implement-agent-skills
Skill1 starsChanged 9 months agoApache-2.0View on GitHub
Implement and maintain Claude Agent Skills with valid SKILL.md frontmatter, focused instructions, and progressive disclosure.
In this repository8 other files it gives its agents.
- implement-agent-teamsSkill
- implement-claude-extensionsSkill
- implement-hooksSkill
- implement-pluginSkill
- implement-sub-agentsSkill
- lint-fixSkill
- plugin-implementation-deprecatedSkill
- plugin-verificationSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Create or update skills/<skill-name>/SKILL.md files with deterministic scope and reusable references/scripts/templates.
- Distinctive: line 12
Assess complexity: Use decision framework to determine skill level needed (simple vs workflow)
- Distinctive: line 18
Validate: Check frontmatter and directory structure
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Implement Agent Skills
Create or update skills/<skill-name>/SKILL.md files with deterministic scope and reusable references/scripts/templates.
Workflow
- Assess complexity: Use decision framework to determine skill level needed (simple vs workflow)
- Start simple: Choose simplest skill type that meets requirements
- Define scope: Single-purpose objective with clear trigger criteria and success metrics
- Create/update:
skills/<name>/SKILL.mdwith valid frontmatter - Add supporting materials: References/scripts/templates for progressive disclosure
- Plan evaluations: Identify 20-50 test cases to validate skill behavior
- Validate: Check frontmatter and directory structure
- Cross-link: Connect to plugin packaging or umbrella guidance as needed
Progressive Disclosure
Best Practices (Anthropic Guidelines)
- Complexity decision framework:
../implement-claude-extensions/references/decision-framework.md - Context management patterns:
../implement-claude-extensions/references/context-management.md - Evaluation strategy:
../implement-claude-extensions/references/evaluation-strategy.md
Skill Design Patterns
- Skill directory conventions:
references/skill-structure.md - Required frontmatter fields:
references/skill-frontmatter.md - Progressive disclosure patterns:
references/skill-progressive-disclosure.md - Invocation and trigger guidance:
references/skill-invocation.md
Validation Tools
- Structure validator:
scripts/validate-skill-structure.sh - Frontmatter checker:
scripts/check-skill-frontmatter.sh
Tiered Templates (by Complexity)
- Level 1 - Simple Skill (Score 1-3):
assets/templates/skill-simple.md - Level 2 - Workflow Skill (Score 4-6):
assets/templates/skill-workflow.md - Base skill template:
assets/templates/skill-template.md - Skill with references example:
assets/templates/skill-with-references.md - Skill with scripts example:
assets/templates/skill-with-scripts.md
Related Skills
- Umbrella routing and component selection:
../implement-claude-extensions/SKILL.md - Plugin packaging/distribution:
../implement-plugin/SKILL.md
Sources
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

