agent-skill-best-practices
Provides best practices for writing Agent Skills. Use when creating or refining SKILL.md content.
Browse published AI skills maintained by drevantonder. Compare skill descriptions and follow each source repository for setup instructions.
Indexed skills
10Repository stars across indexed skills
10Repository forks
0Average repository stars per indexed skill
1Repository stars may repeat across skills from the same repository.
Provides best practices for writing Agent Skills. Use when creating or refining SKILL.md content.
Create change proposals and delta specs for capability-scoped updates.
Use this skill to evaluate implementation quality, track technical debt via an append-only log, and generate a fix queue (prd.json) when a change does not meet the specification.
Archive completed changes and optionally sync specs first.
Use this skill to orchestrate autonomous implementation loops with ralph-tui. It guides you through creating a bite-sized, spec-aligned task list (prd.json) and setting up the execution environment.
Guidelines for writing small, stable AGENTS.md files. Use when creating, refactoring, or reviewing AGENTS.md.
Sync change delta specs into current truth using intelligent merge.
Adjust the spec driven development workflow to reduce drift and duplication.
Use git-worktree-runner (gtr) for isolated worktree workflows.
Use this skill to reject an implementation, extract learnings, and update change artifacts (proposal, specs, prd.json) before cleaning up the worktree for a retry.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.