getcompanion-ai/co-mono
1
0
Fork 0
mirror of https://github.com/getcompanion-ai/co-mono.git synced 2026-04-20 12:04:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

docs(coding-agent): fix token count in themes.md, rewrite skills.md

Browse source 
- Fixed themes.md: 50 -> 51 color tokens
- Rewrote skills.md to match structure of other docs (TOC, concise sections)
- Removed redundant content from skills.md while keeping all essential info
This commit is contained in:
Mario Zechner 2026-01-25 20:48:47 +01:00
parent 728dc86d49
commit 3dca4979e4
2 changed files with 80 additions and 159 deletions
Download patch file Download diff file Expand all files Collapse all files

235
packages/coding-agent/docs/skills.md
View file

@ -6,52 +6,73 @@ Skills are self-contained capability packages that the agent loads on-demand. A
Pi implements the [Agent Skills standard](https://agentskills.io/specification). Pi implements the [Agent Skills standard](https://agentskills.io/specification).
**Example use cases:** ## Table of Contents
- Web search and content extraction (Brave Search API)
- Browser automation via Chrome DevTools Protocol
- Google Calendar, Gmail, Drive integration
- PDF/DOCX processing and creation
- Speech-to-text transcription
- YouTube transcript extraction
See [Skill Repositories](#skill-repositories) for ready-to-use skills. - [Locations](#locations)
- [How Skills Work](#how-skills-work)
- [Skill Commands](#skill-commands)
- [Skill Structure](#skill-structure)
- [Frontmatter](#frontmatter)
- [Validation](#validation)
- [Example](#example)
- [Skill Repositories](#skill-repositories)
## When to Use Skills ## Locations
| Need | Solution | Pi loads skills from:
|------|----------|
| Always-needed context (conventions, commands) | AGENTS.md |
| User triggers a specific prompt template | Slash command |
| Additional tool directly callable by the LLM (like read/write/edit/bash) | Custom tool |
| On-demand capability package (workflows, scripts, setup) | Skill |
Skills are loaded when: - Global: `~/.pi/agent/skills/`
- The agent decides the task matches a skill's description - Project: `.pi/skills/`
- The user explicitly asks to use a skill (e.g., "use the pdf skill to extract tables") - Packages: `skills/` directories or `pi.skills` entries in `package.json`
- Settings: `skills` array with files or directories
- CLI: `--skill <path>` (repeatable, additive even with `--no-skills`)
**Good skill examples:** Discovery rules:
- Browser automation with helper scripts and CDP workflow - Direct `.md` files in the skills directory root
- Google Calendar CLI with setup instructions and usage patterns - Recursive `SKILL.md` files under subdirectories
- PDF processing with multiple tools and extraction patterns
- Speech-to-text transcription with API setup
**Not a good fit for skills:** Disable discovery with `--no-skills` (explicit `--skill` paths still load).
- "Always use TypeScript strict mode" → put in AGENTS.md
- "Review my code" → make a prompt template ## How Skills Work
- Need user confirmation dialogs or custom TUI rendering → make a custom tool
1. At startup, pi scans skill locations and extracts names and descriptions
2. The system prompt includes available skills in XML format
3. When a task matches, the agent uses `read` to load the full SKILL.md
4. The agent follows the instructions, using relative paths to reference scripts and assets
This is progressive disclosure: only descriptions are always in context, full instructions load on-demand.
## Skill Commands
Skills register as `/skill:name` commands:
```bash
/skill:brave-search # Load and execute the skill
/skill:pdf-tools extract # Load skill with arguments
```
Arguments after the command are appended to the skill content as `User: <args>`.
Toggle skill commands in settings:
```json
{
"enableSkillCommands": true
}
```
## Skill Structure ## Skill Structure
A skill is a directory with a `SKILL.md` file. Everything else is freeform. Example structure: A skill is a directory with a `SKILL.md` file. Everything else is freeform.
``` ```
my-skill/ my-skill/
├── SKILL.md # Required: frontmatter + instructions ├── SKILL.md # Required: frontmatter + instructions
├── scripts/ # Helper scripts (bash, python, node) ├── scripts/ # Helper scripts
│ └── process.sh │ └── process.sh
├── references/ # Detailed docs loaded on-demand ├── references/ # Detailed docs loaded on-demand
│ └── api-reference.md │ └── api-reference.md
└── assets/ # Templates, images, etc. └── assets/
└── template.json └── template.json
``` ```
@ -77,47 +98,46 @@ cd /path/to/skill && npm install
\`\`\`bash \`\`\`bash
./scripts/process.sh <input> ./scripts/process.sh <input>
\`\`\` \`\`\`
## Workflow
1. First step
2. Second step
3. Third step
``` ```
### Frontmatter Fields Use relative paths from the skill directory:
```markdown
See [the reference guide](references/REFERENCE.md) for details.
```
## Frontmatter
Per the [Agent Skills specification](https://agentskills.io/specification#frontmatter-required): Per the [Agent Skills specification](https://agentskills.io/specification#frontmatter-required):
| Field | Required | Constraints | | Field | Required | Description |
|-------|----------|-------------| |-------|----------|-------------|
| `name` | Yes | Max 64 chars. Lowercase a-z, 0-9, hyphens only. Must match parent directory name. | | `name` | Yes | Max 64 chars. Lowercase a-z, 0-9, hyphens. Must match parent directory. |
| `description` | Yes | Max 1024 chars. What the skill does and when to use it. | | `description` | Yes | Max 1024 chars. What the skill does and when to use it. |
| `license` | No | License name or reference to bundled license file. | | `license` | No | License name or reference to bundled file. |
| `compatibility` | No | Max 500 chars. Environment requirements (system packages, network access, etc.). | | `compatibility` | No | Max 500 chars. Environment requirements. |
| `metadata` | No | Arbitrary key-value mapping for additional metadata. | | `metadata` | No | Arbitrary key-value mapping. |
| `allowed-tools` | No | Space-delimited list of pre-approved tools (experimental). | | `allowed-tools` | No | Space-delimited list of pre-approved tools (experimental). |
| `disable-model-invocation` | No | When `true`, the skill is hidden from the system prompt. The model cannot invoke it agentically; users must use `/skill:name`. | | `disable-model-invocation` | No | When `true`, skill is hidden from system prompt. Users must use `/skill:name`. |
#### Name Validation ### Name Rules
The `name` field must: - 1-64 characters
- Be 1-64 characters - Lowercase letters, numbers, hyphens only
- Contain only lowercase letters (a-z), numbers (0-9), and hyphens - No leading/trailing hyphens
- Not start or end with a hyphen - No consecutive hyphens
- Not contain consecutive hyphens (--) - Must match parent directory name
- Match the parent directory name exactly
Valid: `pdf-processing`, `data-analysis`, `code-review` Valid: `pdf-processing`, `data-analysis`, `code-review`
Invalid: `PDF-Processing`, `-pdf`, `pdf--processing` Invalid: `PDF-Processing`, `-pdf`, `pdf--processing`
#### Description Best Practices ### Description Best Practices
The `description` is critical. It determines when the agent loads the skill. Be specific about both what it does and when to use it. The description determines when the agent loads the skill. Be specific.
Good: Good:
```yaml ```yaml
description: Extracts text and tables from PDF files, fills PDF forms, and merges multiple PDFs. Use when working with PDF documents or when the user mentions PDFs, forms, or document extraction. description: Extracts text and tables from PDF files, fills PDF forms, and merges multiple PDFs. Use when working with PDF documents.
``` ```
Poor: Poor:
@ -125,107 +145,19 @@ Poor:
description: Helps with PDFs. description: Helps with PDFs.
``` ```
### File References ## Validation
Use relative paths from the skill directory:
```markdown
See [the reference guide](references/REFERENCE.md) for details.
Run the extraction script:
\`\`\`bash
./scripts/extract.py input.pdf
\`\`\`
```
## Skill Locations
Skills are discovered from these locations (later wins on name collision):
1. `~/.pi/agent/skills/` (global)
2. `<cwd>/.pi/skills/` (project)
3. Paths listed in `settings.json` under `skills`
4. CLI `--skill` paths (additive even with `--no-skills`)
Discovery rules for each directory:
- Direct `.md` files in the root
- Recursive `SKILL.md` files under subdirectories
## Configuration
Configure skill paths in `~/.pi/agent/settings.json`:
```json
{
"skills": ["~/my-skills-repo", "/path/to/skill/SKILL.md"],
"enableSkillCommands": true
}
```
Use project-local settings in `<cwd>/.pi/settings.json` to scope skills to a single project.
| Setting | Default | Description |
|---------|---------|-------------|
| `skills` | `[]` | Additional skill file or directory paths |
| `enableSkillCommands` | `true` | Register skills as `/skill:name` commands |
### CLI Additions
Use `--skill` to add skills for a specific invocation:
```bash
pi --skill ~/my-skills/terraform
pi --skill ./skills/custom-skill/SKILL.md
```
Use `--no-skills` to disable automatic discovery (CLI `--skill` paths still load).
## How Skills Work
1. At startup, pi scans skill locations and extracts names + descriptions
2. The system prompt includes available skills in XML format
3. When a task matches, the agent uses `read` to load the full SKILL.md
4. The agent follows the instructions, using relative paths to reference scripts/assets
This is progressive disclosure: only descriptions are always in context, full instructions load on-demand.
## Skill Commands
Skills are automatically registered as slash commands with a `/skill:` prefix:
```bash
/skill:brave-search # Load and execute the brave-search skill
/skill:pdf-tools extract # Load skill with arguments
```
Arguments after the command name are appended to the skill content as `User: <args>`.
Toggle skill commands via `/settings` or in `settings.json`:
```json
{
"enableSkillCommands": true
}
```
| Setting | Default | Description |
|---------|---------|-------------|
| `enableSkillCommands` | `true` | Register skills as `/skill:name` commands |
## Validation Warnings
Pi validates skills against the Agent Skills standard and warns (but still loads) non-compliant skills: Pi validates skills against the Agent Skills standard and warns (but still loads) non-compliant skills:
- Name doesn't match parent directory - Name doesn't match parent directory
- Name exceeds 64 characters - Name exceeds 64 characters or contains invalid characters
- Name contains invalid characters
- Name starts/ends with hyphen or has consecutive hyphens - Name starts/ends with hyphen or has consecutive hyphens
- Description missing or exceeds 1024 characters - Description missing or exceeds 1024 characters
- Unknown frontmatter fields - Unknown frontmatter fields
Name collisions (same name from different locations) warn and keep the first skill found. Name collisions (same name from different locations) warn and keep the first skill found.
## Example: Web Search Skill ## Example
``` ```
brave-search/ brave-search/
@ -265,16 +197,5 @@ cd /path/to/brave-search && npm install
## Skill Repositories ## Skill Repositories
For inspiration and ready-to-use skills: - [Anthropic Skills](https://github.com/anthropics/skills) - Document processing (docx, pdf, pptx, xlsx), web development
- [Pi Skills](https://github.com/badlogic/pi-skills) - Web search, browser automation, Google APIs, transcription
- [Anthropic Skills](https://github.com/anthropics/skills) - Official skills for document processing (docx, pdf, pptx, xlsx), web development, and more
- [Pi Skills](https://github.com/badlogic/pi-skills) - Skills for web search, browser automation, Google APIs, transcription
## Disabling Skills
CLI:
```bash
pi --no-skills
```
Use `--no-skills` to disable automatic discovery while keeping explicit `--skill` paths.

4
packages/coding-agent/docs/themes.md
View file

@ -139,13 +139,13 @@ vim ~/.pi/agent/themes/my-theme.json
- `name` is required and must be unique. - `name` is required and must be unique.
- `vars` is optional. Define reusable colors here, then reference them in `colors`. - `vars` is optional. Define reusable colors here, then reference them in `colors`.
- `colors` must define all 50 required tokens. - `colors` must define all 51 required tokens.
The `$schema` field enables editor auto-completion and validation. The `$schema` field enables editor auto-completion and validation.
## Color Tokens ## Color Tokens
Every theme must define all 50 color tokens. There are no optional colors. Every theme must define all 51 color tokens. There are no optional colors.
### Core UI (11 colors) ### Core UI (11 colors)