wacli
Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).
79
72%
Does it follow best practices?
Impact
96%
2.00xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./openclaw/skills/wacli/SKILL.mdQuality
Discovery
57%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 identifies a clear and distinct niche (WhatsApp via wacli CLI) with reasonable specificity on core actions. However, it lacks an explicit 'Use when...' clause, which limits its completeness score, and could benefit from more natural trigger terms that users might actually say when needing this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to send a WhatsApp message, look up WhatsApp chat history, or interact with WhatsApp programmatically.'
Include additional natural trigger terms users might say, such as 'text someone on WhatsApp', 'WhatsApp chat log', 'WhatsApp notification', or reference the 'wacli' tool name explicitly as a trigger.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (WhatsApp) and some actions (send messages, search/sync history), but doesn't list comprehensive specific actions like formatting options, group messaging, media handling, etc. | 2 / 3 |
Completeness | Describes what it does (send WhatsApp messages, search/sync history via wacli CLI) but lacks an explicit 'Use when...' clause. The parenthetical '(not for normal user chats)' provides a negative boundary but doesn't serve as a positive trigger guide. | 2 / 3 |
Trigger Term Quality | Includes natural keywords like 'WhatsApp', 'messages', 'search', 'sync', and 'history', but misses common variations users might say like 'text someone', 'chat history', 'message log', or 'wacli'. The parenthetical clarification is helpful but not trigger-oriented. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — WhatsApp messaging via a specific CLI tool (wacli) is unlikely to conflict with other skills. The clarification '(not for normal user chats)' further narrows the scope and reduces ambiguity. | 3 / 3 |
Total | 9 / 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 strong, concise skill that provides fully actionable CLI commands with realistic examples. The safety guardrails (explicit recipient, confirmation before send) are well-placed. The main weakness is the lack of an explicit end-to-end workflow sequence with validation checkpoints, particularly important given that sending messages to third parties is a sensitive operation.
Suggestions
Add a brief numbered workflow showing the typical end-to-end sequence (e.g., 1. Find chat with `chats list`, 2. Confirm recipient with user, 3. Send message, 4. Verify delivery) to improve workflow clarity.
Remove the duplicate note about wacli not being needed for routine user chats (appears in both the intro and Notes section) to tighten conciseness further.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every section serves a purpose—scope boundaries, safety rules, and concrete commands. The repeated note about not using wacli for normal chats appears twice (intro and Notes), which is minor redundancy, but overall token usage is excellent. | 3 / 3 |
Actionability | Every command is fully concrete and copy-paste ready with real flags, example arguments, and realistic values (phone numbers, JIDs, date ranges). No pseudocode or vague descriptions. | 3 / 3 |
Workflow Clarity | The safety section establishes a confirm-before-send checkpoint, which is good. However, the overall workflow (auth → sync → find chat → send) is presented as separate sections without explicit sequencing or validation steps between them. For a destructive operation like sending messages to third parties, a clearer numbered workflow with verification checkpoints would be stronger. | 2 / 3 |
Progressive Disclosure | For a skill under 50 lines with no need for external references, the content is well-organized into clearly labeled sections (Safety, Auth, Find, Send, Notes) that are easy to scan and navigate. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 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 |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 8 / 11 Passed | |
- Repository
- trpc-group/trpc-agent-go
- Commit
0c1ec2b
- 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.