agentsclimarketplace

Skill creator

Skill jscraik/Agent-Skills/Plugins/skill-factory/fixtures/budget-archive/2026-04-19/skills/scaffolding_templates/scaffolding_templates/skill-creator

Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.

Install
npx -y skills add jscraik/Agent-Skills --skill skill-creator

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Guide for creating effective skills. Use this skill when users need to create a new skill or reshape a draft skill package before hardening, benchmarking, or distribution.

SKILL.md

2.1 KB, as published. Nobody here has run it

Skill Creator

Use this skill to create or restructure a skill package so it is ready for hardening.

When to use

  • New skill creation from user intent.
  • Major reshape of an existing draft skill.
  • Packaging alignment across SKILL.md, references/, scripts/, and agents/openai.yaml.

Do not use

  • Release-hardening/evals: route to [[skill-builder]].
  • Install/import flows: route to [[skill-installer]].

Core Philosophy

  • Start with a narrow, executable scope.
  • Keep routing intent explicit in SKILL.md.
  • Preserve required context by relocating detail to references/.

Core workflow

  1. Confirm goal, trigger phrases, and category.
  2. Define smallest viable package boundary.
  3. Create/update required files with canonical names.
  4. Move deep details to references and keep SKILL.md route-focused.
  5. Run baseline validation commands and report outcomes.

Required output contract

Provide:

  • schema_version
  • mode
  • skill_path
  • changed_files
  • context_routes
  • validation_evidence
  • risks

Progressive disclosure policy

Never drop required context; relocate depth into references/ with explicit signposts.

Read when:

Anti-Patterns to Avoid

  • Building broad package scaffolds without a clear trigger surface.
  • Duplicating long policy text in SKILL.md instead of references.
  • Returning unvalidated scaffolds as production-ready outputs.

Constraints

  • Preserve user constraints exactly.
  • Use deterministic, reproducible edits.
  • Redact sensitive values in outputs.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.