skill-helper

Create, validate, audit, review, refactor, optimize, and improve Agent Skills. Works with YAML frontmatter, SKILL.md docs, trigger-rich descriptions, slash commands, and automated validation + grading to keep skills consistent and discoverable.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "skill-helper" with this command: npx skills add jander99/skills/jander99-skills-skill-helper

Quick Start

Prerequisites:

  • Write access to skill directory (.opencode/skill/ or .claude/skills/)
  • Bash for validation script
  • Git configured (for author metadata)

Tools Used: Read, Write, Edit, Bash, Grep, Glob

Three Primary Workflows:

  1. Create a New Skill

    User: "Create a skill for [task]"
    Agent: Follows 8-step creation workflow
    

    See: references/creation-workflow.md

  2. Validate & Grade Existing Skill

    ./scripts/validate-skill.sh path/to/skill
    # Returns: 34 validation checks + 100-point grade
    

    See: references/validation-guide.md

    Rubric: references/grading-rubric.md

  3. Optimize for Discoverability

    User: "Make [skill-name] more discoverable"
    Agent: Analyzes description, adds verbs/keywords
    

    See: references/optimization-patterns.md

What I Do

  • Create new skills from scratch with templates
  • Validate skills against 33-check system (8 errors, 17 warnings, 8 suggestions)
  • Grade skills using 100-point rubric (A/B/C/D/F scale)
  • Optimize descriptions for auto-activation (5+ verbs, 10+ keywords)
  • Generate slash commands with proper naming (ak- prefix for agent-kit)
  • Audit existing skills for quality and compliance
  • Refactor skills for token efficiency (1000-2000 token sweet spot)
  • Bundle resources (assets/, references/, scripts/)
  • Provide skill templates and patterns

When to Use Me

Use this skill when you:

  • Create, write, or generate new Agent Skills
  • Validate, audit, or review existing skills
  • Grade or score skills using rubric
  • Optimize descriptions for trigger-richness
  • Fix validation errors (placeholders, XML, format issues)
  • Refactor skills that are too small (<1000 tokens) or too large (>3500 tokens)
  • Generate or fix slash commands
  • Check Context7 integration format
  • Prepare skills for publishing
  • Need skill templates or patterns
  • Convert documentation to skills

Core Principles

Auto-Activation: 5+ action verbs, 10+ keywords, "Use when" triggers, parenthetical grouping, task-centric framing

Progressive Loading: L1 (frontmatter ~100 tokens) → L2 (SKILL.md 1000-2000 tokens) → L3 (references/ unlimited)

Token Targets: Sweet spot 1000-2000 tokens; warn <500 or >3500

Validation + Grading: 34 checks + 100-point rubric; grade calculated first, used as validation input

Run: ./scripts/validate-skill.sh path/to/skill

Validation Overview

33 checks across 3 tiers:

  • 🔴 Errors (8): Must fix to publish
  • 🟡 Warnings (17): Should fix for effectiveness
  • 🟢 Suggestions (8): Polish & best practices

See references/validation-guide.md for complete details.

Grading Overview

100-point rubric: Description Quality (35%), Structure (25%), Content (20%), Technical (15%), Compliance (5%)

Grades: A (90-100), B (80-89), C (70-79), D (60-69), F (0-59)

See references/grading-rubric.md for scoring details.

Skill Patterns

Workflow Skills: Multi-step processes with phases (planning, deployment) Reference Skills: Domain knowledge with quick references (testing, security) Tool Skills: Specific operations with clear input/output (validation, formatting)

See references/creation-workflow.md for pattern details.

Quick Reference

ElementRuleExample
Name^[a-z0-9-]+$ (max 64)spring-boot-core
Description50-1024 chars, 5+ verbs, 10+ keywordsSee frontmatter above
Tokens1000-2000 ideal, >500 min, <3500 warn~200-400 lines
SectionsWhat I Do, When to Use Me, Quick StartRequired
Resourcesassets/, references/, scripts/Optional
Command{name}.md or ak-{name}.mdMatches skill name
GradeA-F scale (100 points)Target: B+ (85+) minimum

Examples

Create new skill:

User: "Create a skill for API validation"
→ 8-step workflow → Grade B+ (87/100)

Validate existing skill:

./scripts/validate-skill.sh .opencode/skill/my-skill
→ 0 errors, Grade A (92/100)

Optimize description:

User: "Make skill more discoverable"
→ Add verbs + keywords → Grade improves C (75) to A (93)

See references/creation-workflow.md for detailed examples.

Common Errors

ErrorSolution
"Invalid name format"Use lowercase, hyphens only
"Description too short"Add action verbs + keywords
"SKILL.md too large"Move content to references/
"No slash command"Create command file

See references/validation-guide.md for complete error catalog.

References

Load detailed guidance as needed:

ReferenceUse WhenContent
creation-workflow.mdCreating new skills8-step process, patterns, examples
validation-guide.mdUnderstanding validation34 checks explained, fixes
optimization-patterns.mdImproving descriptionsTrigger-rich patterns, testing
grading-rubric.mdUnderstanding grades100-point scoring breakdown

Related Skills

  • markdown-editor - For creating and editing SKILL.md markdown files
  • github-actions - For CI/CD integration of validation
  • github-project-manager - For tracking skill development tasks

Next Steps

Complete workflows & resources:

Templates:

Automation:

  • ./scripts/validate-skill.sh - Validation + grading in one command

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

retro

No summary provided by upstream source.

Repository SourceNeeds Review
General

markdown-editor

No summary provided by upstream source.

Repository SourceNeeds Review
Security

Skill Safe Install

L0 级技能安全安装流程。触发“安装技能/安全安装/审查权限”时,强制执行 Step0-5(查重→检索→审查→沙箱→正式安装→白名单)。

Registry SourceRecently Updated
3800Profile unavailable
Security

Skill Hunter

Find, evaluate, and install ClawHub skills. Semantic search across 10,000+ skills, security vetting before install, side-by-side comparison. The skill that m...

Registry SourceRecently Updated
5192Profile unavailable