CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mcp-integration-reference

Template for skills that integrate with an MCP server. Demonstrates the reference file pattern: Claude reads a domain-specific MCP cheatsheet before making any tool calls, reducing query failures caused by server-specific gotchas. Fork this skill and replace the Sentry example with your target MCP.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./examples/skills/mcp-integration-reference/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is a well-structured, lean workflow that correctly delegates MCP-specific details to a real, well-organized reference file. Steps are sequenced with concrete defaults and output templates; only minor gains are available from trimming meta-commentary and adding light validation checkpoints.

DimensionReasoningScore

Conciseness

The body is efficient: steps are short and directive ("Cap results at 50 issues. If more exist, note the count..."), and it does not explain concepts Claude already knows. Minor over-explanation could be trimmed — the "What this pattern solves" section and template meta-commentary ("Zero guessing.") add tokens beyond strict necessity — keeping it at anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Guidance is concrete: exact defaults ("last 72 hours", "production only", "all projects"), explicit caps ("top 5 issues by event count", "Cap results at 50"), a copy-paste report template, and a Step 1 instruction pointing to a real reference file containing working tool-call examples. It is not 5 because the body itself gives no executable tool calls and a few analysis directives ("ordered by frequency", "group by root cause") leave execution details to be inferred from the reference file.

4 / 5

Workflow Clarity

Steps 1-5 are clearly sequenced (read reference → gather scope → fetch → analyze → report) with concrete contingencies ("If the user says 'just run it with defaults'...", "If an issue is ambiguous, flag it as 'needs investigation'"). Since the workflow is read-only analysis ("It does not modify code or create tickets"), the destructive/batch validation cap does not apply, but there are no explicit validation checkpoints (e.g., verifying fetched data or empty results), placing it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The body is a clean overview that defers all server-specific gotchas, query syntax, and examples to the verified one-level-deep reference (references/sentry-mcp.md, 151 lines, well-sectioned), signaled clearly in Step 1 ("Before doing anything else, read the full MCP reference"). No nested references exist, and the split is appropriate for the bundle structure — matching anchor 5.

5 / 5

Total

17

/

20

Passed

Description

53%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 clearly explains the template's mechanism (reading an MCP cheatsheet before tool calls to reduce query failures) but is written for skill authors forking the template rather than for triggering the skill in session. It lacks a 'Use when...' clause and natural end-user trigger terms, and it omits the skill's actual analysis-and-reporting workflow.

Suggestions

Add an explicit trigger clause, e.g. "Use when analyzing Sentry errors, investigating production issues, or generating error reports via the Sentry MCP."

Describe the skill's concrete operational capabilities (fetch unresolved issues, group by root cause, output a structured error report), not just the template pattern.

Include natural user phrasings and synonyms — "Sentry errors", "error report", "production issues", "stack traces" — to improve trigger term coverage.

DimensionReasoningScore

Specificity

Phrases like "reads a domain-specific MCP cheatsheet before making any tool calls, reducing query failures caused by server-specific gotchas" and "Fork this skill and replace the Sentry example" name the domain and 1-2 concrete actions. However, the description covers only the template pattern and omits the skill's actual operational workflow (fetching issues, grouping by root cause, generating an error report), so coverage is not comprehensive — matching anchor 3 rather than anchor 4, whose 'minor gaps' criterion the missing core workflow exceeds.

3 / 5

Completeness

The 'what' is reasonably clear ("Template for skills that integrate with an MCP server. Demonstrates the reference file pattern..."), but there is no 'Use when...' clause or equivalent explicit trigger guidance — "Fork this skill and replace the Sentry example" addresses skill authors, not when to invoke the skill. Per the judging guideline, a missing trigger clause caps completeness at 3; it is not 2 because the 'what' is concrete and specific.

3 / 5

Trigger Term Quality

Relevant keywords are present ("MCP server", "Sentry", "tool calls", "query failures", "gotchas"), but common natural phrases a user would say when needing this skill are missing: "Sentry errors", "error report", "production issues", "analyze issues". This lands on anchor 3 ('some relevant keywords but missing common variations or synonyms') rather than 4, since the included terms skew toward template-author language rather than end-user trigger language.

3 / 5

Distinctiveness Conflict Risk

The niche is well-delineated — "skills that integrate with an MCP server", the "reference file pattern", and the Sentry example give it distinct triggers with only minor overlap risk against other MCP-wrapper skills. It is not 5 because 'MCP integration' as a category could collide with other MCP tooling skills, and the lack of explicit trigger phrases weakens distinct triggering.

4 / 5

Total

13

/

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

FlorianBruniaux/claude-code-ultimate-guide

Path

examples/skills/mcp-integration-reference/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.