Skip to content

unxed/f4 / .agents/skills/aif-skill-generator

aif-skill-generator

Flagged

Generate professional Agent Skills for AI agents. Creates complete skill packages with SKILL.md, references, scripts, and templates. Use when creating new skills, generating custom slash commands, or building reusable AI capabilities. Validates against Agent Skills specification.

FileKindSize
SKILL.mdskill md23.6 KB
references/BEST-PRACTICES.mdmarkdown5.3 KB
references/EXAMPLES.mdmarkdown5.0 KB
references/LEARN-MODE.mdmarkdown7.1 KB
references/SECURITY-SCANNING.mdmarkdown4.6 KB
references/SPECIFICATION.mdmarkdown3.0 KB
scripts/cleanup-blocked-skill.pyexecutablescript23.4 KB
scripts/search-skills.pyexecutablescript2.9 KB
scripts/security-scan.pyexecutablescript27.9 KB
scripts/validate.shexecutablescript5.5 KB
templates/basic.mdmarkdown511 B
templates/dynamic-context.mdmarkdown1.4 KB
templates/research.mdmarkdown956 B
templates/task.mdmarkdown807 B
templates/visual.mdmarkdown1.9 KB

references/SPECIFICATION.md

View on GitHub
# Agent Skills Specification Reference

Complete specification from https://agentskills.io/specification

## Directory Structure

```
skill-name/
├── SKILL.md          # Required: Main instructions
├── scripts/          # Optional: Executable code
├── references/       # Optional: Additional docs
└── assets/           # Optional: Static resources
```

## SKILL.md Format

### Required Frontmatter

```yaml
---
name: skill-name
description: A description of what this skill does and when to use it.
---
```

### All Frontmatter Fields

| Field | Required | Constraints |
|-------|----------|-------------|
| `name` | Yes | Max 64 chars, lowercase, hyphens only, no consecutive hyphens |
| `description` | Yes | Max 1024 chars, non-empty |
| `license` | No | License name or file reference |
| `compatibility` | No | Max 500 chars, environment requirements |
| `metadata` | No | Key-value pairs for custom data |
| `allowed-tools` | No | Space-delimited tool list |

### Agent Extensions

| Field | Description |
|-------|-------------|
| `argument-hint` | Shown in autocomplete: `[issue-number]` |
| `disable-model-invocation` | `true` = only user can invoke |
| `user-invocable` | `false` = only model can invoke |
| `context` | `fork` = run in subagent |
| `agent` | Subagent type: Explore, Plan, general-purpose |
| `model` | Model override: sonnet, opus, haiku |
| `hooks` | Lifecycle hooks configuration |

## Name Field Rules

Valid:
- `pdf-processing`
- `data-analysis`
- `code-review`

Invalid:
- `PDF-Processing` (uppercase)
- `-pdf` (starts with hyphen)
- `pdf--processing` (consecutive hyphens)
- `pdf_processing` (underscores)

## Description Best Practices

Good:
```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.
```

Bad:
```yaml
description: Helps with PDFs.
```

## Tool Specification Syntax

```yaml
# Basic tools
allowed-tools: Read Write Grep Glob

# Bash with patterns
allowed-tools: Bash(git *) Bash(npm run *) Bash(docker *)

# Combined
allowed-tools: Read Write Bash(git *) Bash(python scripts/*.py)
```

## String Substitutions

| Variable | Description |
|----------|-------------|
| `$ARGUMENTS` | All arguments passed to skill |
| `$ARGUMENTS[N]` | Argument by index (0-based) |
| `$N` | Shorthand for $ARGUMENTS[N] |
| `${CLAUDE_SESSION_ID}` | Current session ID |
| exclamation+backtick+cmd+backtick | Shell command output injection |

## Progressive Disclosure

Token budgets:
1. **Metadata** (~100 tokens): name + description loaded at startup
2. **Instructions** (<5000 tokens): Full SKILL.md when activated
3. **Resources** (as needed): Supporting files on demand

Keep SKILL.md under 500 lines.

## Validation Checklist

- [ ] `name` matches directory name
- [ ] `name` follows naming rules
- [ ] `description` is 1-1024 characters
- [ ] `description` explains what AND when
- [ ] Frontmatter YAML is valid
- [ ] Body under 500 lines
- [ ] File references are relative
- [ ] Scripts are executable
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall