CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

whatsapp-automation

Automate WhatsApp Business tasks via Rube MCP (Composio): send messages, manage templates, upload media, and handle contacts. Always search tools first for current schemas.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/whatsapp-automation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, highly actionable MCP tool guide with concrete tool sequences, parameters, and domain pitfalls throughout. Its main weaknesses are redundancy across the Pitfalls/Common Patterns/Known Pitfalls sections and a vacuous closing 'When to Use' section, with everything inlined in one long file rather than split into reference files.

Suggestions

Deduplicate the repeated guidance: the phone-number format, 24-hour window, and media-upload flow each appear in both per-workflow Pitfalls and the Common Patterns/Known Pitfalls sections — state each once and cross-reference.

Delete or replace the filler closing section ("This skill is applicable to execute the workflow or actions described in the overview") with concrete trigger conditions for when to reach for this skill.

Move the 14-row Quick Reference table and/or the per-tool pitfall detail into a one-level-deep reference file (e.g., references/quick-reference.md) to shorten SKILL.md to a lean overview.

DimensionReasoningScore

Conciseness

The body is dense with WhatsApp-specific facts Claude doesn't know (24-hour window, E.164 format, media size limits), but it could be tightened: the phone-number format rules, 24-hour window, and media-upload flow each appear twice (per-workflow Pitfalls plus 'Common Patterns'/'Known Pitfalls' sections), and the closing "When to Use" section is pure filler ("This skill is applicable to execute the workflow or actions described in the overview"). It fits the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor; it is not a 2 because there is no padding explaining concepts Claude already knows.

3 / 5

Actionability

Every workflow names exact MCP tool slugs (e.g., `WHATSAPP_SEND_MESSAGE`, `WHATSAPP_UPLOAD_MEDIA`) with ordered sequences, [Prerequisite]/[Required]/[Optional] tags, and concrete parameter examples ('+14155551234', 'en_US', size limits). It is not a 5 because actual invocation shapes are never shown — e.g., the `components` template-variable structure is named but its format is only hinted at via "{{1}}, {{2}}" in a later section, and contact-card object structure is left as 'follow the WhatsApp Business API contact schema'.

4 / 5

Workflow Clarity

Sequences are clearly ordered with prerequisites resolved first (phone_number_id resolution, connection ACTIVE verification before any workflow), and the setup section has explicit verification checkpoints. Minor validation gaps remain: send flows have no checkpoint for confirming delivery success or handling template-rejection errors mid-flow. This is not capped at 3 by the destructive/batch rule — sending individual messages is neither destructive nor batch — and not a 5 because the feedback loops (validate → fix → retry) are only partially present (template resubmission is mentioned but not as a loop).

4 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the ~200-line body is organized into well-labeled sections (Prerequisites, Setup, six numbered workflows, Common Patterns, Known Pitfalls, Quick Reference table) with no nested references — easy to navigate in one level. It sits at the 'good structure; most content appropriately placed; minor organization gaps' anchor rather than 5 because all detail lives inline in a single fairly long file; the per-tool Quick Reference table and deep pitfalls are candidates for a one-level-deep reference file.

4 / 5

Total

15

/

20

Passed

Description

70%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 specific, distinctive description with concrete named actions, weakened only by the complete absence of a 'when to use this' trigger clause and a few missing natural trigger terms (reply, send media, broadcast).

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to send or schedule WhatsApp Business messages, reply to customer chats, send template campaigns, or share media/contacts via WhatsApp."

Include a few more natural user phrasings as triggers, such as "reply to a WhatsApp message", "send a file or image on WhatsApp", and "WhatsApp broadcast", to broaden keyword coverage.

Consider naming the business-profile capability (e.g., "update business profile") to close the coverage gap with the body's workflows.

DimensionReasoningScore

Specificity

The description lists four concrete actions — "send messages, manage templates, upload media, and handle contacts" — tied to a named domain (WhatsApp Business via Rube MCP). Minor gaps in coverage keep it below a 5: replying to messages, sending media by ID/URL, and business-profile management (all covered in the body) are absent, matching the 'several specific actions; minor gaps' anchor rather than comprehensive coverage.

4 / 5

Completeness

The 'what' is clear (automating WhatsApp Business messaging, templates, media, and contacts), but there is no 'Use when...' clause or equivalent trigger guidance; the closing sentence "Always search tools first for current schemas" is procedural instruction, not a 'when to use' trigger. Per the judging guidelines, a missing explicit trigger clause caps completeness at 3 — it is not a 2 because the 'what' is specific and well-stated, and not a 4 because 'when' is entirely absent rather than merely under-specified.

3 / 5

Trigger Term Quality

Natural user-facing keywords are present: "send messages", "templates", "upload media", "handle contacts", plus "WhatsApp" itself. A few natural terms are missing — users would say "reply to a message", "send a file/image", "broadcast", or "WhatsApp Business API" — and "Rube MCP (Composio)" is technical jargon users wouldn't say, so it fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

"WhatsApp Business tasks via Rube MCP (Composio)" carves out a clear niche with distinct triggers; no other plausible skill overlaps with WhatsApp-specific messaging automation. Anti-drift check: a 4 requires minor overlap risk with closely related skills, and none is evident here.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/whatsapp-automation/SKILL.md

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.