WhatsApp router: history/search/read/send; wacrawl read, wacli live.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/whatsapp/SKILL.md

Quality

Content

83%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.

The body is an excellent, lean routing skill: sharp source boundaries, concrete copy-paste commands, and explicit safety gating for destructive operations. Its one real weakness is the absence of validation/verification checkpoints around the live send/mutate workflows, which the rubric caps at workflow clarity 3.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: 'Keep the source boundary sharp' followed by terse tool boundaries, a routing table, safety rules, and command blocks — no concept explanations and no padding. Every token earns its place, matching anchor 5.	5 / 5
Actionability	Commands are fully executable and copy-paste ready with realistic placeholders and flags, e.g. 'wacrawl messages --chat JID --asc --limit 100' and 'wacli --account me send text --to JID_OR_NAME --message "message"', covering the common cases (status, unread, search, media, send). Matches anchor 5.	5 / 5
Workflow Clarity	Routing is well sequenced and destructive operations are gated ('use `wacli` only after explicit user intent'), but the send/mutate workflows involve destructive, outward-facing operations with no validation or verification steps — no auth-status check sequenced before send and no post-send confirmation. Per the judging guideline, missing validation in destructive workflows caps this at 3; it is not 2 because the sequence and intent-gating are clear.	3 / 5
Progressive Disclosure	No bundle files exist; the body is well organized into Routing, Safety, Common Commands, Comparisons, and Repo Pointers, with one-level-deep pointers to the per-tool skills ('read that tool's own skill too', 'Global skill copies: ~/Projects/agent-scripts/skills/...'). Not 5 because the sizable Common Commands catalog could arguably live in reference files and the pointers are to repo paths rather than clearly-signaled skill files — anchor 4's 'good structure, minor organization gaps'.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description is admirably terse and distinct, but it reads like an internal note rather than a trigger description: it cryptically compresses capabilities and omits any 'when to use this' guidance. Adding an explicit trigger clause and the natural vocabulary users actually say (messages, chats, unread, media) would raise it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about WhatsApp messages, history, unread counts, or sending — or mentions wacrawl or wacli.'

Include natural synonyms users would say — 'messages', 'chats', 'unread', 'media', 'backup' — alongside the current verb list, so the description matches real queries.

Rewrite the telegraphic fragments ('wacrawl read, wacli live') as full third-person clauses stating each tool's role, e.g. 'wacrawl reads the local Desktop archive; wacli operates live linked-device accounts for sending and sync.'

Dimension	Reasoning	Score
Specificity	Names the domain and a few concrete actions ("history/search/read/send; wacrawl read, wacli live"), but the telegraphic, jargon-heavy phrasing leaves coverage minimal and non-comprehensive — no mention of accounts, media, sync, or unread triage. This fits anchor 3 (1-2 concrete actions, not comprehensive) better than anchor 4, which expects several listed actions with only minor gaps.	3 / 5
Completeness	There is a recognizable 'what' (routing history/search/read/send across wacrawl and wacli), but the description contains no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not score 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	Relevant keywords are present ("WhatsApp", "history", "search", "read", "send") but common natural variations users would say are missing: "messages", "chats", "unread", "media", "backups". This matches anchor 3 (some relevant keywords, missing common variations or synonyms) rather than anchor 4's good coverage.	3 / 5
Distinctiveness Conflict Risk	"WhatsApp router" plus the tool names wacrawl/wacli carves a mostly distinct niche with low conflict risk against unrelated skills. Not 5 because the skill ecosystem includes separate wacrawl and wacli skills it routes to, creating minor overlap risk with those closely related skills — exactly anchor 4.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: steipete/agent-scripts
Path: skills/whatsapp/SKILL.md
Commit: 3f8c6a3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.