Content
63%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.
A well-structured, highly actionable MCP tool guide with clear sequenced workflows and real validation checkpoints, but it is a ~190-line monolith with no progressive disclosure and significant duplication between workflow-level pitfalls, the Known Pitfalls section, and Common Patterns. Consolidating the redundancy and splitting per-workflow detail into reference files would improve both conciseness and organization.
Suggestions
Deduplicate the pitfalls: state each pitfall once (either in the workflow or in Known Pitfalls) instead of repeating media-URL, rate-limit, and account-requirement rules across three sections.
Split per-workflow details (sequences, parameters, pitfalls) into one-level-deep reference files (e.g., references/workflows.md, references/insights.md), keeping SKILL.md as an overview with the Quick Reference table.
Remove the vacuous 'When to Use' section ("This skill is applicable to execute the workflow or actions described in the overview.") and replace it with concrete conditions, e.g., when the user asks to publish, schedule, or analyze Instagram content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly dense tool-specific knowledge Claude would not know (tool slugs, parameters, limits), but it is noticeably redundant: pitfalls are repeated verbatim across "Core Workflows", "Known Pitfalls", and "Common Patterns" (e.g., media URL accessibility and the 25-post/24-hour limit each appear twice), 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 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than level 4, where over-explanation is only minor. | 3 / 5 |
Actionability | Concrete, executable guidance throughout: exact tool slugs (INSTAGRAM_CREATE_MEDIA_CONTAINER), key parameters (image_url, ig_user_id, children), numeric limits (2-10 carousel items, 2200-char caption, 25 posts/24h), and a quick-reference table. It falls short of level 5's copy-paste-ready calls because no example call payloads or argument structures are shown — sequences are named but not instantiated. For an MCP-tool instruction skill, this is 'mostly executable guidance with minor gaps'. | 4 / 5 |
Workflow Clarity | Each workflow has a clear ordered tool sequence with prerequisites and validation checkpoints: setup requires confirming "connection status shows ACTIVE before running any workflows", and publishing requires polling until status is 'FINISHED'. It misses level 5 because there are no explicit error-recovery loops (e.g., what to do when GET_POST_STATUS never reaches FINISHED or a container creation fails) — checkpoints exist but feedback/retry loops are only implied by the backoff note. | 4 / 5 |
Progressive Disclosure | No bundle files exist (references/, scripts/, assets/ are absent) and the body references none, so the ~190-line SKILL.md is a single monolith. Section structure and the Quick Reference table are good, but content that clearly belongs in separate files is inlined — five full workflow specifications plus duplicated pitfalls and a 13-row API table would fit one-level-deep reference files. This matches 'some structure but... content that should be separate is inline' better than level 4's 'most content is appropriately placed'. | 3 / 5 |
Total | 14 / 20 Passed |