plugin-build-smoke-regression
Catch packaging-script regressions by asserting the real script exit path and current overlay surface.
51
40%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.squad/skills/plugin-build-smoke-regression/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is overly technical and opaque, using domain-specific jargon without explaining concrete actions or providing trigger guidance. It fails to communicate what the skill does in understandable terms and completely lacks a 'Use when...' clause, making it very difficult for Claude to know when to select it.
Suggestions
Rewrite using plain language that describes concrete actions, e.g., 'Runs regression tests on packaging scripts to verify exit codes and overlay configurations.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about testing packaging scripts, verifying build outputs, or checking script exit codes.'
Include natural keywords users might say, such as 'packaging', 'build script', 'regression test', 'exit code', 'overlay' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, jargon-heavy language like 'asserting the real script exit path' and 'current overlay surface' without listing concrete, understandable actions. It's unclear what specific tasks this skill performs. | 1 / 3 |
Completeness | There is no explicit 'Use when...' clause or equivalent trigger guidance. The 'what' is vaguely stated and the 'when' is entirely missing, making it unclear when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | The terms used ('script exit path', 'overlay surface', 'packaging-script regressions') are highly technical jargon that users would not naturally say when seeking help. No common or natural trigger terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | The description is niche enough in its domain (packaging scripts, overlay surface) that it's unlikely to broadly conflict with many other skills, but the vagueness still makes it hard to distinguish precisely from other testing or CI-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a focused, well-structured skill that efficiently communicates domain-specific testing patterns for packaging script regressions. Its main weakness is the lack of executable code examples—the patterns and examples reference specific files and test names but don't provide copy-paste ready test code or assertion snippets. The anti-patterns section adds good guardrails.
Suggestions
Add a concrete, executable code snippet showing a minimal smoke test that asserts exit code 0 and validates the ASCII summary output block.
Include a brief example assertion showing how to check for current assets being present AND legacy files being absent (e.g., a few lines of C# test code from the referenced test file).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every bullet point conveys a distinct, non-obvious testing insight specific to this packaging context. No unnecessary explanations of basic concepts. | 3 / 3 |
Actionability | Provides concrete guidance on what to assert (exit code 0, ASCII summary, current vs legacy file names) and references specific test files, but lacks executable code snippets or copy-paste ready test templates. The patterns are directional rather than fully executable. | 2 / 3 |
Workflow Clarity | The patterns describe what tests should check but don't present a clear sequenced workflow for creating or running these tests. There's no explicit validation checkpoint or feedback loop for verifying the tests themselves catch regressions. | 2 / 3 |
Progressive Disclosure | For a simple, focused skill under 50 lines, the content is well-organized with clear sections (Context, Patterns, Examples, Anti-Patterns). References to specific test files serve as natural pointers for deeper exploration without unnecessary nesting. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sbroenne/mcp-server-excel
- Commit
468809e
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.