Content
61%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is well-organized, information-dense, and actionable, with concrete tool slugs, parameters, expression syntax, and per-workflow pitfalls that assume Claude's competence rather than teaching basics. The main weaknesses are the missing validation/verify loop around the batch profile-update workflow and redundant repetition of date-format and expression-syntax rules across sections.
Suggestions
Add a validation loop to the profile-update workflow: query profiles with QUERY_PROFILES to confirm the target set before MIXPANEL_PROFILE_BATCH_UPDATE, then re-query to verify the changes applied — this also lifts the workflow_clarity cap.
Deduplicate repeated guidance: state the 'YYYY-MM-DD' date rule and the properties["name"] expression syntax once in 'Known Pitfalls' and remove them from individual workflow pitfall lists.
Delete the empty 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview.') — it adds tokens without information — and consider moving the quick-reference table and expression-syntax guide into a references/ file to keep SKILL.md a leaner overview.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient — tool sequences, parameter lists, and pitfalls are terse and information-dense — but there is noticeable redundancy: the 'YYYY-MM-DD' date-format rule is repeated in nearly every workflow's pitfalls and again under 'Known Pitfalls', the expression syntax (properties["name"] == value) appears in both 'Common Patterns' and 'Known Pitfalls', and the closing 'When to Use' section ('This skill is applicable to execute the workflow or actions described in the overview.') is pure filler. This matches the anchor 'Mostly efficient but includes some unnecessary explanation or could be tightened'; it is not a 2 because there is no concept-explanation padding and most sections earn their tokens. | 3 / 5 |
Actionability | Guidance is concrete and executable in the MCP context: exact tool slugs (MIXPANEL_QUERY_SEGMENTATION, MIXPANEL_PROFILE_BATCH_UPDATE), exact parameter names and formats, copy-paste-ready expression examples (properties["country"] == "US"), and step-by-step ID resolution patterns. This matches the anchor 'Mostly executable guidance; concrete code or commands with minor gaps'. It falls short of 5 because no literal example tool call (e.g., a sample request payload) is shown, leaving the exact call shape implicit. | 4 / 5 |
Workflow Clarity | Each workflow has a 'When to use', a numbered tool sequence with [Prerequisite]/[Required] tags, and the setup steps include verification checkpoints ('Confirm connection status shows ACTIVE before running any workflows'). However, the skill includes a batch write operation (MIXPANEL_PROFILE_BATCH_UPDATE) with no validation step — there is no guidance to verify targets with QUERY_PROFILES before writing or to re-query afterwards to confirm the update. Per the guideline that missing validation in batch/destructive operations caps workflow clarity at 3, this matches the anchor 'Steps listed but validation gaps; sequence present but checkpoints missing or implicit'. | 3 / 5 |
Progressive Disclosure | The single SKILL.md is well structured with clear section headers, per-workflow subsections, and a quick-reference table, and it references no files (so no dead or nested references). This matches the anchor 'Good structure; most content is appropriately placed; minor organization gaps'. It is not a 5 because at ~220 lines the reference material (expression syntax guide, quick-reference table, JQL notes) could be split into one-level-deep reference files to keep SKILL.md a leaner overview. | 4 / 5 |
Total | 14 / 20 Passed |