CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

integration-binding

Connect a task to MCP tools, workflows, resources, files, or visual outputs through explicit validated interfaces.

60

Quality

76%

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 ./resources/bundled-skills/integration-binding/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 a model of token-efficient instruction writing: a concrete tool-routing table, a sequenced workflow with validation and authorization gates, and explicit boundaries. Its main weakness is that the workflow and gates describe what to do in the abstract, without a single concrete invocation example or explicit error-recovery loop to anchor execution.

DimensionReasoningScore

Conciseness

The body is lean and efficient: a routing table, a five-step workflow, and terse gate/boundary/delivery sections with zero concept explanation or padding. It assumes Claude's competence and every token earns its place, matching the top anchor.

5 / 5

Actionability

The tool-routing table gives exact tool ids (mcp_search, mcp_describe, mcp_call, mcp_read_only_call) with concrete per-tool use cases, and the workflow prescribes specifics like minimum arguments and privilege. It falls short of 5 because no concrete call example or argument shape is shown, and some steps ("Discover candidates instead of guessing an id") remain directive rather than executable.

4 / 5

Workflow Clarity

The five steps are clearly sequenced and validation is present ("Validate the returned data at the next system boundary", read-back gates for mutations, authorization confirmation for external effects). It is below 5 because the checkpoints are abstract — no concrete validation commands or error-recovery loop (fix and re-validate) is spelled out — matching the anchor for clear sequence with most checkpoints but minor validation gaps.

4 / 5

Progressive Disclosure

The skill is under 50 lines, has no bundle files, and needs no external references; its well-organized sections (Purpose, Tool routing, Workflow, Completion gates, Boundaries, Delivery) satisfy the simple-skill exception, which allows a 5 with just well-organized sections.

5 / 5

Total

18

/

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 is concise, third-person, and names a clear domain, but it functions as a one-sentence capability statement. It lacks any explicit trigger guidance ("Use when...") and natural user phrasing, which limits discoverability and caps both completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to connect, call, or integrate with an MCP tool, server, resource, or external integration."

Add natural synonyms users would actually say — "call a tool", "invoke an integration", "connect to an MCP server", "read a resource" — alongside the current technical terms.

List one or two more concrete actions (e.g. "discover tools by intent, inspect input schemas, invoke calls with minimal privilege, read server resources") to strengthen specificity.

DimensionReasoningScore

Specificity

The description names its domain ("MCP tools, workflows, resources, files, or visual outputs") but offers only one generic action ("Connect"), matching the anchor for domain plus 1-2 concrete actions. It falls below anchor 4 because it lists integration targets rather than several specific operations, and above anchor 2 because the targets and "explicit validated interfaces" are concrete.

3 / 5

Completeness

The "what" is stated clearly ("Connect a task to MCP tools, workflows, resources, files, or visual outputs through explicit validated interfaces") but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Keywords like "MCP tools", "workflows", and "resources" are relevant but skewed toward technical jargon, with no natural user phrasings or synonyms (e.g. "invoke a tool", "connect to a server", "call an integration"). This matches the anchor for some relevant keywords while missing common variations.

3 / 5

Distinctiveness Conflict Risk

The MCP framing and "explicit validated interfaces" carve a mostly distinct niche with only minor overlap risk against generic tool-use or file-handling skills. It is not a 5 because "resources, files, or visual outputs" is broad enough to contend with adjacent skills.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

KunAgent/Kun

Path

resources/bundled-skills/integration-binding/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.