View the complete source on GitHubweekly-planning
When your agent uses it
Use when the user is transitioning from a completed retro into a weekly plan, choosing weekly outcomes, scheduling a full ISO week, or asking for "план на неделю", "weekly planning", priorities, capacity, or outcomes.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
2,235 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
- Overview
- When to Use
- Iron Rule: Planning Is Not Execution
- Process
- Red Flags — STOP
- Common Mistakes
- Integration with weekly-retro
- Setup
- Quick Reference
Scripts executed separately
scripts/living_week.py
Files
SKILL.mdcore9,585 bytesSKILL.mdcore9,585 bytesSKILL.mdcore9,585 bytesSKILL.mdcore9,585 bytesSKILL.mdcore9,585 bytesSKILL.mdcore9,585 bytesassets/illustration.pngasset554,786 bytesassets/living-week-plan.htmlasset21,549 bytesscripts/living_week.pyruns3,746 bytes
Read SKILL.md
# Weekly Planning
## Overview
Turn retro findings + existing backlog into a prioritized week with clear outcomes, issues in correct repos, and delegation matrix (founder vs agent).
## When to Use
- After weekly retro is complete
- Monday/Tuesday when planning the week
- When user says "план на неделю", "приоритизация", "что делаем"
## Iron Rule: Planning Is Not Execution
View the complete source on GitHubweekly-retro
When your agent uses it
Use when the user is closing an ISO week, reviewing planned outcomes against evidence, interviewing work Areas, resolving unfinished commitments, or asking for "ретро", "weekly retro", "week review", or lessons from the week.
What it loads into context
Frontmatter
53 tokensAlways available to the agent
SKILL.md
5,592 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
- Setup
- Two modes — never mix
- Iron Rules
- Phase 1: Gather Data (before interview, automatic)
- Phase 1.5: Outcomes scorecard (planned vs actual) — REQUIRED before Phase 2
- Phase 2: Interview (core of retro)
- Phase 3: Advisory analysis (optional)
- Phase 4: Compile summary
- Phase 5: Create retro backlog
- Phase 5.5: Triage to zero — every open WNN item gets a terminal decision
- Phase 6: Canonical updates + Wrap-up
- Red Flags — STOP
- Common Rationalizations
Files
SKILL.mdcore22,089 bytesSKILL.mdcore22,089 bytesSKILL.mdcore22,089 bytesSKILL.mdcore22,089 bytesSKILL.mdcore22,089 bytesSKILL.mdcore22,089 bytesassets/illustration.pngasset444,563 bytes
Read SKILL.md
# Weekly Retro
Part of the Personal Corp framework — running a one-person business through AI agents.
Structured weekly retrospective. Gather facts from code and project management tools, interview the founder, capture findings into issues and canonical files.
## Setup
Before first use, define these in your project's `CLAUDE.md`:
```markdown
## Weekly Retro Config
### Repos to scanView the complete source on GitHubdaily
When your agent uses it
Use when the user asks "что сегодня", "задачи на сегодня", "план на день", or wants the current department's living weekly plan refreshed from task facts.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
954 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
- Граница
- Алгоритм
- Формат ответа
- Запрещено
Files
SKILL.mdcore5,685 bytes
Read SKILL.md
# Daily
Быстрый локальный скилл: человек спрашивает — сразу получает ответ в чате.
## Граница
Работай только с текущим отделом. Не обходи штаб, соседние отделы, календарь и внешние системы. GitHub разрешён только тогда, когда `tasks/README.md` называет GitHub Issues активным источником задач этого отдела.
## Алгоритм
1. Определи сегодняшнюю дату, ISO-неделю и все семь дат недели из системного времени. Имя плана всегда вычисляется заново: `reports/WNN-plan.html` или формат, принятый текущим отделом.
2. Прочитай `AGENTS.md`, `README.md` и блок "Активный режим" в `tasks/README.md`.
3. Собери активные задачи из одного указанного источника:
- режим `локальные файлы` → прочитай `tasks/*.md`, кроме `README.md` и `_template.md`;View the complete source on GitHubplanning
When your agent uses it
Use when a completed department retro should become accepted outcomes and a full living ISO-week plan, or the user asks "планирование", "план недели", or "что делаем на следующей неделе".
What it loads into context
Frontmatter
56 tokensAlways available to the agent
SKILL.md
1,331 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
- Пререквизит
- Граница
- Этап 1. Собрать вход
- Этап 2. Выбрать результаты недели
- Этап 3. Создать или обновить задачи
- Этап 4. Сохранить HTML-план
- Этап 5. Проверка и приёмка
- Запрещено
Files
SKILL.mdcore8,532 bytes
Read SKILL.md
# Planning
Планирование смотрит вперёд и не выполняет запланированную работу.
## Пререквизит
До начала найди принятый отчёт `reports/ГГГГ-WNN-retro.html` за предыдущую неделю.
Если ретро не завершено или не принято, остановись и предложи сначала запустить `retro`.
## Граница
Планируй только текущий отдел. Не обходи штаб и соседние отделы. GitHub разрешён только как активный источник задач текущего отдела, указанный в `tasks/README.md`.
View the complete source on GitHubretro
When your agent uses it
Use when the user asks for "ретро", "обзор недели", or "что было за неделю" and the department needs a fact-based closeout plus its next Area goal.
What it loads into context
Frontmatter
50 tokensAlways available to the agent
SKILL.md
1,303 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
- Граница
- Этап 1. Собрать факты
- Этап 2. Разрешить незавершённое
- Этап 3. Интервью
- Этап 4. Сохранить отчёт
- Этап 5. Проверка и приёмка
- Запрещено
Files
SKILL.mdcore8,362 bytes
Read SKILL.md
# Retro
Ретро смотрит назад. Сначала полностью закрой разбор недели, только затем разрешай переход к `planning`.
## Граница
Работай со всеми задачами текущего отдела. Не обходи другие отделы и не собирай общий срез Personal Corp.
Записи задач и системы результатов остаются источниками истины. HTML — датированное представление недели.
## Этап 1. Собрать факты
1. Определи календарную неделю и её даты.
2. Прочитай `AGENTS.md`, `README.md` и блок "Активный режим" в `tasks/README.md`.View the complete source on GitHubSkills included
- paperclip-api
- daily-retro
- art-director
- audit-agent-rules
- avatar
- benchmark
- cc-analytics
- ceo-council
- claude-md-writer
- claude-sessions-sync
- corp-doctor
- corp-new
- daily
- fable-ruki-agenty
- gh-issues
- grill-me
- harness
- html-draft
- idea
- it-ram-doctor
- make-3d
- make-landing
- manager
- meeting-copilot
- readme-generator
- retro
- safe-public-release
- sdlc-milestones
- tg-bot-ops
- to-issues
- to-prd
- weekly-planning
- weekly-retro
- daily
- planning
- retro
Repository facts
- License
- MIT
- Created
- Dec 15, 2025
- Last pushed
- Nov 3, 2026
- Forks
- 24
- Open issues
- 7
- 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 160 notes
archive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedarchive/skills/paperclip-api/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/art-director/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 11 dangerous shell commandsin 7 files: paperclip-api/SKILL.md:26 corp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:79 corp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh:72 and 4 more
- 188 network referencesin 29 files: paperclip-api/SKILL.md:22 avatar/THIRD_PARTY_NOTICES.md:7 art-director/assets/style-search-map-template.html:5 and 26 more
- No hidden or obfuscated text
- No instruction overrides
- 18 executable scriptsin 18 files: daily-retro/scripts/collect.py:1 audit-agent-rules/scripts/scan.py:1 avatar/avatar.py:1 and 15 more
- 47 references to secretsin 14 files: benchmark/scripts/claude_step.py:14 corp-new/templates/corp-it/skills/machine-access/SKILL.md.tmpl:23 corp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:66 and 11 more
- No requests to vote in Hot
Show all 264 signals by file
.claude-plugin/plugin.json
- Network accessline 6
"name": "Sereja Ris", "email": "ris@sereja.tech", "url": "https://sereja.tech" - Network accessline 7
"email": "ris@sereja.tech", "url": "https://sereja.tech" }, - Network accessline 8
"url": "https://sereja.tech" - Network accessline 9
}, "homepage": "https://github.com/serejaris/personal-corp-os", "repository": "https://github.com/serejaris/personal-corp-os", - Network accessline 10
"homepage": "https://github.com/serejaris/personal-corp-os", - Network accessline 11
"repository": "https://github.com/serejaris/personal-corp-os",
archive/skills/paperclip-api/README.md
- Network accessline 5
Manage [Paperclip](https://github.com/paperclipai/paperclip) AI agent companies from Claude Code — create tasks, manage agents, approve hires, run heartbeats. No browser needed. - Network accessline 19
- [Paperclip](https://github.com/paperclipai/paperclip) running locally (`npx paperclipai onboard --yes`) - Network accessline 34
# Or use REST API directly curl -X POST http://127.0.0.1:3101/api/companies/{companyId}/issues \ - Network accessline 35
curl -X POST http://127.0.0.1:3101/api/companies/{companyId}/issues \ - Network accessline 42
- [Paperclip Docs](https://docs.paperclip.ing) - Network accessline 43
- [API Overview](https://docs.paperclip.ing/api/overview) - Network accessline 44
- [CLI Commands](https://docs.paperclip.ing/cli/control-plane-commands)
archive/skills/paperclip-api/README.ru.md
- Network accessline 5
Управление компаниями AI-агентов [Paperclip](https://github.com/paperclipai/paperclip) из Claude Code — создание задач, управление агентами, одобрение наймов, запуск heartbeat. Без браузера. - Network accessline 19
- [Paperclip](https://github.com/paperclipai/paperclip) запущен локально (`npx paperclipai onboard --yes`) - Network accessline 34
# Или использовать REST API напрямую curl -X POST http://127.0.0.1:3101/api/companies/{companyId}/issues \ - Network accessline 35
curl -X POST http://127.0.0.1:3101/api/companies/{companyId}/issues \ - Network accessline 42
- [Документация Paperclip](https://docs.paperclip.ing) - Network accessline 43
- [Обзор API](https://docs.paperclip.ing/api/overview) - Network accessline 44
- [CLI-команды](https://docs.paperclip.ing/cli/control-plane-commands)
archive/skills/paperclip-api/SKILL.md
- Network accessline 22
# Базовый URL (по умолчанию) PAPERCLIP_API=http://127.0.0.1:3101 - Network accessline 23
PAPERCLIP_API=http://127.0.0.1:3101 - Network accessline 25
# Найти companyId curl -s $PAPERCLIP_API/api/companies | python3 -m json.tool - Dangerous shell operationline 26
curl -s $PAPERCLIP_API/api/companies | python3 -m json.tool - Network accessline 26
curl -s $PAPERCLIP_API/api/companies | python3 -m json.tool - Network accessline 28
# Найти agentId curl -s $PAPERCLIP_API/api/companies/{companyId}/agents | python3 -m json.tool - Dangerous shell operationline 29
curl -s $PAPERCLIP_API/api/companies/{companyId}/agents | python3 -m json.tool - Network accessline 29
curl -s $PAPERCLIP_API/api/companies/{companyId}/agents | python3 -m json.tool - Network accessline 32
[Credential-related source omitted] - Network accessline 59
# ─── Контекст (сохранить defaults) ─── pnpm paperclipai context set --api-base http://localhost:3101 --company-id <id> - Network accessline 60
pnpm paperclipai context set --api-base http://localhost:3101 --company-id <id> - Network accessline 66
Base: `http://127.0.0.1:3101/api` - Network accessline 111
# Запустить heartbeat — ТОЛЬКО через CLI, не через REST API! # npx paperclipai heartbeat run --agent-id {agentId} --api-base http://127.0.0.1:3101 - Network accessline 112
# npx paperclipai heartbeat run --agent-id {agentId} --api-base http://127.0.0.1:3101 - Network accessline 185
# Создать curl -X POST $PAPERCLIP_API/api/companies/$CID/issues \ - Network accessline 186
curl -X POST $PAPERCLIP_API/api/companies/$CID/issues \ - Network accessline 190
# Назначить (из ответа взять issueId) curl -X POST $PAPERCLIP_API/api/issues/$ISSUE_ID/checkout \ - Network accessline 191
curl -X POST $PAPERCLIP_API/api/issues/$ISSUE_ID/checkout \ - Network accessline 203
# Или через API curl -X PATCH $PAPERCLIP_API/api/agents/$AGENT_ID \ - Network accessline 204
curl -X PATCH $PAPERCLIP_API/api/agents/$AGENT_ID \ - Dangerous shell operationline 212
curl -s $PAPERCLIP_API/api/companies/$CID/approvals?status=pending | python3 -c "import sys,json; [print(a['id']) for a in json.load(sys.stdin)]" | - Network accessline 212
curl -s $PAPERCLIP_API/api/companies/$CID/approvals?status=pending | \ - Network accessline 213
python3 -c "import sys,json; [print(a['id']) for a in json.load(sys.stdin)]" | \ xargs -I{} curl -X POST $PAPERCLIP_API/api/approvals/{}/approve \ -H "Content-Type: application/json" -d '{"notes": "Одобрено"}' - Network accessline 214
xargs -I{} curl -X POST $PAPERCLIP_API/api/approvals/{}/approve \ - Network accessline 223
npx paperclipai heartbeat run \ --agent-id {agentId} \ --api-base http://127.0.0.1:3101 - Network accessline 225
--api-base http://127.0.0.1:3101 - Network accessline 261
- MCP-сервера нет ([#369](https://github.com/paperclipai/paperclip/issues/369)) - Network accessline 267
- [API Overview](https://docs.paperclip.ing/api/overview) - Network accessline 268
- [CLI Overview](https://docs.paperclip.ing/cli/overview) - Network accessline 269
- [Control-Plane Commands](https://docs.paperclip.ing/cli/control-plane-commands) - Network accessline 270
- [Issues API](https://docs.paperclip.ing/api/issues) - Network accessline 271
- [Agents API](https://docs.paperclip.ing/api/agents) - Network accessline 272
- [Approvals API](https://docs.paperclip.ing/api/approvals) - Network accessline 273
- [Companies API](https://docs.paperclip.ing/api/companies)
experimental/skills/daily-retro/automation/daily-retro.plist
experimental/skills/daily-retro/scripts/collect.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/art-director/SKILL.md
- Network accessline 96
Then open `http://127.0.0.1:8080/...`. If the preview depends on a CDN and the network is blocked, report the blocker and keep the run in `blocked` or `needs-local-runtime` status. Store third-party library source only when the host repo po - Network accessline 279
curl -I -L --max-time 10 https://cdn.jsdelivr.net/npm/@dagrejs/dagre@1.1.8/dist/dagre.min.js - Network accessline 288
Then open `http://127.0.0.1:8080/...` and verify:
skills/art-director/assets/style-search-map-template.html
- Network accessline 5
<meta name="viewport" content="width=device-width, initial-scale=1"> <title>Style Search Decision Graph</title> <script src="https://cdn.jsdelivr.net/npm/@dagrejs/dagre@1.1.8/dist/dagre.min.js"></script> - Network accessline 6
<title>Style Search Decision Graph</title> <script src="https://cdn.jsdelivr.net/npm/@dagrejs/dagre@1.1.8/dist/dagre.min.js"></script> <style> - Network accessline 7
<script src="https://cdn.jsdelivr.net/npm/@dagrejs/dagre@1.1.8/dist/dagre.min.js"></script> - Network accessline 189
g.edges().forEach((edge) => { const points = g.edge(edge).points; const path = document.createElementNS("http://www.w3.org/2000/svg", "path"); - Network accessline 190
const points = g.edge(edge).points; const path = document.createElementNS("http://www.w3.org/2000/svg", "path"); path.setAttribute("class", "edge"); - Network accessline 191
const path = document.createElementNS("http://www.w3.org/2000/svg", "path"); - Network accessline 197
nodes.forEach((node) => { const layout = g.node(node.id); const group = document.createElementNS("http://www.w3.org/2000/svg", "g"); - Network accessline 198
const layout = g.node(node.id); const group = document.createElementNS("http://www.w3.org/2000/svg", "g"); group.setAttribute("class", `node ${node.status || "shown"}`); - Network accessline 199
const group = document.createElementNS("http://www.w3.org/2000/svg", "g"); - Network accessline 202
group.setAttribute("tabindex", "0"); group.addEventListener("click", () => showDetails(node)); const rect = document.createElementNS("http://www.w3.org/2000/svg", "rect"); - Network accessline 203
group.addEventListener("click", () => showDetails(node)); const rect = document.createElementNS("http://www.w3.org/2000/svg", "rect"); rect.setAttribute("width", layout.width); - Network accessline 204
const rect = document.createElementNS("http://www.w3.org/2000/svg", "rect"); - Network accessline 205
rect.setAttribute("width", layout.width); rect.setAttribute("height", layout.height); const title = document.createElementNS("http://www.w3.org/2000/svg", "text"); - Network accessline 206
rect.setAttribute("height", layout.height); const title = document.createElementNS("http://www.w3.org/2000/svg", "text"); title.setAttribute("x", 12); - Network accessline 207
const title = document.createElementNS("http://www.w3.org/2000/svg", "text"); - Network accessline 209
title.setAttribute("y", 28); title.textContent = node.title.length > 26 ? `${node.title.slice(0, 25)}...` : node.title; const status = document.createElementNS("http://www.w3.org/2000/svg", "text"); - Network accessline 210
title.textContent = node.title.length > 26 ? `${node.title.slice(0, 25)}...` : node.title; const status = document.createElementNS("http://www.w3.org/2000/svg", "text"); status.setAttribute("class", "status"); - Network accessline 211
const status = document.createElementNS("http://www.w3.org/2000/svg", "text");
skills/audit-agent-rules/SKILL.md
- Network accessline 84
- Anthropic, память и файлы правил: https://code.claude.com/docs/en/memory - Network accessline 85
- Anthropic, лучшие практики Claude Code: https://code.claude.com/docs/en/best-practices - Network accessline 86
- Anthropic, скиллы Claude Code: https://code.claude.com/docs/en/skills - Network accessline 87
- OpenAI, AGENTS.md в Codex: https://learn.chatgpt.com/docs/agent-configuration/agents-md - Network accessline 88
- OpenAI, скиллы Codex: https://learn.chatgpt.com/docs/build-skills - Network accessline 89
- Anthropic, Agent Skills: https://www.anthropic.com/engineering/equipping-agents-for-the-real-world-with-agent-skills
skills/audit-agent-rules/scripts/scan.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/avatar/THIRD_PARTY_NOTICES.md
- Network accessline 7
https://react.dev/ - Network accessline 35
https://react.dev/ - Network accessline 63
https://react.dev/ - Network accessline 91
https://threejs.org/ - Network accessline 119
https://github.com/pmndrs/react-three-fiber#readme - Network accessline 147
https://github.com/pmndrs/its-fine - Network accessline 175
https://github.com/pmndrs/suspend-react#readme - Network accessline 203
https://github.com/pmndrs/react-use-measure - Network accessline 259
https://github.com/pmndrs/zustand - Network accessline 287
https://babel.dev/docs/en/next/babel-runtime - Network accessline 316
https://github.com/feross/buffer - Network accessline 344
https://github.com/beatgammit/base64-js - Network accessline 390
https://lucide.dev - Network accessline 440
https://fontsource.org/fonts/inter - Network accessline 443
Copyright 2016 The Inter Project Authors (https://github.com/rsms/inter) Inter-Italic[opsz,wght].ttf: Copyright 2016 The Inter Project Authors (https://github.com/rsms/inter) - Network accessline 445
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: http://scripts.sil.org/OFL - Network accessline 447
http://scripts.sil.org/OFL - Network accessline 540
https://fontsource.org/fonts/jetbrains-mono - Network accessline 543
Copyright 2020 The JetBrains Mono Project Authors (https://github.com/JetBrains/JetBrainsMono) JetBrainsMono-Italic[wght].ttf: Copyright 2020 The JetBrains Mono Project Authors (https://github.com/JetBrains/JetBrainsMono) - Network accessline 545
This Font Software is licensed under the SIL Open Font License, Version 1.1. This license is copied below, and is also available with a FAQ at: http://scripts.sil.org/OFL - Network accessline 547
http://scripts.sil.org/OFL
skills/avatar/avatar.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 124
def link(code): return 'https://t.me/%s?start=%s' % (BOT, code) - Network accessline 125
return 'https://t.me/%s?start=%s' % (BOT, code) - Access to secretsline 250
[Credential-related source omitted] - Access to secretsline 303
[Credential-related source omitted]
skills/avatar/pc3live.py
- Executable scriptline 1
#!/usr/bin/env python3 - Access to secretsline 29
[Credential-related source omitted] - Access to secretsline 30
[Credential-related source omitted] - Network accessline 53
def http(url, body=None, accept='application/json'): data = json.dumps(body).encode('utf-8') if body is not None else None req = urllib.request.Request(url, data=data, headers={ - Network accessline 54
data = json.dumps(body).encode('utf-8') if body is not None else None req = urllib.request.Request(url, data=data, headers={ 'Content-Type': 'application/json', 'Accept': accept, 'User-Agent': 'pc3live/1'}) - Network accessline 55
req = urllib.request.Request(url, data=data, headers={ - Network accessline 56
'Content-Type': 'application/json', 'Accept': accept, 'User-Agent': 'pc3live/1'}) try: with urllib.request.urlopen(req, timeout=TIMEOUT) as r: - Network accessline 57
try: with urllib.request.urlopen(req, timeout=TIMEOUT) as r: return json.loads(r.read().decode('utf-8')) - Network accessline 58
with urllib.request.urlopen(req, timeout=TIMEOUT) as r:
skills/avatar/robot.html
- Network accessline 21
`).replace(ep,``)}function np(e,t){return t=tp(t),tp(e)===t}function rp(e,t,n,r,a,o){switch(n){case`children`:if(typeof r==`string`)t===`body`||t===`textarea`&&r===``||fn(e,r);else if(typeof r==`number`||typeof r==`bigint`)t!==`body`&&fn(e,
skills/benchmark/SKILL.md
skills/benchmark/examples/adapter_example.py
skills/benchmark/prices.example.json
- Network accessline 6
"EUR_RUB": 96.0625, "date": "2026-09-30", "source": "https://www.cbr.ru/scripts/XML_daily.asp?date_req=30/09/2026" - Network accessline 7
"date": "2026-09-30", "source": "https://www.cbr.ru/scripts/XML_daily.asp?date_req=30/09/2026" }, - Network accessline 8
"source": "https://www.cbr.ru/scripts/XML_daily.asp?date_req=30/09/2026" - Network accessline 9
}, "items": { "elevenlabs.scribe_v2": {"kind": "per_hour", "usd": 0.22, "source": "https://elevenlabs.io/pricing/api", "checked": "2026-09-30", "note": "Scribe v2 batch, API price per hour of audio"}, - Network accessline 10
"items": { "elevenlabs.scribe_v2": {"kind": "per_hour", "usd": 0.22, "source": "https://elevenlabs.io/pricing/api", "checked": "2026-09-30", "note": "Scribe v2 batch, API price per hour of audio"}, "elevenlabs.scribe_v2+keyterms": { - Network accessline 11
"elevenlabs.scribe_v2": {"kind": "per_hour", "usd": 0.22, "source": "https://elevenlabs.io/pricing/api", "checked": "2026-09-30", "note": "Scribe v2 batch, API price per hour of audio"}, - Network accessline 12
"elevenlabs.scribe_v2+keyterms": {"kind": "per_hour", "usd": 0.27, "source": "https://elevenlabs.io/pricing/api", "checked": "2026-09-30", "note": "0.22 + keyterm prompting 0.05"}, - Network accessline 13
"openai.gpt-transcribe": {"kind": "per_hour", "usd": 0.27, "source": "https://developers.openai.com/api/docs/pricing", "checked": "2026-09-30", "note": "$0.0045 per minute"}, - Network accessline 14
"openrouter.openai/whisper-large-v3-turbo": {"kind": "per_hour", "usd": 0.012, "source": "https://openrouter.ai/api/v1/models?output_modalities=transcription", "checked": "2026-09-30", "note": "$0.00000333 per second"}, - Network accessline 15
"openrouter.google/gemini-3.8-flash": {"kind": "tokens", "usd_per_mtok": {"audio_in": 0.75, "in": 0.75, "out": 3.75}, "audio_tokens_per_sec": 32, "est_out_tokens_per_hour": 25000, "source": "https://openrouter.ai/api/v1/models", "checked": - Network accessline 16
"openrouter.openai/gpt-audio-mini": {"kind": "tokens", "usd_per_mtok": {"audio_in": 0.6, "in": 0.6, "out": 2.4}, "source": "https://openrouter.ai/api/v1/models", "checked": "2026-09-30", "note": "audio tokenization not published: cost only - Network accessline 17
"yandex.speechkit.async": {"kind": "per_hour", "rub": 47.6, "source": "https://yandex.cloud/ru-kz/docs/speechkit/pricing", "checked": "2026-09-30", "note": "0.01321666 RUB per second of two-channel audio, VAT included; the RU page answered - Network accessline 18
"sber.salutespeech.legal": {"kind": "per_hour", "rub": 36.0, "source": "https://developers.sber.ru/docs/ru/salutespeech/tariffs/legal-tariffs", "checked": "2026-09-30", "note": "0.01 RUB per second, minimum 15 000 RUB per month; since 2026- - Network accessline 19
"zai.glm-5.3": {"kind": "tokens", "usd_per_mtok": {"in": 1.4, "cache_read": 0.26, "cache_write": 1.4, "out": 4.4}, "source": "https://docs.z.ai/guides/overview/pricing", "checked": "2026-09-30"}, - Network accessline 20
"zai.glm-5.3-flash": {"kind": "tokens", "usd_per_mtok": {"in": 0.15, "out": 0.5}, "source": "https://docs.z.ai/guides/overview/pricing", "checked": "2026-09-30", "note": "no separate cache price found: cached input counted at input price"}, - Network accessline 21
"anthropic.claude-opus-5-5": {"kind": "tokens", "usd_per_mtok": {"in": 4, "cache_read": 0.2, "cache_write": 5, "out": 20}, "source": "https://claude.com/pricing", "checked": "2026-09-30"}, - Network accessline 22
"anthropic.claude-sonnet-5-5": {"kind": "tokens", "usd_per_mtok": {"in": 2, "cache_read": 0.2, "cache_write": 2.5, "out": 10}, "source": "https://claude.com/pricing", "checked": "2026-09-30"},
skills/benchmark/scripts/asr.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 74
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Network accessline 75
base = v.get("base_url", "https://api.elevenlabs.io/v1") - Network accessline 78
def credits() -> int | None: try: r = httpx.get(f"{base}/user/subscription", headers=headers, timeout=30) - Network accessline 79
try: r = httpx.get(f"{base}/user/subscription", headers=headers, timeout=30) return r.json().get("character_count") if r.status_code == 200 else None - Network accessline 80
r = httpx.get(f"{base}/user/subscription", headers=headers, timeout=30) - Network accessline 93
data["keyterms"] = keyterms before = credits() with audio.open("rb") as fh, httpx.Client(timeout=httpx.Timeout(3600, connect=30)) as client: - Network accessline 94
before = credits() with audio.open("rb") as fh, httpx.Client(timeout=httpx.Timeout(3600, connect=30)) as client: r = client.post(f"{base}/speech-to-text", headers=headers, data=data, files={"file": (audio.name, fh)}) - Network accessline 95
with audio.open("rb") as fh, httpx.Client(timeout=httpx.Timeout(3600, connect=30)) as client: - Network accessline 113
if v.get("send_language", True) and task.get("language"): data["language"] = task["language"] with audio.open("rb") as fh, httpx.Client(timeout=httpx.Timeout(float(v.get("timeout", 7200)), connect=30)) as client: - Network accessline 114
data["language"] = task["language"] with audio.open("rb") as fh, httpx.Client(timeout=httpx.Timeout(float(v.get("timeout", 7200)), connect=30)) as client: r = client.post(v["base_url"].rstrip("/") + "/audio/transcriptions", head - Network accessline 115
with audio.open("rb") as fh, httpx.Client(timeout=httpx.Timeout(float(v.get("timeout", 7200)), connect=30)) as client: - Network accessline 149
[Credential-related source omitted] - Access to secretsline 149
[Credential-related source omitted] - Network accessline 150
base = v.get("base_url", "https://openrouter.ai/api/v1").rstrip("/") - Network accessline 172
[Credential-related source omitted] - Network accessline 173
[Credential-related source omitted] - Network accessline 174
[Credential-related source omitted] - Network accessline 175
timeout=httpx.Timeout(1800, connect=30))
skills/benchmark/scripts/claude_step.py
- Executable scriptline 1
Executable file - Network accessline 13
Providers (keys come from env; values are never written to logs): zai https://api.z.ai/api/anthropic ZAI_API_KEY - Network accessline 14
[Credential-related source omitted] - Access to secretsline 14
[Credential-related source omitted] - Network accessline 15
[Credential-related source omitted] - Access to secretsline 15
[Credential-related source omitted] - Network accessline 16
[Credential-related source omitted] - Access to secretsline 16
[Credential-related source omitted] - Access to secretsline 17
[Credential-related source omitted] - Network accessline 31
PROVIDERS = { "zai": {"base_url": "https://api.z.ai/api/anthropic", "token_env": "ZAI_API_KEY"}, - Network accessline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Network accessline 33
[Credential-related source omitted] - Access to secretsline 33
[Credential-related source omitted] - Network accessline 34
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 35
[Credential-related source omitted] - Access to secretsline 47
[Credential-related source omitted] - Access to secretsline 48
[Credential-related source omitted] - Access to secretsline 53
[Credential-related source omitted] - Access to secretsline 54
[Credential-related source omitted] - Access to secretsline 60
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted] - Access to secretsline 68
[Credential-related source omitted]
skills/benchmark/scripts/common.py
skills/benchmark/scripts/llm.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/benchmark/scripts/report.py
- Executable scriptline 1
#!/usr/bin/env python3 - Network accessline 134
items = [l[2:].strip() for l in args.notes.read_text(encoding="utf-8").splitlines() if l.startswith("- ")] notes = "<h2>Как читать</h2><ul>" + "".join(f"<li>{esc(i)}</li>" for i in items) + "</ul>" fonts = ('<link rel="styleshee - Network accessline 135
notes = "<h2>Как читать</h2><ul>" + "".join(f"<li>{esc(i)}</li>" for i in items) + "</ul>" fonts = ('<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=PT+Mono&family=PT+Sans:wght@400;700' '&family=PT+Ser - Network accessline 136
fonts = ('<link rel="stylesheet" href="https://fonts.googleapis.com/css2?family=PT+Mono&family=PT+Sans:wght@400;700'
skills/benchmark/scripts/score.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/benchmark/task.example.json
- Network accessline 11
{"id": "elevenlabs-scribe-v2-terms", "engine": "elevenlabs", "model": "scribe_v2", "keyterms": true, "price": "elevenlabs.scribe_v2+keyterms"}, {"id": "elevenlabs-scribe-v2", "engine": "elevenlabs", "model": "scribe_v2", "keyterms": fal - Network accessline 12
{"id": "elevenlabs-scribe-v2", "engine": "elevenlabs", "model": "scribe_v2", "keyterms": false, "price": "elevenlabs.scribe_v2"}, {"id": "gigaam-self-hosted", "engine": "openai_compat", "base_url": "http://10.0.0.10:8001/v1", "model": " - Network accessline 13
[Credential-related source omitted] - Access to secretsline 13
[Credential-related source omitted]
skills/claude-sessions-sync/SKILL.md
- Network accessline 69
Background write-up: https://sereja.tech/blog/claude-code-sessions-between-accounts/
skills/corp-new/SKILL.md
skills/corp-new/assets/illustration-en.svg
- Network accessline 1
<svg viewBox="0 0 960 792" width="960" height="792" role="img" aria-labelledby="t d" xmlns="http://www.w3.org/2000/svg">
skills/corp-new/assets/illustration.svg
- Network accessline 1
<svg viewBox="0 0 960 792" width="960" height="792" role="img" aria-labelledby="t d" xmlns="http://www.w3.org/2000/svg">
skills/corp-new/templates/common/gitignore
- Access to secretsline 2
[Credential-related source omitted]
skills/corp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh
- Executable scriptline 1
#!/bin/bash - Access to secretsline 66
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Access to secretsline 71
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted] - Access to secretsline 74
[Credential-related source omitted] - Dangerous shell operationline 79
# sudo -n true ничего не запускает, а только проверяет, пустит ли система без пароля. - Dangerous shell operationline 80
if sudo -n true 2>/dev/null; then echo "- sudo без пароля: да"; else echo "- sudo без пароля: нет"; fi
skills/corp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh
- Executable scriptline 1
#!/bin/bash - Network accessline 55
section "Доступы" if nc -z localhost 22 2>/dev/null; then echo "- SSH на устройство: порт 22 принимает соединения"; else echo "- SSH на устройство: порт 22 закрыт (Remote Login выключен)"; fi - Network accessline 56
if nc -z localhost 22 2>/dev/null; then echo "- SSH на устройство: порт 22 принимает соединения"; else echo "- SSH на устройство: порт 22 закрыт (Remote Login выключен)"; fi - Network accessline 57
if nc -z localhost 5900 2>/dev/null; then echo "- удалённый экран: порт 5900 принимает соединения"; else echo "- удалённый экран: порт 5900 закрыт"; fi - Access to secretsline 59
[Credential-related source omitted] - Access to secretsline 60
[Credential-related source omitted] - Access to secretsline 64
[Credential-related source omitted] - Access to secretsline 65
[Credential-related source omitted] - Access to secretsline 67
[Credential-related source omitted] - Dangerous shell operationline 72
# sudo -n true ничего не запускает, а только проверяет, пустит ли система без пароля. - Dangerous shell operationline 73
if sudo -n true 2>/dev/null; then echo "- sudo без пароля: да"; else echo "- sudo без пароля: нет"; fi
skills/corp-new/templates/corp-it/skills/device-inventory/template.md
- Dangerous shell operationline 50
- sudo без пароля: <да | нет>;
skills/corp-new/templates/corp-it/skills/machine-access/SKILL.md.tmpl
- Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 26
[Credential-related source omitted] - Access to secretsline 28
[Credential-related source omitted] - Access to secretsline 34
[Credential-related source omitted] - Access to secretsline 55
[Credential-related source omitted] - Access to secretsline 58
[Credential-related source omitted]
skills/html-draft/SKILL.md
- Network accessline 75
1. **Tailwind v4 via browser CDN** — version-pinned `https://cdn.jsdelivr.net/npm/@tailwindcss/browser@4` - Network accessline 76
2. **D3 v7 via jsDelivr CDN** — version-pinned `https://cdn.jsdelivr.net/npm/d3@7` - Network accessline 90
<meta name="viewport" content="width=device-width, initial-scale=1.0" /> <title>[Diagram Title]</title> <script src="https://cdn.jsdelivr.net/npm/@tailwindcss/browser@4"></script> - Network accessline 91
<title>[Diagram Title]</title> <script src="https://cdn.jsdelivr.net/npm/@tailwindcss/browser@4"></script> <style type="text/tailwindcss"> - Network accessline 92
<script src="https://cdn.jsdelivr.net/npm/@tailwindcss/browser@4"></script> - Network accessline 138
<script src="https://cdn.jsdelivr.net/npm/d3@7"></script> - Network accessline 244
`d3-sankey` plugin (`https://cdn.jsdelivr.net/npm/d3-sankey@0.12`) when volumes matter. Keep ribbons grayscale; one accent only for the watched flow.
skills/it-ram-doctor/SKILL.md
- Network accessline 15
- pressure: `sysctl kern.memorystatus_vm_pressure_level` is 4 or stays at 2 for long ([threshold](https://github.com/anthropics/claude-code/issues/73834): on Apple silicon 2 appears under ordinary compression); `memory_pressure | tail -1` s
skills/it-ram-doctor/scripts/tails-linux.sh
skills/it-ram-doctor/scripts/tails-macos.sh
skills/make-landing/scripts/freeze_concept.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/meeting-copilot/SKILL.md
skills/safe-public-release/SKILL.md
- Dangerous shell operationline 245
rm -rf "$STAGING_ROOT/package" - Network accessline 306
workdir=$(mktemp -d) git clone --depth 1 https://github.com/OWNER/REPO.git "$workdir/repo" - Network accessline 307
git clone --depth 1 https://github.com/OWNER/REPO.git "$workdir/repo" - Network accessline 326
release_status: VERIFIED public_url: https://github.com/OWNER/REPO - Network accessline 327
public_url: https://github.com/OWNER/REPO
skills/safe-public-release/references/release-manifest.example.yaml
- Network accessline 5
intended_license: MIT status: INVENTORY source_issue: https://github.com/OWNER/INTERNAL-OWNER-REPO/issues/N - Network accessline 6
status: INVENTORY source_issue: https://github.com/OWNER/INTERNAL-OWNER-REPO/issues/N release_owner: null - Network accessline 7
source_issue: https://github.com/OWNER/INTERNAL-OWNER-REPO/issues/N
skills/sdlc-milestones/SKILL.md
- Network accessline 8
Источник: [The AI-Native SDLC Playbook](https://cdn.prod.website-files.com/6889473510b50328dbb70ae6/6aba736348bdf4f08183f463_AI%20Native%20SDLC%20Playbook_designv2%20(1).pdf), Louis Claxton, Anthropic. Ниже пересказ, приложенный к работе с
skills/sdlc-milestones/scripts/milestones.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/tg-bot-ops/SKILL.md
- Access to secretsline 32
[Credential-related source omitted] - Network accessline 82
[Credential-related source omitted] - Access to secretsline 82
[Credential-related source omitted] - Network accessline 83
for method in ("getMe", "getWebhookInfo"): with urllib.request.urlopen(f"https://api.telegram.org/bot{token}/{method}") as response: data = json.load(response) - Network accessline 84
with urllib.request.urlopen(f"https://api.telegram.org/bot{token}/{method}") as response:
skills/weekly-planning/scripts/living_week.py
- Executable scriptline 1
#!/usr/bin/env python3
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.
Some files could not be read; the facts below still hold.
Combined signals: 4 facts
- Passes downloaded content to an interpreterpaperclip-api/SKILL.md:26High confidence
- Passes downloaded content to an interpreterpaperclip-api/SKILL.md:29High confidence
- Reads SSH keys, and the same file sends data over the network or runs a command (line 80)corp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:66High confidence
- Reads SSH keys, and the same file sends data over the network or runs a command (line 73)corp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh:59High confidence
Declared and executed: 16 facts
- Contacts t.me, which SKILL.md, the README and the plugin manifest do not mentionavatar/avatar.py:125High confidence
- Contacts api.elevenlabs.io, which SKILL.md, the README and the plugin manifest do not mentionbenchmark/scripts/asr.py:75High confidence
- Contacts openrouter.ai, which SKILL.md, the README and the plugin manifest do not mentionbenchmark/scripts/asr.py:150High confidence
- Contacts openrouter.ai, which SKILL.md, the README and the plugin manifest do not mentionbenchmark/scripts/claude_step.py:33High confidence
- Contacts api.deepseek.com, which SKILL.md, the README and the plugin manifest do not mentionbenchmark/scripts/claude_step.py:34High confidence
- Contacts fonts.googleapis.com, which SKILL.md, the README and the plugin manifest do not mentionbenchmark/scripts/report.py:136High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:66High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:67High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:71High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:72High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-linux.sh:74High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh:59High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh:60High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh:64High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh:65High confidence
- Uses SSH keys, which the skill description does not mentioncorp-new/templates/corp-it/skills/device-inventory/scripts/snapshot-macos.sh:67High confidence
Signal confidence: 204 facts
- Network access in prose of documentationpaperclip-api/README.md:5Low confidence
- Network access in prose of documentationpaperclip-api/README.md:19Low confidence
- Network access in code of documentationpaperclip-api/README.md:34Low confidence
- Network access in code of documentationpaperclip-api/README.md:35Low confidence
- Network access in prose of documentationpaperclip-api/README.md:42Low confidence
- Network access in prose of documentationpaperclip-api/README.md:43Low confidence
- Network access in prose of documentationpaperclip-api/README.md:44Low confidence
- Network access in prose of documentationpaperclip-api/README.ru.md:5Low confidence
- Network access in prose of documentationpaperclip-api/README.ru.md:19Low confidence
- Network access in code of documentationpaperclip-api/README.ru.md:34Low confidence
- Network access in code of documentationpaperclip-api/README.ru.md:35Low confidence
- Network access in prose of documentationpaperclip-api/README.ru.md:42Low confidence
- Network access in prose of documentationpaperclip-api/README.ru.md:43Low confidence
- Network access in prose of documentationpaperclip-api/README.ru.md:44Low confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:22High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:23High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:25High confidence
- Dangerous shell operation in code of the SKILL.mdpaperclip-api/SKILL.md:26High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:26High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:28High confidence
- Dangerous shell operation in code of the SKILL.mdpaperclip-api/SKILL.md:29High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:29High confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:32Low confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:59High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:60High confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:66Low confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:111High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:112High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:185High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:186High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:190High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:191High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:203High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:204High confidence
- Dangerous shell operation in code of the SKILL.mdpaperclip-api/SKILL.md:212High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:212High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:213High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:214High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:223High confidence
- Network access in code of the SKILL.mdpaperclip-api/SKILL.md:225High confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:261Low confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:267Low confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:268Low confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:269Low confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:270Low confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:271Low confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:272Low confidence
- Network access in prose of the SKILL.mdpaperclip-api/SKILL.md:273Low confidence
- Executable script in code of a file that runsdaily-retro/scripts/collect.py:1High confidence
- Network access in prose of the SKILL.mdart-director/SKILL.md:96Low confidence
and 154 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md archive/skills/paperclip-api/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md archive/skills/paperclip-api/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md archive/skills/paperclip-api/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md archive/skills/paperclip-api/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.