discord-automation

Automate Discord tasks via Rube MCP (Composio): messages, channels, roles, webhooks, reactions. Always search tools first for current schemas.

1.85x

Quality

—

Does it follow best practices?

Impact

89%

1.85x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete tool sequences, typed parameters, and pitfalls, and it avoids teaching Claude concepts it already knows. Its main weaknesses are a redundant quick-reference table, missing validation/feedback checkpoints around destructive Discord operations, and a monolithic single-file structure that could benefit from reference splitting.

Suggestions

Add validation/feedback steps for destructive ops, e.g. after DELETE_GUILD_ROLE verify via GET_GUILD_MEMBER or list-roles that the role is gone, and before DELETE_ALL_MESSAGE_REACTIONS confirm the target message_id.

Trim or justify the Quick Reference table, since every tool slug and key param it lists is already stated in the per-workflow sections.

Move the per-workflow parameter and pitfall detail (or the full tool catalog) into a references file (e.g. references/tool-catalog.md) and keep SKILL.md as a lean overview with one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence with no basic-concept explanations, but the Quick Reference table duplicates tool slugs and params already enumerated per workflow, which is redundant padding; it is not 3 because of that duplication and not 1 because it avoids verbose known-concept exposition.	2 / 3
Actionability	Concrete tool slugs with role tags, typed parameters and limits ("content: Message text (max 2000 characters)", "color: RGB color integer"), URL-encoding examples, and permission bitfields make the guidance copy-paste-ready; per the code_vs_instruction note, the absence of executable code is not penalized when instruction-only guidance is this actionable.	3 / 3
Workflow Clarity	Steps are clearly sequenced with numbered tool lists and prerequisite/required/optional tags, and setup has an ACTIVE-status checkpoint, but destructive/batch operations (DELETE_GUILD_ROLE, DELETE_ALL_MESSAGE_REACTIONS) lack validate-then-retry feedback loops, which the feedback_loops note says must cap workflow_clarity at 2.	2 / 3
Progressive Disclosure	The skill is a single ~185-line inline document with no bundle files in references/, scripts/, or assets/; it is too long for the under-50-line simple-skill carve-out, and per-workflow detail plus the reference table that could live in separate files are all inline, matching the anchor for content that should be separate being inline.	2 / 3
	Total	9 / 12 Passed

Description

82%

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 specific and well-targeted with strong natural trigger terms and a distinct niche, but it omits an explicit "Use when..." usage trigger, which caps its completeness score. Adding a when-to-use clause would raise the description's strongest remaining weakness.

Suggestions

Add an explicit usage trigger, e.g. "Use when automating Discord messaging, role management, webhooks, or reactions via Composio's Rube MCP."

Drop or shorten the parenthetical "(Composio)" so the trigger surface stays on user-natural terms like Discord messages, roles, and webhooks.

Consider naming the bot-vs-user distinction only if it helps users self-select; otherwise it adds noise to the description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capability categories — "messages, channels, roles, webhooks, reactions" — tied to a named domain, matching the anchor for listing multiple specific concrete actions; it is above score 2 because five distinct operations are enumerated rather than just a domain plus a few actions.	3 / 3
Completeness	It clearly states what the skill does but provides no "Use when..." or equivalent explicit trigger guidance, which the judging guidelines state must cap completeness at 2; it cannot reach 3 because the "when" clause is entirely missing rather than explicit.	2 / 3
Trigger Term Quality	Uses natural user-facing terms (Discord, messages, channels, roles, webhooks, reactions) a person would actually say; the technical "Rube MCP (Composio)" framing is parenthetical context rather than the trigger surface, so keyword coverage is good.	3 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (Discord automation via Rube MCP/Composio) with distinct triggers unlikely to collide with other skills; above 2 because the domain and capability list make mis-targeting improbable.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Commit: 366e45b

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.