discord-automation
Automate Discord tasks via Rube MCP (Composio): messages, channels, roles, webhooks, reactions. Always search tools first for current schemas.
70
58%
Does it follow best practices?
Impact
89%
1.85xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/all-skills/skills/discord-automation/SKILL.mdQuality
Discovery
67%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 is concise and specific about its capabilities, clearly identifying the platform (Discord), the integration method (Rube MCP/Composio), and the types of tasks supported. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms cover the main Discord concepts but could benefit from additional natural language variations.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about Discord automation, sending Discord messages, managing Discord servers, or interacting with Discord bots.'
Include additional natural trigger terms like 'Discord bot', 'Discord server', 'DM', 'send message', 'manage server' to improve matching with common user phrasing.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: messages, channels, roles, webhooks, reactions. Also specifies the tool/platform (Rube MCP via Composio) and includes a concrete procedural instruction ('Always search tools first for current schemas'). | 3 / 3 |
Completeness | Clearly answers 'what' (automate Discord tasks via Rube MCP with specific capabilities listed), but lacks an explicit 'Use when...' clause. The 'when' is only implied by the domain mention. Per rubric guidelines, missing 'Use when...' caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes 'Discord', 'messages', 'channels', 'roles', 'webhooks', 'reactions' which are natural terms users might say. However, it's missing common variations like 'bot', 'server', 'DM', 'send message', 'create channel', or 'Discord bot' that users would naturally use. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific combination of Discord + Rube MCP (Composio). The platform-specific nature (Discord) and tool-specific reference (Rube MCP/Composio) make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid structural organization with clear workflow sequences and comprehensive coverage of Discord operations. Its main weaknesses are the lack of concrete executable examples (actual tool invocation payloads), missing validation/confirmation steps for destructive operations, and some redundancy that inflates token usage. The content would benefit from being more concise with example-driven guidance.
Suggestions
Add concrete example tool invocations with actual parameter payloads (e.g., show a complete DISCORDBOT_CREATE_MESSAGE call with sample channel_id and content) to improve actionability.
Add explicit validation/confirmation steps before destructive operations like DELETE_GUILD_ROLE and DELETE_ALL_MESSAGE_REACTIONS (e.g., 'List current roles first, confirm target role, then delete').
Remove the snowflake ID explanation and reduce redundant pitfall mentions (rate limits appear twice) to improve conciseness.
Consider moving the detailed workflow sections (roles, webhooks, reactions) into a separate reference file and keeping SKILL.md as a concise overview with the quick reference table.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy — pitfalls are repeated across sections (rate limits mentioned in both Send Messages and Known Pitfalls), the snowflake ID explanation is unnecessary for Claude, and the quick reference table largely duplicates information already covered in the workflow sections. | 2 / 3 |
Actionability | Tool sequences are clearly named with specific tool slugs and key parameters, which is good. However, there are no executable code examples or concrete invocation patterns showing exact parameter payloads — it's all descriptive rather than copy-paste ready. The guidance stays at the level of 'call this tool with these params' without showing actual example calls. | 2 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps and labeled as Required/Optional/Prerequisite, which is helpful. However, there are no validation checkpoints or error recovery loops — for destructive operations like DELETE_GUILD_ROLE or DELETE_ALL_MESSAGE_REACTIONS, there's no 'confirm before proceeding' or 'verify result' step, which should cap this at 2. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a useful quick reference table. However, at ~180 lines it's quite long and could benefit from splitting detailed workflow sections into separate files, keeping SKILL.md as a concise overview. The external link to Composio docs is good but the inline content is heavy. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- davepoon/buildwithclaude
- Commit
7cc63f3
- 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.