discord

Send, read, edit, delete, and search Discord messages, reactions, polls, pins, and threads via the message tool. Use when interacting with Discord channels, sending media or embeds, creating polls or threads, managing presence, or moderating messages.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

The canonical home for this skill is discord in Hung-Reo/hungreo-openclaw

Quality

Content

68%Weight 40%Scale 1-5

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

The body is a tight, example-driven reference that is highly actionable and free of padding, with the main gaps being a non-executable components placeholder and duplicated style rules. The destructive delete/moderation actions lack any validation checkpoint, which caps workflow clarity per the rubric.

Suggestions

Add a verification step for destructive actions (e.g., read the message or confirm channelId/messageId with the user before "delete" and moderation actions) to lift workflow clarity.

Replace the "[Carbon v2 components]" placeholder with a minimal executable components payload or link to a concrete example, so every code block is copy-paste ready.

Deduplicate the Writing Style section ("No markdown tables", "Mention users as `<@USER_ID>`" already appear in Guidelines) and consider moving the long examples catalog into a references/ file for leaner top-level disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean — terse "Musts"/"Guidelines" bullets and compact JSON examples with no over-explanation of concepts Claude already knows. Not 5 because "No markdown tables" and "Mention users as `<@USER_ID>`" are stated twice (Guidelines and Writing Style sections).	4 / 5
Actionability	Twelve of the thirteen JSON examples (send, media, react, read, edit, delete, poll, pin, thread-create, search, set-presence, embeds) are copy-paste ready and cover the common cases. Not 5 because the components-v2 example uses the placeholder "[Carbon v2 components]", which is not executable without external Carbon instances.	4 / 5
Workflow Clarity	Each action is individually unambiguous and well-organized, but the destructive "delete" action (and gated moderation) has no validation or verification guidance (e.g., confirming the target messageId before deletion). The rubric caps workflow clarity at 3 for destructive operations without validation; not 4 because that checkpoint is entirely absent.	3 / 5
Progressive Disclosure	Sections (Musts, Guidelines, Targets, Common Actions, Writing Style) are clear and there are no buried or nested references since no bundle files exist. Not 5 because the ~13-example API reference is fully inlined in SKILL.md where a references file could carry the bulk, leaving minor organization headroom.	4 / 5
	Total	15 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 exemplary: concrete verb-object capability lists, an explicit third-person 'Use when' trigger clause, and a clearly distinct Discord niche. The only weakness is modest synonym coverage for common user phrasings like DM or server.

Dimension	Reasoning	Score
Specificity	"Send, read, edit, delete, and search Discord messages, reactions, polls, pins, and threads" lists multiple concrete verb-object pairs covering the domain comprehensively, matching the top anchor. Not 4 because coverage of capabilities is essentially complete rather than having minor gaps.	5 / 5
Completeness	Explicitly answers both what ("Send, read, edit, delete, and search...") and when ("Use when interacting with Discord channels, sending media or embeds...") with concrete trigger phrases, in third person. Not 4 because the when-clause is already explicit and specific rather than needing more detail.	5 / 5
Trigger Term Quality	Natural phrases like "Discord channels", "sending media or embeds", "creating polls or threads", and "moderating messages" give good keyword coverage a user would naturally say. Not 5 because common variations such as "DM"/"direct message", "server", or "emoji" are absent.	4 / 5
Distinctiveness Conflict Risk	"Discord" plus "via the message tool" carves a clear niche with distinct triggers and minimal conflict risk with other skills. Not 4 because the domain term dominates every trigger phrase, leaving only negligible overlap with generic messaging skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 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

	Total	14 / 16 Passed

Repository: Bitterbot-AI/bitterbot-desktop
Path: skills/discord/SKILL.md
Commit: 1c7dc1b

Reviewed: 19 hours 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.