AgentStack
SKILL verified MIT Self-run

Skill Authoring

skill-jakesterns-agent-skills-skill-authoring · by jakesterns

Helps create, review, and improve agent skill markdown with strong trigger descriptions, concise workflows, metadata, validation, and examples.

No reviews yet
0 installs
18 views
0.0% view→install

Install

$ agentstack add skill-jakesterns-agent-skills-skill-authoring

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Skill Authoring? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Skill Authoring

Use this skill when creating or improving an AI agent skill, prompt package, or reusable markdown workflow.

Inputs

  • Skill goal, target users, expected trigger phrases, examples, draft markdown, or existing skill folder
  • Target providers or compatibility requirements

Steps

  1. Clarify the task the skill should handle and when an agent should use it.
  2. Write a description that includes the action, domain, and trigger conditions.
  3. Keep the body concise: inputs, steps, outputs, and guidelines.
  4. Add tags that improve search and filtering.
  5. Add provider metadata when the skill is compatible across agents.
  6. Move detailed examples or long reference material into reference files when needed.
  7. Validate frontmatter, file naming, category placement, and discoverability.
  8. Review whether the skill gives useful procedural knowledge rather than generic advice.

Output

Return:

  • Improved skill markdown or review notes
  • Metadata recommendations
  • Trigger and searchability improvements
  • Validation issues
  • Suggested tests or example prompts

Guidelines

  • Prefer concrete workflows over broad principles.
  • Avoid bloated skills that consume context without improving execution.
  • Make the skill useful to an autonomous agent, not just a human reader.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.