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.
78
Quality
68%
Does it follow best practices?
Impact
100%
3.84xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/slack/SKILL.mdQuality
Discovery
50%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 proper 'Use when' structure and identifies the Slack domain, but lacks specificity in describing concrete capabilities. The phrase 'control Slack' is too vague, and the specific actions mentioned (reacting, pinning/unpinning) feel incomplete. The description would benefit from more explicit action verbs and natural trigger terms users would actually say.
Suggestions
Replace 'control Slack' with specific action verbs like 'Add emoji reactions to messages, pin important messages, unpin items'
Add more natural trigger terms users would say, such as 'add reaction', 'emoji', 'pin this message', 'unpin'
Separate the 'what' and 'when' more clearly - start with capabilities, then follow with 'Use when...'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Slack) and some actions ('reacting to messages', 'pinning/unpinning items'), but the phrase 'control Slack' is vague and doesn't comprehensively list specific capabilities. | 2 / 3 |
Completeness | Has a 'Use when' clause which is good, but the 'what' portion is weak - it says 'control Slack' without clearly explaining what specific capabilities exist. The when and what are somewhat merged rather than distinctly answered. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Slack', 'messages', 'channels', 'DMs', 'pinning', but missing common variations users might say like 'emoji', 'reaction', 'pin message', 'unpin', or specific action verbs. | 2 / 3 |
Distinctiveness Conflict Risk | Mentions 'slack tool' and 'OpenClaw' which adds some specificity, but 'control Slack' is broad enough it could overlap with other Slack-related skills (messaging, channel management, etc.). | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
87%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, concise skill with excellent actionability through complete JSON examples for every action. The main weakness is the lack of validation guidance for destructive operations (delete, edit) - there's no mention of confirming success, handling errors, or verifying the action completed as expected.
Suggestions
Add validation/confirmation guidance for destructive actions (deleteMessage, editMessage) - e.g., how to verify the action succeeded or handle common errors
Include a brief note on error handling or what to do if an action fails (rate limits, permission errors, invalid IDs)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, providing only necessary information without explaining what Slack is or how APIs work. Every section serves a clear purpose with no padding. | 3 / 3 |
Actionability | All actions include complete, copy-paste ready JSON examples with concrete field values. The inputs section clearly specifies required parameters and their formats. | 3 / 3 |
Workflow Clarity | Actions are clearly listed but there's no validation or error handling guidance for destructive operations like deleteMessage or editMessage. No feedback loops for confirming success or handling failures. | 2 / 3 |
Progressive Disclosure | For a skill of this scope, the content is well-organized with clear sections (Overview, Inputs, Actions, Ideas). The action groups table provides quick reference, and individual actions are easy to navigate. | 3 / 3 |
Total | 11 / 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.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
50ef2f3
- 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.