CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-schema-enum-regression

Keep generated MCP schemas strict-client compatible by avoiding nullable enum signatures.

47

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is notably concise and well-structured with concrete file references and clear anti-pattern guardrails, but it is instructional rather than copy-paste executable and lacks an explicit validate→fix→retest feedback loop for what is a regression-test workflow. No bundle files exist to support progressive disclosure beyond the inline pointers.

Suggestions

Add an explicit validation checkpoint tying the regression test to the fix, e.g. 'Run GeneratedToolSchemaEnumRegressionTests; if it fails on a nullable enum, fix the generator and re-run until green.'

Include a short copy-paste-ready snippet (the test invocation command or the exact assertion that catches the null sentinel) to lift actionability from 2 to 3.

Move the detailed generator/parse logic into a references/ file and link to it from SKILL.md so progressive disclosure is genuinely one level deep rather than all inline.

DimensionReasoningScore

Conciseness

The body is lean throughout — every line is a concrete directive or a real file path with no concept explanations Claude would already know, fitting the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

Guidance is concrete and points to real files (e.g. 'required `action` enum, optional enum-like inputs as strings, local parse'), but it is instruction-style description rather than copy-paste-ready executable code or commands, so it is actionable but not fully copy-paste ready.

2 / 3

Workflow Clarity

The Patterns list implies a sensible sequence (test the contract → treat nullable enums as the hazard → keep `action` required → emit others as strings → scan every enum property) and the Anti-Patterns act as guardrails, but there is no explicit validation/checkpoint step linking the test to a fix-and-retest loop, capping workflow clarity at 2.

2 / 3

Progressive Disclosure

The body is well-organized into Context/Patterns/Examples/Anti-Patterns sections and the Examples point to real one-level-deep source files, but since no references/scripts/assets bundle directories exist and no files are split out, it is not leveraging progressive disclosure beyond inline pointers, matching 'some structure but could be better organized'.

2 / 3

Total

9

/

12

Passed

Description

35%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific to a clear niche (MCP schema enum regressions) but is written in internal jargon rather than natural user trigger terms and omits any explicit 'Use when...' guidance. It answers 'what' but not 'when', leaving its discoverability and trigger quality as the main weaknesses.

Suggestions

Add an explicit trigger clause, e.g. 'Use when an MCP client rejects generated tool schemas because enum arrays contain null or empty-string sentinels.'

Reword jargon into natural terms a user would say — mention 'MCP tool schemas', 'enum validation errors', and 'null enum values' rather than 'nullable enum signatures'.

State the action in third person and list concrete operations (e.g. 'Audits, fixes, and regression-tests generated MCP tool schemas') to lift specificity from 2 to 3.

DimensionReasoningScore

Specificity

It names a concrete domain (MCP schemas) and a concrete action (avoiding nullable enum signatures), but stops at one action rather than listing multiple specific operations, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It states what the skill does ('Keep generated MCP schemas strict-client compatible...') but provides no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is only implied, capping completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

The phrasing relies on internal jargon ('nullable enum signatures', 'strict-client compatible') rather than natural keywords a user would say when they need the skill, landing in the 'technical jargon or overly generic' anchor rather than containing common user-facing terms.

1 / 3

Distinctiveness Conflict Risk

The narrow MCP-schema-enum focus gives it a reasonably distinct niche unlikely to fire for unrelated skills, but the lack of explicit triggers means it could still overlap with generic schema-generation or MCP-server skills, matching 'somewhat specific but could still overlap'.

2 / 3

Total

7

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sbroenne/mcp-server-excel
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.