Name: implementing-mcp-tools
Rating: 71.2 (1 reviews)
Author: PostHog

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.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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.

A well-structured, highly actionable skill body with concrete commands, an annotated YAML schema, and a clear sequenced workflow backed by a verification checklist. Main gaps are minor: a missing post-generation validation checkpoint and a somewhat monolithic body that could split detail into bundle reference files.

Suggestions

Add an explicit validation step after `hogli build:openapi` (e.g. run `lint-tool-names` and verify the generated tool schema is non-empty) to close the workflow's verification loop.

Move the detailed YAML field reference and the client tool-name limit table into a `references/` file, keeping SKILL.md as a tighter overview that links out.

Trim restating sentences like 'Agents compose these primitives into higher-level workflows' that restate concepts Claude already understands.

Dimension	Reasoning	Score
Conciseness	Dense and information-rich with minimal padding, but a few restating sentences ('Agents compose these primitives into higher-level workflows', 'These descriptions are what agents read to understand tool parameters') could be trimmed to fully assume Claude's competence.	4 / 5
Actionability	Provides copy-paste ready commands (pnpm scaffold-yaml, hogli build:openapi, lint-tool-names), a complete annotated YAML template, and concrete file paths that cover the common cases of the pipeline.	5 / 5
Workflow Clarity	The four-step quick workflow is clearly sequenced with a backend-first verification checklist and CI lint callout, but there is no explicit validation checkpoint after the final `hogli build:openapi` generation step, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Good section structure with clearly signaled one-level external references (the full guide and type-system doc paths), though the ~200-line body inlines several topics (naming, YAML, HogQL, versions) that no bundle files exist to offload.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, specific description that concretely names the skill's domain and actions, provides an explicit 'Use when' trigger clause, and is tightly scoped to the PostHog MCP pipeline with low conflict risk. Minor room for additional trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — exposing endpoints as MCP tools, creating/updating endpoints, adding tool definitions, scaffolding YAML configs, writing serializers — with comprehensive pipeline coverage, matching the anchor for several specific concrete actions.	5 / 5
Completeness	Explicitly states both what ('Guide for exposing PostHog product endpoints as MCP tools... full pipeline from Django serializer to generated TypeScript tool handler') and when ('Use when creating new or updating API endpoints, adding MCP tool definitions, scaffolding YAML configs, or writing serializers').	5 / 5
Trigger Term Quality	Good coverage of natural trigger phrases ('creating new or updating API endpoints', 'adding MCP tool definitions', 'scaffolding YAML configs', 'writing serializers') that a PostHog engineer would say, though a few synonym variations are missing.	4 / 5
Distinctiveness Conflict Risk	Highly specific to the PostHog MCP tooling pipeline (Django serializer to TypeScript tool handler), giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: .agents/skills/implementing-mcp-tools/SKILL.md
Commit: 06292db

Reviewed: 22 minutes ago

Table of Contents

Discovery Implementation Validation

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.