Content
67%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 strong, highly actionable instruction-only skill: exact MCP tool slugs, parameter formats, ordered workflows with tagged prerequisites, and genuinely useful pitfalls. Its main weaknesses are duplicated material across sections (rate limits, search delays, ID rules stated multiple times), a filler closing section, and no worked example payloads or error-recovery loops.
Suggestions
De-duplicate the repeated guidance: state rate limits, search-index delays, and nested-response parsing once (keep them in "Known Pitfalls" or the relevant workflow, not both), and delete the content-free "When to Use" section.
Add one worked example (e.g., a sample TRELLO_ADD_CARDS request/response and the nested data.data checklist extraction) so guidance is fully copy-paste ready.
Weave validation into the workflows as explicit feedback loops — e.g., "verify card ID and confirm before TRELLO_UPDATE_CARDS_BY_ID_CARD", and a confirm-before-delete step given attachment deletion is irreversible.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is dense with operationally useful material (tool sequences, parameters, pitfalls) but repeats itself: rate limits appear in both "### Rate Limits" and "Known Pitfalls", search-indexing delays and nested-response parsing are each stated twice, and ID-format rules are given three times. The closing "When to Use" section ("This skill is applicable to execute the workflow or actions described in the overview.") is pure filler. Not 4 because the duplication is noticeable rather than minor; not 2 because there is no explanation of concepts Claude already knows. | 3 / 5 |
Actionability | Concrete, executable guidance throughout: exact tool slugs (e.g., "TRELLO_ADD_CARDS"), parameter names and formats ("idList: 24-char hex ID (NOT list name)", "due: ISO 8601"), ordered sequences tagged [Prerequisite]/[Required]/[Optional], and the smart instruction to fetch current schemas via RUBE_SEARCH_TOOLS first. Not anchor 5 because there are no worked example payloads or a sample call, leaving minor gaps for a copy-paste-ready experience. | 4 / 5 |
Workflow Clarity | Each of the six workflows has a clearly numbered sequence with explicit prerequisite chains and ID-resolution steps, plus real checkpoints: "verify card name before updating", "Confirm connection status shows ACTIVE before running any workflows", and "Store returned id (idCard) immediately". Not 5 because recovery loops are thin (pitfalls are listed but not woven back into the sequences as validate-then-retry steps), and the noted irreversible attachment deletion has no verify-before-acting step; not 3 because most checkpoints are present and explicit. | 4 / 5 |
Progressive Disclosure | No bundle files exist (references/, scripts/, assets/ are all absent), and the ~176-line body is well-organized with clear section headers, a "Common Patterns" section, and a scannable Quick Reference table. Not anchor 5 because the body exceeds the simple-skill threshold and carries reference-style material (the 12-row tool table plus six full workflows) that could be split into one-level-deep reference files; not 3 because structure, signaling, and navigation are good with nothing buried. | 4 / 5 |
Total | 15 / 20 Passed |