slack

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

Quality

76%

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

Fix and improve this skill with Tessl

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

Quality

Content

83%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.

An efficient, fully actionable single-tool reference whose only material weakness is the absence of validation around its destructive delete operation, which caps workflow clarity per the rubric.

Suggestions

Add a pre-delete verification step, e.g. "Before deleteMessage, run readMessages to confirm the target message content and author" — destructive operations without validation cap workflow clarity at 3.

For edit and delete, instruct reusing the `slack message id` and `channel` fields from the message context line to guarantee the correct messageId is targeted.

Consider moving the per-action JSON examples into a references/actions.md file and keeping SKILL.md to the overview, inputs, and action-group table to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean: brief overview, a compact inputs list, and one JSON payload per action with no re-teaching of concepts Claude already knows. Every token earns its place, matching anchor 5.	5 / 5
Actionability	Every action has a complete, copy-paste-ready JSON payload with realistic IDs, plus an explicit inputs section and target formats ("channel:<id>" or "user:<id>") — fully executable, anchor 5.	5 / 5
Workflow Clarity	The skill includes the destructive "deleteMessage" action (and batch-capable read/edit flows) with no validation or verification step such as reading or confirming the target message before deletion. The rubric explicitly caps workflow clarity at 3 for destructive operations without validation, taking precedence over the simple-skill exception; the actions themselves are unambiguous, so it is not a 2.	3 / 5
Progressive Disclosure	Sections are well-organized and easy to navigate with no buried or nested references, but the ~140-line body exceeds the 50-line simple-skill threshold and inlines a full action catalog that could partly live in a reference file — good structure with minor organization gaps, anchor 4.	4 / 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 solid, distinctly-scoped description with a proper 'Use when' clause and natural trigger terms, held back by second-person voice and an incomplete enumeration of the tool's capabilities.

Suggestions

Rewrite the trigger in third person, e.g. "Use when the user asks to react to, pin, or manage messages in Slack", to avoid the second-person penalty.

Enumerate the remaining capabilities in the description (send/edit/delete messages, member info, emoji list) instead of the vague "including", improving both specificity and completeness.

Add natural trigger terms users would say, such as "send a Slack message", "emoji reaction", or "pin a message".

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ("reacting to messages or pinning/unpinning items") but omits the messaging, member-info, and emoji capabilities covered in the body, fitting anchor 3; however, the second-person phrasing "Use when you need to control Slack" triggers the rubric's mandated 1-point specificity penalty, reducing it to 2. It is not a 1 because it does list concrete, non-generic actions.	2 / 5
Completeness	Both parts are present: an explicit trigger clause ("Use when you need to control Slack from Clawdbot via the slack tool") and a what-clause ("reacting to messages or pinning/unpinning items"). It is not a 5 because the what under-enumerates the skill's actual capabilities and the when is generic ('control Slack') rather than concrete trigger phrases.	4 / 5
Trigger Term Quality	"Slack", "reacting to messages", "pinning/unpinning", and "channels or DMs" are natural phrases a user would say, matching anchor 4. It falls short of anchor 5 because common variations like "send a Slack message", "emoji", or "Slackbot" are absent.	4 / 5
Distinctiveness Conflict Risk	"control Slack from Clawdbot via the slack tool" carves out a clear niche with distinct triggers (Slack, reacting, pinning, channels/DMs) that would not fire for other skills — anchor 5.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: huangruiteng/CS-Notes
Path: .trae/openclaw-skills/slack/SKILL.md
Commit: 77c775d

Reviewed: 1 day 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.