slack

Use when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.

3.84x

Quality

74%

Does it follow best practices?

Impact

100%

3.84x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./openclaw/skills/slack/SKILL.md

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

Quality

Content

80%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.

A well-structured, highly actionable reference: complete executable JSON examples for every action, a useful inputs section, and lean organization with no filler references. The main weakness is the absence of any validation/confirmation guidance for the destructive deleteMessage action, which caps workflow clarity despite the skill otherwise being clean and simple.

Suggestions

Add a short caution/checkpoint for destructive actions, e.g., under 'Delete a message': confirm the messageId against the message context line's 'slack message id' field before deleting, since deletion is irreversible.

Trim the 'Ideas to try' section or fold it into the Overview, and drop the Overview sentence that restates the frontmatter description to reach full token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is lean — an action-group table plus minimal JSON payloads per action, with no explanation of concepts Claude already knows. Minor trims are possible (the Overview line re-states the description, and the two-bullet "Ideas to try" section is soft filler), so it fits anchor 4 ('minor instances... that could be trimmed') rather than 5's 'every token earns its place'.	4 / 5
Actionability	Every one of the 11 actions has a complete, copy-paste-ready JSON payload with concrete example values ("channelId": "C123", emoji "✅", timestamp format), and the 'Inputs to collect' section tells exactly where to source required fields; not 4 because there are no gaps in the common cases.	5 / 5
Workflow Clarity	Each single action is unambiguous, but the skill includes destructive operations — deleteMessage (and pinning/unpinning) — with no validation or confirmation guidance (e.g., verify the messageId from the message context line before deleting), so the rubric's destructive-operation cap applies: cannot score above 3 even though each action is simple.	3 / 5
Progressive Disclosure	There are no bundle files and none are needed: the content is small, self-contained, and appropriately inline, organized with a clear overview, an action-group table, per-action sections, and the header-to-example navigation is trivial. Nothing should be split out and there is no nesting, matching the well-organized simple-skill case; not 4 because there are no organization gaps.	5 / 5
	Total	17 / 20 Passed

Description

68%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.

A distinct, well-triggered description for the Slack domain that answers both what and when, but it under-sells the tool's actual capabilities (message send/edit/delete, member info) relative to the body, and the second-person phrasing 'you need to' violates the third-person voice guideline. The 'when' clause is also circular rather than offering concrete trigger phrases.

Suggestions

List the full capability set in the description (e.g., 'send, edit, and delete messages, react with emoji, manage pins, and look up member info') so the 'what' is comprehensive and matches the body's documented actions.

Rewrite in third person, e.g., 'Use when the user asks to react to Slack messages, pin or unpin items, or send/edit/delete Slack messages in channels or DMs' — this also replaces the circular 'when you need to' with concrete trigger phrases.

Dimension	Reasoning	Score
Specificity	"control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items" names the domain and 2-3 concrete actions, but omits major documented capabilities (send/edit/delete messages, member info), so the base is 3 ("not comprehensive"); the rubric's second-person penalty applies to "Use when you need to control Slack", reducing it to 2.	2 / 5
Completeness	Both 'what' (react, pin/unpin, message control via the slack tool) and 'when' ("Use when you need to control Slack...") are present, but the 'when' clause is circular — it restates the capability rather than giving concrete trigger phrases like 'when the user mentions Slack, reactions, or pinning' — matching anchor 4 exactly and falling short of 5.	4 / 5
Trigger Term Quality	Natural trigger terms are present — "control Slack", "reacting to messages", "pinning/unpinning", "Slack channels or DMs" — but common phrases like "send a Slack message", "Slack emoji", or "DM" variations are missing, matching the anchor 'Good keyword coverage; a few natural terms missing' rather than 5's comprehensive synonym/extension coverage.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — Slack operations through OpenClaw's slack tool — with distinctive terms (Slack, reacting, pinning, DMs) and minimal overlap risk with other skills; not 4 because no closely related skill domain is conflated.	5 / 5
	Total	15 / 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: trpc-group/trpc-agent-go
Path: openclaw/skills/slack/SKILL.md
Commit: 9bb1c42

Reviewed: 7 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.