Agent Skill
Skill Creator skill
skill-creatorThinkInAIXYZ/deepchatresources/skills/skill-creator/SKILL.md
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
always on
45 tokname + description
once used
3,614 tokSKILL.md body
bundled files
63 scripts
repo stars
6.4kGitHub
Install the Skill Creator skill
Skills CLI (Claude Code, Codex, Cursor and others)
npx skills add https://github.com/ThinkInAIXYZ/deepchat --skill skill-creator
Claude Code, by hand (all projects)
git clone --depth 1 https://github.com/ThinkInAIXYZ/deepchat.git /tmp/deepchat mkdir -p ~/.claude/skills cp -R /tmp/deepchat/resources/skills/skill-creator ~/.claude/skills/skill-creator
For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.
What it costs your context
Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.
| When | What loads | Cost |
|---|---|---|
| Every session | Name and description | 45 tok |
| When the agent uses it | The SKILL.md instructions | 3,614 tok |
| Only if opened | 6 bundled files (31 KB) | varies |
Until it is used, skill-creator costs about 30× less than the median MCP server we measured (1,362 tokens on every turn). Installing all 24 skills from ThinkInAIXYZ/deepchat would load 1,435 tokens of descriptions. Skills vs MCP study
Checks
- Ships scripts the agent can run. Read them before installing.
Checked 2026-10-22 · method
What's inside
The headings of its SKILL.md. Read the full file on GitHub.
- Skill Creator
- About Skills
- What Skills Provide
- Core Principles
- Concise is Key
- Set Appropriate Degrees of Freedom
- Anatomy of a Skill
- Progressive Disclosure Design Principle
- Skill Creation Process
- Step 1: Understanding the Skill with Concrete Examples
- Step 2: Planning the Reusable Skill Contents
- Step 3: Initializing the Skill
- Step 4: Edit the Skill
- Step 5: Packaging a Skill
- Step 6: Iterate
More skills from ThinkInAIXYZ/deepchat
- add-providerThinkInAIXYZ/deepchat
Add a DeepChat LLM provider through explicit reviewed source changes. Use when a developer asks Codex to add a provider, provider profile, upstream provider config, model catalog mapping, provider auth behavior, or a special provider adapter in this repository.
6.4k52 tok idle · 927 in use - code-reviewThinkInAIXYZ/deepchat
Comprehensive code review assistant that analyzes code quality, security, and best practices
6.4k17 tok idle · 253 in use - computer-useThinkInAIXYZ/deepchat
Drive native desktop apps through DeepChat's built-in Computer Use tools. Use when the user asks to operate, inspect, automate, or perform a GUI task in a real desktop application.
6.4k40 tok idle · 2,565 in use - deepchat-cliThinkInAIXYZ/deepchat
Use DeepChat's bundled CLI control plane for model inference, image/video/speech generation, transcription, OCR, artifact inspection, public configuration, Skills, and MCP operations. Activate when a user asks to invoke DeepChat capabilities that are not already exposed as a more specific tool, compare models, run a benchmark, inspect DeepChat runtime state, or manage DeepChat through the CLI.
6.4k80 tok idle · 1,176 in use - deepchat-data-importThinkInAIXYZ/deepchat
Help developers build third-party tools that import, inspect, migrate, or analyze DeepChat data. Use when Codex needs to work with DeepChat provider configuration, model configuration, MCP/app settings, sessions, messages, legacy chat data, `agent.db`, `chat.db`, SQLCipher encrypted SQLite, Electron safeStorage wrapped passwords, Tauri importers, or native macOS/Windows/Linux data access.
6.4k86 tok idle · 544 in use - deepchat-releaseThinkInAIXYZ/deepchat
Prepare and publish DeepChat releases in this repository. Use when Codex needs to bump the app version, update CHANGELOG.md, keep release notes bilingual from v1.0.1 onward with English bullets first and Chinese bullets second, run release checks, create or update versioned release branches such as release/v1.0.1, continue a half-finished release, fast-forward main with the documented release flow, create or push version tags, or clean up release branches after publishing.
6.4k102 tok idle · 968 in use - deepchat-sddThinkInAIXYZ/deepchat
Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path. Skip trivial style fixes, small localized logic changes, routine docs edits, and simple bugs unless the developer asks for SDD. Use plan.md as the only separate tracker when needed, default to implementation-first validation, and ask before optional GitHub issue sync unless the developer explicitly requested sync.
6.4k98 tok idle · 1,682 in use - deepchat-sdd-cleanupThinkInAIXYZ/deepchat
Use only when a developer explicitly asks to clean, prune, tidy, or organize DeepChat SDD documentation after implementation and validation. Scans docs/features, docs/issues, and docs/architecture; prefers multi-agent review when available; removes completed issue docs when a linked GitHub issue is closed or implementation and validation evidence proves the bug no longer exists, drops stale plans and legacy task files from completed feature or architecture goals, and deletes obsolete feature or architecture docs.
6.4k99 tok idle · 574 in use