CtrlK
BlogDocsLog inGet started
Tessl Logo

finding-experiments

Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list` (not feature-flag tools), with disambiguation when multiple experiments match. Use when the user names or quotes an experiment ("split test demo", "the File engagement boost experiment", "onboarding retention test", "landing page hero experiment", "pricing experiment"), describes it loosely ("the signup experiment", "my pricing test", "the one with the new checkout"), uses a relative reference ("latest", "most recent", "the one I created yesterday"), filters by status (running, draft, paused, exposure frozen, stopped, archived), or otherwise refers to an experiment by anything other than its concrete ID.

77

Quality

96%

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

93%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, lean, and actionable instruction-only skill body. Its only soft spot is workflow clarity, which stops at clear checkpoints rather than full validate/retry feedback loops — appropriate for a read-only finding skill but short of a 5.

Suggestions

Add a brief explicit verification loop for the no-match and multiple-match cases (e.g., re-query with broader terms or check archived before reporting 'no matches'), to push workflow clarity toward a 5.

Consider a short checklist after resolving an ID (confirm name + status with the user) so the confirm-before-destructive gate is consistently applied.

DimensionReasoningScore

Conciseness

Lean and efficient: it names the tool, the returned fields, and the matching criteria without explaining what PostHog or experiments are; every section earns its place. The two opening framing lines are brief and non-redundant in context.

5 / 5

Actionability

Fully actionable for an instruction-only MCP-tool skill: it specifies the exact tool (`experiment-list`) and server, enumerates returned fields, gives matching strategies, a one/multiple/none decision tree, and a concrete worked example.

5 / 5

Workflow Clarity

The find → disambiguate → confirm/get-details sequence is clear with checkpoints (one/multiple/none branches, confirm-before-destructive, no-match suggestions), but it lacks explicit error-recovery feedback loops or checklists that would lift it to a 5.

4 / 5

Progressive Disclosure

A self-contained SKILL.md under 50 lines with no external reference files needed; sections are well-organized and the Related-skills pointers are one level deep and clearly signaled.

5 / 5

Total

19

/

20

Passed

Description

100%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.

An excellent description: concrete, comprehensive in its trigger coverage, and explicit about both what and when. The negative boundary (not feature-flag tools) further sharpens activation. No meaningful gaps.

DimensionReasoningScore

Specificity

Names the domain and concrete actions — "Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing `experiment-list`" and "with disambiguation when multiple experiments match" — and names the exact tool, giving comprehensive coverage for this skill's scope.

5 / 5

Completeness

Explicitly answers both what ("Resolves... natural language to a concrete experiment ID") and when ("Use when the user names or quotes an experiment... or otherwise refers to an experiment by anything other than its concrete ID") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive coverage of natural phrasings users would actually say, including quoted names ("split test demo", "the one with the new checkout"), relative references ("latest", "most recent"), and status filters.

5 / 5

Distinctiveness Conflict Risk

Carves a clear niche and even states the negative boundary ("not feature-flag tools"), names the specific tool, so it is unlikely to trigger for the wrong skill.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.