anthropic-skill-creator

Original：🇺🇸 English

Translated

1 scriptsChecked / no sensitive code detected

Design, review, and improve Claude/Codex skills based on Anthropic's "The Complete Guide to Building Skills for Claude". Use when creating a new skill, rewriting SKILL.md frontmatter and workflows, fixing under-triggering or over-triggering, designing scripts/references/assets, building test cases, or preparing a skill for upload/distribution.

1installs

Sources-hiraoku/skills-factory

Added on2026-02-15

NPX Install

npx skill4agent add s-hiraoku/skills-factory anthropic-skill-creator

SKILL.md Content

View Translation Comparison →

Create Skills

Build skills that trigger correctly, execute reliably, and stay concise.

Core Principles

Use progressive disclosure:
- Frontmatter (
```
name
```
  ,
```
description
```
  ) for trigger selection.
- ```
SKILL.md
```
  body for core workflow.
- ```
references/
```
  for deep details loaded only when needed.
Keep skills composable: avoid assumptions that this is the only active skill.
Prefer deterministic scripts for fragile validation logic.

Workflow

Define 2-3 concrete use cases.
Draft trigger-strong frontmatter.
Design reusable resources (
```
scripts/
```
,
```
references/
```
,
```
assets/
```
).
Write actionable instructions and error handling.
Run triggering/functional/performance tests.
Iterate based on under-trigger/over-trigger signals.

1) Define Use Cases

Capture for each use case:

User phrasing (what they actually say)
Intended result
Multi-step workflow and required tools (built-in and/or MCP)
Failure points that need guardrails

If use cases are vague, ask targeted follow-up questions before authoring.

2) Frontmatter Design (Most Important)

Write only what is needed to trigger correctly.

Required fields:

```
name
```
: kebab-case, matches folder name
```
description
```
: include BOTH
- What the skill does
- When to use it (trigger phrases/context/file types)

Description formula:

[What it does] + [When to use it] + [Key capabilities]

Good pattern:

"Processes PDF legal documents for contract review. Use when users ask for clause extraction, risk flags, or redline summaries from .pdf contracts."

Bad pattern:

"Helps with projects."

Precision controls:

Add negative triggers to reduce over-triggering.
Mention relevant file types when applicable.
Keep wording aligned with real user phrases from use cases.

3) Resource Plan

```
scripts/
```
: deterministic checks/transforms used repeatedly
```
references/
```
: large docs, domain logic, variant-specific guidance
```
assets/
```
: templates and artifacts used in outputs

Rules:

Keep
```
SKILL.md
```
compact; link to
```
references/
```
.
Avoid extra docs in skill folder (
```
README.md
```
, changelog, etc.).

4) Instruction Writing

Write imperative, testable steps.

Include:

Clear step order and dependencies
Validation checkpoints
Common errors with concrete fixes
Example user inputs and expected outputs

For critical checks, prefer scripts over prose-only checks.

5) Test Protocol

Run these three test groups.

A. Triggering Tests

Should trigger on obvious requests
Should trigger on paraphrased requests
Should NOT trigger on unrelated requests

Target benchmark:

Trigger on ~90% of relevant prompts in a 10-20 prompt suite

B. Functional Tests

Validate:

Correct outputs
Tool/API call success
Error handling paths
Edge cases

C. Performance Comparison

Compare with vs without skill:

Number of clarification turns
Failed tool/API calls
Token usage
End-to-end completion quality

6) Iteration Rules

Under-triggering signals:

Skill does not load when expected
Users keep manually invoking it

Fix:

Add clearer trigger phrases and technical terms to
```
description
```
.

Over-triggering signals:

Skill loads for unrelated requests

Fix:

Add negative triggers and tighten scope language.

Execution issues:

Inconsistent outputs, retries, user corrections

Fix:

Tighten instructions, add explicit validations, and script critical checks.

Troubleshooting Quick Guide

Upload fails with missing
```
SKILL.md
```
: file must be exactly
```
SKILL.md
```
.
Invalid frontmatter: verify YAML delimiters
```
---
```
and valid syntax.
Invalid skill name: use lowercase kebab-case.
Skill not followed: move critical instructions to top and make them concrete.
Slow behavior: move long content to
```
references/
```
; reduce enabled skills.

Packaging

Validate and package before distribution:

bash

python3 .agents/skills/skill-creator/scripts/quick_validate.py <skill-dir>
python3 .agents/skills/skill-creator/scripts/package_skill.py <skill-dir>

References

```
references/checklist.md
```
```
references/prompt-templates.md
```
```
references/patterns.md
```
```
references/source.md
```
: source PDF and extracted principles
```
references/trigger-examples.md
```
: trigger/non-trigger examples for description tuning
```
references/failure-remedies.md
```
: failure patterns and minimum effective fixes

anthropic-skill-creator

NPX Install

Tags

SKILL.md Content

Create Skills

Core Principles

Workflow

1) Define Use Cases

2) Frontmatter Design (Most Important)

3) Resource Plan

4) Instruction Writing

5) Test Protocol

A. Triggering Tests

B. Functional Tests

C. Performance Comparison

6) Iteration Rules

Troubleshooting Quick Guide

Packaging

References