slack-outgoing-message

Primary skill for composing, drafting, or refining any outbound Slack content. Use this whenever the task will require using `slack_send_message`, `slack_send_message_draft`, or `slack_create_canvas`. Use `slack` to read or analyze Slack context; use this skill to produce the final outgoing message.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%Weight 40%Scale 1-3

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

A tight, actionable instruction skill with a clear sequenced workflow and explicit error-recovery guardrails. Its main weakness is progressive disclosure: the one external reference it depends on ('Read this reference before finalizing any outgoing Slack text') is a broken link to a non-existent file.

Suggestions

Create or restore ../slack/references/markdown.md so the required reference actually resolves, or inline the essential Slack markdown syntax so the skill is self-contained.

If the markdown reference lives elsewhere, update the link in the Reference Notes table to the correct path and verify it loads.

Consider moving the Tool Guardrails error-handling details (e.g. draft_already_exists handling) into a short reference file to keep the overview even leaner once the markdown reference is fixed.

Dimension	Reasoning	Score
Conciseness	The body is lean and bulleted with no padding or explanation of concepts Claude already knows (e.g., it never explains what Slack is); every section adds tool-contract or behavior guidance that earns its tokens.	3 / 3
Actionability	Gives concrete, executable guidance for an instruction-only skill — exact tool names, mention syntax like '<@U123456>' and '<!subteam^S123456>', and explicit parameter rules (omit thread_ts for normal posts), which per the scoring notes satisfies actionability without code.	3 / 3
Workflow Clarity	The Workflow section sequences steps with explicit decision branches (direct send vs draft vs schedule vs canvas) and the Tool Guardrails include a real feedback loop ('If slack_send_message_draft returns draft_already_exists, stop immediately'), providing checkpoints and error recovery.	3 / 3
Progressive Disclosure	The body is well organized and points to a single clearly-signaled reference (the markdown.md table), but the referenced path ../slack/references/markdown.md does not exist in the bundle, so navigation is broken rather than cleanly one-level-deep.	2 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that states concrete capabilities, gives explicit 'use when' triggers, and cleanly disambiguates from the read/analyze Slack skill. Voice is correctly third person and it avoids fluff.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'composing, drafting, or refining any outbound Slack content' — and ties them to specific tools (slack_send_message, slack_send_message_draft, slack_create_canvas), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (compose/draft/refine outgoing Slack content) and when ('Use this whenever the task will require using...'), satisfying the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Uses natural user verbs ('composing, drafting, refining', 'send, draft, canvas') that a user would plausibly say, alongside tool names, giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Clearly carves a niche from the sibling read skill ('Use `slack` to read or analyze Slack context; use this skill to produce the final outgoing message'), making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: openai/plugins
Path: plugins/slack/skills/slack-outgoing-message/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.