CtrlK
BlogDocsLog inGet started
Tessl Logo

implementing-mcp-tools

Guide for exposing PostHog product endpoints as MCP tools. Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML configs, or writing serializers with good descriptions. Covers the full pipeline from Django serializer to generated TypeScript tool handler.

79

Quality

100%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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 well-organized, actionable overview of the MCP tool pipeline: lean and concrete, with executable commands, a sequenced workflow plus validation checkpoints, and clearly signaled one-level-deep references to the full guide.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious domain specifics (MCP client name-length limits, YAML schema fields, serializer-to-Zod flow) and avoids explaining concepts Claude already knows; it does not pad, so it sits at the lean/efficient anchor rather than the "could be tightened" level.

3 / 3

Actionability

It provides copy-paste-ready commands (pnpm scaffold-yaml, hogli build:openapi, lint-tool-names), a complete YAML key-fields example, and concrete code patterns (ListField(child=CharField()), @extend_schema_field), meeting the fully-executable anchor.

3 / 3

Workflow Clarity

The Quick workflow gives a clear 4-step sequence backed by a pre-scaffold verification checklist, a stated error-recovery feedback loop ("If a generated tool has an empty or wrong schema, the fix is almost always on the Django side"), and CI validation commands — matching the explicit-validation-and-feedback anchor.

3 / 3

Progressive Disclosure

It opens by linking a full one-level-deep guide and clearly signals further references (type-system guide, system.py, querying-posthog-data skill) with descriptive link text, while keeping a well-sectioned working overview inline; no bundle files exist locally, so structure is scored on the body organization and signaled references.

3 / 3

Total

12

/

12

Passed

Description

100%

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

A strong, specific description that states concrete capabilities, provides an explicit use-when trigger, and occupies a clearly distinct niche. It is concise without padding and uses third-person voice throughout.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "creating new or updating API endpoints", "adding MCP tool definitions", "scaffolding YAML configs", and "writing serializers" — matching the anchor for several specific concrete actions rather than a single named domain.

3 / 3

Completeness

It explicitly answers both "what" ("exposing PostHog product endpoints as MCP tools ... full pipeline from Django serializer to generated TypeScript tool handler") and "when" (an explicit "Use when ..." clause), so it is not capped at 2.

3 / 3

Trigger Term Quality

The "Use when" clause surfaces natural developer phrasing ("creating new or updating API endpoints", "adding MCP tool definitions", "scaffolding YAML configs") giving good coverage of terms a user would actually say in this domain.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply scoped to PostHog endpoints exposed as MCP tools with distinct, domain-specific triggers, making it unlikely to fire for the wrong skill.

3 / 3

Total

12

/

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

relative_links

Relative link issues: 5 suspicious

Warning

Total

15

/

16

Passed

Repository
PostHog/posthog
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.