Back to list
ingpoc

skill-creator

by ingpoc

5🍴 0📅 Jan 2, 2026

SKILL.md


name: skill-creator description: "Use when creating a new skill, updating an existing skill, or learning skill best practices. Load for extending Claude's capabilities with specialized workflows, tool integrations, or domain expertise. Covers skill anatomy, progressive disclosure (98% token savings), and the critical description-as-trigger pattern." keywords: skill, create, template, workflow, progressive-disclosure license: Complete terms in LICENSE.txt

Skill Creator

Create modular, token-efficient skills that extend Claude's capabilities.

Critical: Description = Trigger

The description field in frontmatter is how Claude decides when to load a skill.

LocationClaude SeesTiming
description (frontmatter)Always in contextBefore trigger
"When to Use" (body)Only after triggeredToo late!

Pattern:

---
name: pdf-toolkit
# GOOD - trigger info in description
description: "Use when processing PDFs, extracting forms, merging documents, or filling PDF forms. Load for any PDF manipulation task."
keywords: pdf, extract, merge, forms
---

Anti-pattern:

---
name: pdf-toolkit
# BAD - trigger info only in body (Claude can't see until AFTER trigger)
description: "PDF manipulation toolkit"
---

## When to Use  ← Claude never sees this before deciding to trigger!

Skill Anatomy

skill-name/
├── SKILL.md (required)      # Workflow + metadata (<5k words)
├── scripts/ (optional)      # Executable code (0 tokens when run)
├── references/ (optional)   # Docs loaded as needed
└── assets/ (optional)       # Output resources (never loaded)

Resource Types

TypeWhen to UseToken CostExamples
scripts/Repeated code, deterministic0 (executes)rotate_pdf.py, validate.sh
references/Schemas, APIs, patternsOn-demandschema.md, api_docs.md
assets/Templates, images0 (output only)logo.png, template.docx

Key insight: Scripts execute WITHOUT loading into context = 0 tokens.

Progressive Disclosure (3 Levels)

LevelWhatWhen LoadedToken Budget
1. Metadataname + descriptionAlways~100 words
2. SKILL.md bodyInstructionsOn trigger<5k words
3. Resourcesscripts/references/assetsAs neededUnlimited

Result: 98% token savings vs loading everything upfront.

Skill Creation Workflow

1. Gather Examples

Ask user:

  • What functionality should the skill support?
  • Example usage scenarios?
  • What triggers this skill?

2. Plan Resources

QuestionMaps To
What code gets rewritten?scripts/
What schemas get rediscovered?references/
What boilerplate gets recreated?assets/

3. Initialize

scripts/init_skill.py <skill-name> --path <output-directory>

4. Write SKILL.md

Order:

  1. Write description (with ALL trigger scenarios)
  2. Add keywords
  3. Write concise body (<5k words)
  4. Reference bundled resources

Frontmatter checklist:

  • name: lowercase, hyphens
  • description: starts with "Use when...", includes ALL triggers
  • keywords: discovery tags

Body checklist:

  • Instructions (imperative form)
  • Resource table (what to load when)
  • Quick reference (common commands)

5. Validate & Package

scripts/quick_validate.py <path/to/skill>
scripts/package_skill.py <path/to/skill> [output-dir]

6. Iterate

Test on real tasks → identify gaps → update → test again.

Key Rules

RuleWhy
Description = triggerClaude decides from metadata, not body
Scripts = 0 tokensExecute without loading into context
Tables over prose30-50% token savings
<5k words in SKILL.mdMove details to references/
keywords for discoveryHelps Claude find relevant skills

References

FileLoad When
references/best_practices.mdWriting style, organization
references/progressive_disclosure.mdToken efficiency patterns
references/examples.mdSkill structure examples

Score

Total Score

50/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

0/10
説明文

100文字以上の説明がある

0/10
人気

GitHub Stars 100以上

0/15
最近の活動

3ヶ月以内に更新がある

0/10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

0/5

Reviews

💬

Reviews coming soon