kage_skills

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that only grounded, non-stale packets are used, files are written to .claude/skills/, and dry_run previews without side effects. However, it does not specify overwrite behavior or return value.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three concise sentences front-load the core purpose, add a quality constraint, and explain key parameters. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers purpose, quality filtering, and two parameters. Missing details on file overwrite behavior, permissions, and return value are acceptable for this tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the description explains dry_run (preview mode) and dir (output directory override) beyond the schema. project_dir is implied as the repository root. Minimal explicit detail for project_dir leaves slight ambiguity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool codifies repo memory into git-native SKILL.md files in .claude/skills/, distinguishing it from sibling tools like kage_context or kage_decisions that handle other aspects of knowledge management.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for creating skills from verified memory but does not explicitly state when to use this tool versus siblings or provide exclusion criteria. The dry_run parameter is mentioned for previewing without writing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.