clawra-selfie

Edit Clawra's reference image with Grok Imagine (xAI Aurora) and send selfies to messaging channels via OpenClaw

Quality

58%

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 ./SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable bash and TypeScript code and a clear step sequence, but it is verbose due to duplicated implementations and does not leverage its own bundle scripts, hurting token efficiency and progressive disclosure. Referencing the existing scripts instead of inlining them and adding a send-step validation checkpoint would improve it.

Suggestions

Replace the inlined full bash/TypeScript implementations with references to the existing scripts/clawra-selfie.sh and scripts/clawra-selfie.ts bundle files to reduce duplication.

Add a validation/checkpoint after the OpenClaw send step (e.g., confirm delivery or check the command exit code) and a retry loop for fal.ai rate limits.

Trim the repeated prompt-template and jq payload blocks to a single canonical definition referenced by the steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with copy-paste-ready code, but the body repeats the same curl/jq payload, prompt templates, and mode logic across the inline example, the full bash script, and the TypeScript implementation, inflating the token budget with near-duplicate content.	2 / 3
Actionability	Provides fully executable curl/jq commands, a complete bash script with argument parsing and error checks, and a runnable TypeScript implementation with concrete usage examples — copy-paste ready.	3 / 3
Workflow Clarity	Steps are clearly sequenced (collect input, edit image, send), and the script validates a missing FAL_KEY and a failed image edit, but there is no validation/checkpoint after the OpenClaw send step and no retry feedback loop for the API call despite rate-limit warnings.	2 / 3
Progressive Disclosure	Well-organized sections, but the SKILL.md is a monolithic body that inlines a full bash script and a full TypeScript implementation; the existing scripts/clawra-selfie.sh and scripts/clawra-selfie.ts bundle files are not referenced from the body, so content that should be external is duplicated inline.	2 / 3
	Total	9 / 12 Passed

Description

52%

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 concrete and distinct in naming the exact tools and actions, but it omits explicit user-facing trigger phrases and any 'Use when' guidance, so a user's natural request is unlikely to match the description. Adding natural-language triggers would raise completeness and trigger_term_quality.

Suggestions

Add natural user trigger phrases, e.g. 'Use when the user asks to send a pic, selfie, or photo of Clawra to a channel.'

Append an explicit 'Use when...' clause stating when Claude should invoke this skill.

Consider including 'selfie'/'pic'/'photo' as keywords so the description mirrors how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	Lists concrete actions — 'Edit Clawra's reference image with Grok Imagine (xAI Aurora) and send selfies to messaging channels via OpenClaw' — naming specific tools, the source model, and the distribution action.	3 / 3
Completeness	Clearly states what the skill does but lacks any 'Use when...' clause; the 'when' is only implied through the product names rather than stated explicitly.	2 / 3
Trigger Term Quality	Contains no natural user phrases like 'send a pic' or 'selfie'; it uses tool/product names (Grok Imagine, xAI Aurora, OpenClaw) that a user would not spontaneously say when requesting this skill.	1 / 3
Distinctiveness Conflict Risk	Highly specific niche (Clawra selfies via Grok Imagine + OpenClaw) with distinct named tools that make it unlikely to trigger for other skills.	3 / 3
	Total	9 / 12 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: sumelabs/clawra
Path: SKILL.md
Commit: f74844e

Reviewed: 3 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.