Skill test skill for AI agents

​

When your agent uses it

• A contributor wants to lint a Summer skill before commit, audit the whole library, or check a behavioral spec assertion
• Running the structural lint and behavioral spec assertions for one skill or the whole library

​

Install

npx -y summer-engine@latest skills install skill-test --agent claude-code

​

The skill

​

Mode: static — Structural lint (default for “test this skill”)

1. Frontmatter completeness. name, description, license, compatibility, category present. name matches the directory name.
2. SKILL.md length. ≤ 500 lines (progressive disclosure: push detail into references).
3. MCP-preferred + file-edit-fallback. If the skill mutates scenes or resources, body must show both:
   • At least one summer_* MCP tool example.
   • At least one file-edit fallback block (e.g., raw .tscn snippet) OR an explicit “no fallback for this — Summer MCP required” note.
4. Collaborative protocol. If the skill triggers user-visible writes, body must contain at least one of: May I, I'm about to, Continue?, OK?, Proceed?. Skills that only inspect/read are exempt.
5. Template-id resolved. If the skill’s frontmatter declares template-id: <id>, that id must exist in the template registry: library/templates/<id>/resource.yaml (see library/templates/README.md).
6. Behavioral spec. If the skill has a spec (evals/skills/specs/<slug>.md or tests/spec.md in the skill folder), it has at least one ## Case heading. A missing spec is a WARN, not a FAIL.
7. Links stay inside the skill folder. Every relative link (](./references/...), ](./examples/...)) must point at an existing file in the skill’s own folder (FAIL if broken). summer setup copies each skill folder alone, so a path that climbs out of it (../) breaks after install: name a shared reference by its library id (summer_docs_read id reference/<slug>) and another skill by its bare slug (design-mechanic).

skill: <slug>
  PASS  (1) frontmatter complete
  PASS  (2) length 217 / 500 lines
  FAIL  (3) no MCP-preferred example found in body
  PASS  (4) collaborative protocol present
  PASS  (5) template-id resolved
  PASS  (6) behavioral spec has cases
  PASS  (7) all relative links resolve

6 PASS / 1 FAIL — fix item 3 before commit.

​

Mode: spec — Behavioral spec runner

1. Lay out the Fixture (starting state, available tools).
2. Read the Input (user prompt).
3. Reason: given the skill’s instructions and this fixture, would the agent follow the Expected MCP tool sequence?
4. For each assertion under **Assertions:**, mark [x] if the skill’s instructions would satisfy it, [ ] if not, with a one-line reason.

​

Mode: audit — Whole library report

1. Run static mode on the skill.
2. Note any last-tested: field in the SKILL.md frontmatter (optional).
3. Flag skills failing static checks.

​

When to use which mode

​

Collaborative protocol

​

See also

• summer_docs_read id reference/collaborative-protocol
• the template registry: library/templates/<id>/resource.yaml (see library/templates/README.md)
• tests/runner.md
• evals/skills/specs/ — per-skill behavioral specs

​

From a shell

​

Related skills

• skill-create: Bootstrap a new Summer library skill (library/skills/<slug>/ with resource.yaml and SKILL.md), frontmatter, and stub sections.
• skill-improve: Upgrade an underperforming Summer skill — run it against a behavioral spec with and without changes via a parallel-eval harness; ship the winner.