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
73%
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 ./skills/slack/SKILL.mdQuality
Discovery
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 provides a clear 'when to use' clause and names specific actions (reacting, pinning/unpinning), which is good. However, the opening phrase 'control Slack from OpenClaw' is somewhat vague and uses internal terminology. The description would benefit from listing more concrete actions and including more natural trigger terms users would actually say.
Suggestions
Expand the list of concrete actions beyond reacting and pinning — e.g., 'add emoji reactions, pin messages, unpin messages' — to improve specificity.
Add more natural trigger terms users would say, such as 'emoji', 'react with', 'pin a message', 'thumbs up', to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Slack) and some actions (reacting to messages, pinning/unpinning items), but doesn't comprehensively list all capabilities. It mentions 'control Slack' which is vague, though the specific examples help. | 2 / 3 |
Completeness | Explicitly answers both 'what' (controlling Slack via the slack tool, reacting to messages, pinning/unpinning) and 'when' ('Use when you need to control Slack... including reacting to messages or pinning/unpinning items in Slack channels or DMs'). | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Slack', 'reacting to messages', 'pinning', 'unpinning', 'channels', 'DMs', but misses common user phrasings like 'add emoji', 'react with', 'pin message', 'slack tool', or 'emoji reaction'. The term 'OpenClaw' is internal jargon that users may not naturally use. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of Slack and specific actions like reacting/pinning helps distinguish it, but 'control Slack' is broad enough that it could overlap with other Slack-related skills (e.g., sending messages, managing channels). The scope boundary between this skill and other potential Slack skills is unclear. | 2 / 3 |
Total | 9 / 12 Passed |
Implementation
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 API reference skill with excellent actionability—every action has a concrete, copy-paste-ready JSON example. The content is concise and respects Claude's intelligence. The main weaknesses are the lack of validation/verification guidance for destructive operations (delete, edit) and the monolithic listing of all actions inline rather than splitting common vs. advanced actions.
Suggestions
Add a brief verification step or confirmation pattern for destructive actions like deleteMessage and editMessage (e.g., 'Read the message first to confirm target before deleting').
Consider splitting less-common actions (emojiList, memberInfo) into a separate reference file, keeping SKILL.md focused on the most frequent actions (react, send, pin).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what Slack is or how APIs work. Every section serves a purpose—inputs, action groups, and concrete JSON examples. The 'Ideas to try' section is minimal and arguably unnecessary but only adds two lines. | 3 / 3 |
Actionability | Every action has a complete, copy-paste-ready JSON payload with realistic field values. The inputs section clearly specifies what to collect and where to find values (e.g., message context lines). This is fully executable guidance. | 3 / 3 |
Workflow Clarity | Each action is clearly documented individually, but there are no multi-step workflows with validation checkpoints. For destructive operations like deleteMessage, there's no guidance on confirming the target or verifying success. The skill is mostly a reference catalog rather than a guided workflow. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and a summary table, but all 11 action examples are inline in a single file. The action group table provides a nice overview, but the extensive JSON examples could benefit from being split into a reference file, with SKILL.md keeping just the most common actions. | 2 / 3 |
Total | 10 / 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
- deepgram/dglabs-deepclaw
- Commit
ec8d4f8
- 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.