New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Skill Authoring

by a-streetcoder in a-streetcoder/agent-deck

Create or improve Agent Deck/Pi skills, including where to save them, SKILL.md frontmatter, simple vs modular structure, and validation.

MITAuto-check passedAgent Workflows

Install Skill Authoring

skills CLI
$ npx skills add a-streetcoder/agent-deck --skill skill-authoring -a claude-code

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

GitHub CLI
$ gh skill install a-streetcoder/agent-deck skill-authoring --agent claude-code

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

Manual copy
$ git clone --depth 1 https://github.com/a-streetcoder/agent-deck.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-deck/bundled-skills/skill-authoring .claude/skills/skill-authoring && rm -rf skills-src

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

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

Facts

Skill name
skill-authoring
GitHub stars
118
Token cost
~1.8k tokens
SKILL.md length
873 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Create or improve Agent Deck/Pi skills, including where to save them, SKILL.md frontmatter, simple vs modular structure, and validation.

  • Works in 9 steps: Choose a short, stable kebab-case skill… → Create new skills under… → Decide whether the skill should be… → …
  • Tasks that involve Skill authoring
  • SKILL.md covers Choose catalog location and…, Basic format, Simple skill pattern and Modular skill pattern, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Skill Authoring is an agent skill from a-streetcoder/agent-deck. Create or improve Agent Deck/Pi skills, including where to save them, SKILL.md frontmatter, simple vs modular structure, and validation.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Skill authoring. The licence is MIT.

When your agent uses it

  • Tasks that involve Skill authoring

Example prompts

  • “/skill-authoring”

Workflow steps

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

  1. Choose a short, stable kebab-case skill name.
  2. Create new skills under ~/.pi/agent/skills//SKILL.md unless the user explicitly requested an external imported-by-reference source.
  3. Decide whether the skill should be enabled for All Projects by default or left unassigned in the catalog; ask if unclear.
  4. Write frontmatter with a specific use-triggering description.
  5. Decide whether the skill should be simple or modular.
  6. For simple skills, keep the workflow in SKILL.md.
  7. For modular skills, keep SKILL.md as a router and create focused reference files.
  8. Validate the directory name, frontmatter name, description, and Markdown structure.
  9. Tell the user where the skill was created and whether it is Default / All Projects, Project-assigned, Agent-assigned, or still unassigned…

What it can do on your machine

Read from SKILL.md and the folder at commit 9efbe6c. It shows what the files ask for, not the result of running them.

  • Tool permissions

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

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

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

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

Skill Authoring loads about 1.8k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 873 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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

Safety

Auto-check passed

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

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

SKILL.md

The full file from a-streetcoder/agent-deck at commit 9efbe6c, republished under its MIT licence (© a-streetcoder). 873 words, ~1,750 tokens.

Download SKILL.mdSave it as .claude/skills/skill-authoring/SKILL.md (or your agent's skills folder).
name
skill-authoring
description
Create or improve Agent Deck/Pi skills, including where to save them, SKILL.md frontmatter, simple vs modular structure, and validation.

Skill authoring

Use this skill when the user wants to create, convert, review, or validate an Agent Deck/Pi skill.

Choose catalog location and assignment

Before creating a new skill, explicitly ask the user whether the skill should be enabled for all projects by default unless they already gave an unambiguous preference. Do not ask whether it is a "personal" skill: Agent Deck treats user-authored skills as catalog resources, then controls runtime use through assignment metadata.

For new user-authored skills, create the skill in the normal global Agent Deck/Pi skills catalog:

text
~/.pi/agent/skills/<skill-name>/SKILL.md

Then explain or apply the requested assignment:

  • Default / All Projects — the skill is injected into parent sessions for every project.
  • Unassigned catalog skill — the skill is visible in the catalog but is not injected until the user manually assigns it to All Projects, a specific project, or a native agent.
  • Project assignment — the skill is injected into parent sessions for one project.
  • Agent assignment — the skill is injected into one native subagent.

Do not infer project-local just because the current working directory is a repository. Agent Deck no longer discovers project-local .pi/skills as a resource catalog source.

Use a non-standard external path only when the user explicitly asks to keep an existing skill or skill collection where it already lives. Warn that Agent Deck will not discover that skill unless the path is imported through Agent Deck’s + import flow; imports are catalog references, not copies:

text
/path/to/skills/<skill-name>/SKILL.md

Read compatibility locations such as .agents/skills/<skill-name>/SKILL.md when reviewing existing skills, but do not create new project-local skills there. Create new skills in the global catalog path unless the user explicitly asks for an external imported-by-reference source.

After creating a skill, tell the user where it was saved and whether it is Default / All Projects, Project-assigned, Agent-assigned, or still unassigned in the catalog.

Ask the user when any of these are unclear:

  • whether the new skill should be enabled for All Projects by default or left unassigned in the catalog for manual assignment
  • whether the user really wants a non-standard external path, with a warning that Agent Deck will not discover it unless configured/imported as an external skill
  • the skill's scope, activation trigger, or expected workflow
  • whether a complex skill should be modular or kept simple

Basic format

Use a directory named exactly like the skill, containing SKILL.md:

text
<skill-name>/
  SKILL.md

Every SKILL.md needs frontmatter at the top. Keep the description specific enough that the model knows when to use the skill:

md
---
name: my-skill
description: Use when creating or validating Foo configuration for Bar projects.
---

# My Skill

Use this skill when the user asks for Foo configuration help.

Rules:

  • name is required.
  • description is required and should explain when to use the skill, not just what it is.
  • The directory name must match name.
  • Use lowercase letters, numbers, and hyphens for the skill name.
  • Keep the skill focused on one domain or workflow.
  • Do not put permanent project instructions in a skill when AGENTS.md or project documentation is the right home.

Simple skill pattern

Use a single-file skill when the instructions are short and likely to fit comfortably in context:

text
my-skill/
  SKILL.md

Good contents:

  • when to use the skill
  • required inputs or files
  • concise workflow
  • one or two examples
  • validation checklist
Show full SKILL.md (369 more words)Show less

Modular skill pattern

Use a modular skill when the guidance is broad, reference-heavy, or split across domains. Keep SKILL.md as a router and put detailed guidance in sibling files or subdirectories:

text
domain-expert/
  SKILL.md
  workflows/
    create.md
    review.md
  references/
    concepts.md
    examples.md
  checklists/
    validation.md
    release.md

The top-level SKILL.md should:

  • explain activation criteria
  • list available modules
  • tell the model which files to read for each user need
  • avoid copying all module content into the top-level file

Use relative paths in module lists so the model can read only the relevant files:

md
## Available Modules

Read relevant module files based on the user's request:

### workflows/
- `create.md` - Creation workflow and required decisions
- `review.md` - Review workflow and common issues

### references/
- `concepts.md` - Background concepts and terminology
- `examples.md` - Representative examples

### checklists/
- `validation.md` - Validation steps before completion
- `release.md` - Release or handoff checklist

This keeps the initial skill small and delegates token-heavy reference material to files the model reads only when needed.

Authoring workflow

  1. Choose a short, stable kebab-case skill name.
  2. Create new skills under ~/.pi/agent/skills/<skill-name>/SKILL.md unless the user explicitly requested an external imported-by-reference source.
  3. Decide whether the skill should be enabled for All Projects by default or left unassigned in the catalog; ask if unclear.
  4. Write frontmatter with a specific use-triggering description.
  5. Decide whether the skill should be simple or modular.
  6. For simple skills, keep the workflow in SKILL.md.
  7. For modular skills, keep SKILL.md as a router and create focused reference files.
  8. Validate the directory name, frontmatter name, description, and Markdown structure.
  9. Tell the user where the skill was created and whether it is Default / All Projects, Project-assigned, Agent-assigned, or still unassigned in Agent Deck.

Agent Deck assignment notes

Do not over-explain runtime internals in ordinary user-facing skills. Only mention assignment when it affects what the user must do next:

  • Bundled or external catalog skills are not injected until assigned.
  • Default assignment makes the skill available to parent sessions across projects.
  • Project assignment makes it available to parent sessions for one project.
  • Agent assignment makes it available to one native subagent.
  • Native subagents with assigned skills need read in their tool allowlist so the skill file can be loaded.

Validation checklist

  • The file is named SKILL.md.
  • The parent directory matches name:.
  • Frontmatter is the first content in the file.
  • description: is present, specific, and use-oriented.
  • Simple skills are not over-engineered.
  • Modular skills list their modules clearly and use relative paths.
  • Large reference content is delegated to focused files instead of pasted into SKILL.md.
  • The final response states the file path and any needed Agent Deck assignment.

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

Files

Just SKILL.md in agent-deck/bundled-skills/skill-authoring of a-streetcoder/agent-deck.

Open the folder on GitHubat commit 9efbe6c

Compare with similar skills

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

Skill Authoring compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Authoring this skilla-streetcoder/agent-deck118—~1.8kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official38k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 11 repos~3.5k tokens
    Agent WorkflowsAuto-check passed

  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    38k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    38k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed

  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    66k GitHub stars~1k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from a-streetcoder/agent-deck

  • Agent Authoring

    a-streetcoder/agent-deck

    A skill your agent uses when creating or reviewing Agent Deck agents, including frontmatter, tools, supervisor behavior, continuation behavior, and skill assignment.

    118 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

  • MCP Install Helper

    a-streetcoder/agent-deck

    A skill your agent uses when helping users install, import, repair, or verify MCP server configurations in Agent Deck.

    118 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

  • Loop Authoring

    a-streetcoder/agent-deck

    A skill your agent uses when creating, refining, or validating Agent Deck loops, especially to guide users iteratively through loop goal, structure, agents, write target, and safety choices.

    118 GitHub stars~1.6k tokensUpdated 2 mo ago
    Auto-check passed

  • Prompt Authoring

    a-streetcoder/agent-deck

    Create or improve Agent Deck/Pi prompt templates for reusable parent-session workflows.

    118 GitHub stars~721 tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Skill Authoring

What does Skill Authoring do?

Create or improve Agent Deck/Pi skills, including where to save them, SKILL.md frontmatter, simple vs modular structure, and validation. Skill Authoring is an agent skill from a-streetcoder/agent-deck.md frontmatter, simple vs modular structure, and validation.

When should I use Skill Authoring?

Skill Authoring fits situations like: tasks that involve Skill authoring.

How do I install Skill Authoring in Claude Code?

Run `npx skills add a-streetcoder/agent-deck --skill skill-authoring -a claude-code`. Or copy the skill folder (agent-deck/bundled-skills/skill-authoring in a-streetcoder/agent-deck) into .claude/skills/skill-authoring in your project. Claude Code loads it when a task matches its description.

How do I install Skill Authoring in Codex?

Run `npx skills add a-streetcoder/agent-deck --skill skill-authoring -a codex`. Or copy the skill folder (agent-deck/bundled-skills/skill-authoring in a-streetcoder/agent-deck) into .agents/skills/skill-authoring in your project. Codex loads it when a task matches its description.

Can I use Skill Authoring in Cursor, Gemini CLI or GitHub Copilot?

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

What does Skill Authoring need to run?

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

Does Skill Authoring access the network?

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

Is Skill Authoring safe to install?

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

What licence does Skill Authoring use?

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

How many tokens does Skill Authoring use?

About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Skill Authoring?

Skills that share tags, products or a category with Skill Authoring: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Authoring?

a-streetcoder (a GitHub organization) maintains it in a-streetcoder/agent-deck, which has 118 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 1, 2026.

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