Use Cases
When a team discovers that an agent repeatedly exhibits the same erroneous behavior on certain tasks (e.g., skipping tests, not following specifications), use this skill to create corresponding skill documentation. First design pressure scenarios and let the agent execute without the skill, documenting failure patterns (RED). Then write SKILL.md providing clear guidance and rules (GREEN). Verify the agent follows new rules with the same scenarios (PASS). Finally iterate on optimization. This ensures each skill document truly changes agent behavior.
When existing skill documentation exists but the agent fails to load or use it correctly, use this skill's Skill Discovery Optimization (SDO) principles to optimize. Focus on optimizing the description field to ensure it only contains triggering conditions without summarizing workflows (preventing agents from bypassing full document reading), add keyword coverage (error messages, symptoms, tool names), and adopt verb-first naming conventions. Also perform token efficiency optimization, compressing redundant content and using cross-references instead of repeated explanations.
Skill File
Domains
Forms
Mechanism
Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.
Maps the TDD RED-GREEN-REFACTOR cycle to skill creation:
Also follows these principles:
creating-skills.Skill Relationships
Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.
Tier 1 · These Skills Use Me
Tier 2 · Current Skill
Tier 3 · I Use These Skills
Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.