Manage Trello boards, lists, and cards via the Trello REST API.
65
52%
Does it follow best practices?
Impact
93%
1.09xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/trello/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description clearly identifies its domain (Trello) making it distinctive, but it is too brief and lacks specific concrete actions beyond the generic 'manage.' The absence of a 'Use when...' clause significantly hurts completeness, making it harder for Claude to know exactly when to select this skill.
Suggestions
Add a 'Use when...' clause with trigger terms like 'Use when the user asks to create, move, or update Trello cards, manage Trello lists, or interact with Trello boards.'
List specific concrete actions such as 'create cards, move cards between lists, add labels, create boards, archive cards, add comments' instead of the generic 'manage.'
Include natural user phrasing variations like 'kanban board', 'task tracking in Trello', or 'Trello automation' to improve trigger term coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Trello) and some actions ('manage boards, lists, and cards'), but doesn't list specific concrete actions like creating cards, moving cards between lists, archiving, adding labels, etc. | 2 / 3 |
Completeness | Describes what it does ('Manage Trello boards, lists, and cards') but completely lacks a 'Use when...' clause or any explicit trigger guidance, which per the rubric caps completeness at 2, and since the 'what' is also fairly thin, a score of 1 is appropriate. | 1 / 3 |
Trigger Term Quality | Includes 'Trello', 'boards', 'lists', 'cards', and 'REST API' which are relevant keywords, but misses common user variations like 'kanban', 'task board', 'add a card', 'move a card', or specific Trello operations users would naturally request. | 2 / 3 |
Distinctiveness Conflict Risk | Trello is a very specific product, and the mention of 'Trello REST API' creates a clear niche that is unlikely to conflict with other skills. It's distinctly identifiable. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with concrete curl commands for all common Trello operations. Its main weaknesses are redundancy between the Usage and Examples sections, and the lack of error handling/validation guidance for state-modifying API calls. Tightening the content and adding response validation would elevate it significantly.
Suggestions
Remove the duplicate Examples section or consolidate it with Usage—the 'list boards' command appears twice, wasting tokens.
Add response validation guidance: check HTTP status codes (e.g., `curl -s -w '\n%{http_code}'`) and verify success before proceeding, especially for create/archive operations.
Add a brief error handling pattern (e.g., what a 401 vs 429 response means and how to handle rate limiting with retries).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient with concrete curl commands, but the Examples section at the bottom largely duplicates the Usage section (e.g., listing boards appears twice). The Notes section includes some useful info (rate limits) but the security warning is something Claude already knows. | 2 / 3 |
Actionability | Every operation has a fully executable curl command with proper flags, query parameters, and jq formatting. Commands are copy-paste ready with clear placeholder conventions ({boardId}, {listId}, etc.). | 3 / 3 |
Workflow Clarity | The setup steps are clearly sequenced, and individual API operations are clear. However, there's no validation guidance—no mention of checking response codes, handling errors, or verifying that destructive operations (archive) succeeded before proceeding. For API operations that modify state, this is a gap. | 2 / 3 |
Progressive Disclosure | The content is reasonably organized with clear section headers, but it's somewhat monolithic—all operations are inline. For a skill of this size (~70 lines of content), the advanced examples and rate limit details could be referenced separately, and the duplicate examples section adds clutter rather than progressive depth. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
09cce3e
Table of Contents
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.