CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mcp

MCP server and client development — scaffold, implement tools/resources/prompts, validate schemas, debug protocol compliance, and deploy with auth and rate limiting.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/mcp/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%Weight 40%Scale 1-5

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

The body is highly actionable with concrete commands, ready-to-paste configs, and a well-sequenced configure-aws workflow. Its main weaknesses are token efficiency (duplicated catalog and repeated JSON blocks) and progressive disclosure (a large inline configure-aws section plus references to bundle files that are not present).

Suggestions

Move the configure-aws interactive question scripts, cost/CLI-first templates, and catalog tables into a dedicated reference file (e.g. references/aws-mcp-configure.md), keeping only the mode summary, flags, and one config example inline in SKILL.md.

De-duplicate the AWS service/kit catalog: keep it only in the final catalog table and have Question 1 reference it rather than restating every service, kit, and token count inside the prompt block.

Either ship references/mcp.md and references/aws-mcp-profiles.md in the bundle or remove/replace the dangling 'Reference:' pointers so every cited path resolves.

DimensionReasoningScore

Conciseness

The create/review/debug modes are lean and imperative, but the AWS service/kit catalog with token counts is duplicated in full (once inside Question 1's prompt block, again as 'AWS MCP Server Catalog'), and the same server JSON block is repeated across three examples. This matches 'mostly efficient but could be tightened' rather than 'minor instances of over-explanation'.

3 / 5

Actionability

Fully executable, copy-paste ready guidance: exact inspector and smoke-test commands ('npx @modelcontextprotocol/inspector node dist/index.js', the stdio JSON-RPC echo test), ready-to-paste host configs, and 'pip index versions awslabs.eks-mcp-server' to resolve the ==VERSION placeholder. Specific examples cover the common create/review/debug/configure cases.

5 / 5

Workflow Clarity

configure-aws has a well-sequenced flow (Step 0 one-question-at-a-time gathering, confirmation summary, cost check, CLI-first check, credential_process check, generation) and debug specifies symptom → root cause → evidence command → fix → validation step. Minor validation gaps remain: create's step 8 mentions 'expected responses' without providing them, and configure-aws has no post-generation connection test, so it does not reach the explicit-feedback-loops-everywhere level.

4 / 5

Progressive Disclosure

References are clearly signaled and one level deep ('Reference: references/mcp.md → Security, Error Handling, Testing and Debugging'), but neither references/mcp.md nor references/aws-mcp-profiles.md exists in the bundle, and roughly 150 lines of configure-aws material (full interactive prompt scripts, catalogs, multi-account JSON examples) are inlined where they belong in a separate reference file.

3 / 5

Total

15

/

20

Passed

Description

75%Weight 40%Scale 1-5

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, action-dense, and clearly distinct, covering the whole MCP lifecycle from scaffolding to deployment. Its single notable weakness is the absence of any 'when to use' trigger clause, which caps completeness and leaves natural-phrase coverage slightly incomplete.

Suggestions

Append an explicit trigger clause, e.g. 'Use when building, reviewing, or debugging MCP (Model Context Protocol) servers or clients, or when configuring MCP integrations with cloud providers.'

Spell out 'Model Context Protocol' at least once and add common synonyms users say ('MCP integration', 'MCP connector') to widen natural trigger coverage.

DimensionReasoningScore

Specificity

'scaffold, implement tools/resources/prompts, validate schemas, debug protocol compliance, and deploy with auth and rate limiting' lists five concrete verb+object actions covering the full MCP development lifecycle, matching the comprehensive-coverage anchor rather than the 'minor gaps' level.

5 / 5

Completeness

The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; it is above level 2 because the 'what' is explicit and multi-action.

3 / 5

Trigger Term Quality

Natural terms like 'MCP server', 'MCP client', 'schema validation', 'protocol compliance', and 'auth' are present, but the spelled-out 'Model Context Protocol' and common synonyms (e.g. 'MCP integration', 'MCP connector') are missing, so coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

'MCP server and client development' carves out a clear niche (Model Context Protocol) with distinct triggers, and no meaningful overlap with related document/git/general-development skills is apparent.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository

nitinjain999/platform-skills

Path

skills/mcp/SKILL.md

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.