testing-mcp-tools-locally

Set up the local dev environment, seed data, and API keys to test the staff-only managed migrations MCP tools (managed-migrations-support-list, managed-migrations-support-get) end to end. Use when testing batch import support tooling, debugging MCP tool responses or discovery (tools not appearing), or verifying the support API before deploying. Covers the discovery gate: hidden scope, is_staff, user:read, and why wildcard keys and OAuth never work.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

88%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 dense, executable end-to-end testing playbook with strong actionability and clear sequenced workflows including validation checkpoints and recovery loops. It is concise for its complexity and uses one real reference file well, with only minor inline bulk that could be externalized.

Suggestions

Move the longer troubleshooting entries (e.g. port-5432 stale mappings, worker-modifies-records) into a references/troubleshooting.md and keep only the most common fix inline to tighten the SKILL.md overview.

Trim the 'The gates, end to end' prose to a compact summary in SKILL.md and defer the full two-layer explanation to the existing docs link.

Dimension	Reasoning	Score
Conciseness	Mostly lean and action-oriented with code-first sections; the explanatory prose about the discovery gate and fail-closed behavior earns its place as non-obvious internal behavior, though some troubleshooting prose could be trimmed further.	4 / 5
Actionability	Provides copy-paste ready bash, Python, curl, and MCP inspector commands plus a concrete discovery matrix table covering the common positive and negative cases.	5 / 5
Workflow Clarity	Seven clearly numbered steps are sequenced with verification checkpoints (DB connectivity in step 3, direct API in step 6 before MCP), an expected-results matrix as a checklist, and ordered troubleshooting feedback loops for error recovery.	5 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled, verified one-level-deep reference (references/seed-data.md) for the full seeding script and an out-of-scope pointer to docs/support-mcp-tools.md; a fair amount of troubleshooting detail stays inline rather than being split out.	4 / 5
	Total	18 / 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, third-person description that states concrete actions, names the specific tools, and gives explicit 'Use when' triggers tied to natural user complaints. It is distinctive and complete with only minor room for additional synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (set up dev environment, seed data, mint API keys) and names the exact tools under test (managed-migrations-support-list, managed-migrations-support-get) end to end — comprehensive coverage with no generic filler.	5 / 5
Completeness	Explicitly answers both 'what' (set up env, seed data, mint keys to test the MCP tools) and 'when' via a clear 'Use when...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'testing batch import support tooling', 'debugging MCP tool responses or discovery (tools not appearing)', and 'verifying the support API before deploying' map well to what a user would say, though a few plain-language synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow, staff-only managed-migrations MCP niche with distinctive triggers; minimal realistic overlap with 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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: PostHog/posthog
Path: products/managed_migrations/skills/testing-mcp-tools-locally/SKILL.md
Commit: 57503b8

Reviewed: 2 days 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.