CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

81

3.84x
Quality

73%

Does it follow best practices?

Impact

100%

3.84x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./openclaw/skills/slack/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

79%

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

This is a well-structured, actionable skill that provides clear JSON examples for every Slack action. Its main weakness is the lack of workflow guidance for multi-step or destructive operations (e.g., confirming before delete, verifying a reaction was added). The content is concise and assumes Claude's competence appropriately.

Suggestions

Add a brief validation/confirmation step for destructive actions like deleteMessage (e.g., read the message first to confirm it's the right one before deleting).

Consider adding a short workflow example showing a common multi-step sequence (e.g., read messages → find a specific one → react to it) to improve workflow clarity.

DimensionReasoningScore

Conciseness

The content is lean and efficient. It avoids explaining what Slack is or how APIs work, assumes Claude's competence, and every section serves a clear purpose. The action group table and JSON examples are compact and informative.

3 / 3

Actionability

Every action is illustrated with a complete, copy-paste-ready JSON payload showing exact field names and values. The inputs section clearly specifies what needs to be collected and where to find values like messageId from context.

3 / 3

Workflow Clarity

The skill presents individual actions clearly but lacks any sequenced workflow or validation guidance. For destructive operations like deleteMessage, there are no confirmation or verification steps mentioned. The actions are listed independently without guidance on when to chain them or how to handle errors.

2 / 3

Progressive Disclosure

The content is well-organized with clear sections and a summary table, but all actions are inline in a single file. For a skill with 12 distinct actions, some could be grouped or referenced separately. However, the total length is manageable and no bundle files exist, so the inline approach is reasonable though not optimal.

2 / 3

Total

10

/

12

Passed

Description

67%

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 has a solid structure with an explicit 'Use when' clause and names specific actions like reacting and pinning/unpinning. However, the broad framing of 'control Slack from OpenClaw' is vague and could overlap with other Slack skills, and the use of internal terminology ('OpenClaw') may not match natural user language. The word 'including' implies additional unstated capabilities, reducing clarity.

Suggestions

Replace the vague 'control Slack from OpenClaw' with a more specific enumeration of all supported actions (e.g., 'Adds emoji reactions to Slack messages, pins and unpins items in channels and DMs').

Add more natural trigger terms users might say, such as 'add emoji', 'react with', 'pin a message', 'unpin', to improve keyword coverage.

DimensionReasoningScore

Specificity

Names the domain (Slack) and some actions (reacting to messages, pinning/unpinning items), but doesn't comprehensively list all capabilities. The phrase 'control Slack from OpenClaw' is somewhat vague.

2 / 3

Completeness

Clearly answers both 'what' (reacting to messages, pinning/unpinning items in Slack channels or DMs) and 'when' (explicit 'Use when' clause specifying the trigger conditions for selecting this skill).

3 / 3

Trigger Term Quality

Includes relevant terms like 'Slack', 'reacting to messages', 'pinning', 'unpinning', 'channels', 'DMs', but misses common user phrasings like 'add emoji', 'add reaction', 'pin message', or 'slack tool'. The term 'OpenClaw' is internal jargon that users may not naturally use.

2 / 3

Distinctiveness Conflict Risk

The mention of 'control Slack' is broad and could overlap with other Slack-related skills (e.g., sending messages, managing channels). However, the specific mention of 'reacting' and 'pinning/unpinning' provides some distinctiveness. The phrase 'including' suggests these are examples rather than exhaustive, which increases conflict risk.

2 / 3

Total

9

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

9

/

11

Passed

Repository
trpc-group/trpc-agent-go
Reviewed

Table of Contents

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.