SKILLEMALL.ai

BF FlexArm Robot Controller

Give AI agents physical eyes and a hand to operate any smartphone. Built-in 50+ atomic actions (click, swipe, OCR, screenshot). AI can call them directly. Also supports YAML scripts. Script Store: once one AI learns an app, all AI agents instantly master it. For strong-reasoning AI models: they can autonomously explore new apps via camera + robot arm — see, reason, act, verify. This closed-loop lets AI use any phone function, almost infinitely.

ClawHub Agent Skills author: hamlet0168 v1.0.2 MIT-0 2 files body ≈ 9 760 tokens Open the sourceclawhub.ai analyzed 29 h ago

Give AI agents physical eyes and a hand to operate any smartphone.

As a process F 38/100 · Will not run — References files that are not bundled: scripts/hello_flexarm.yaml, scripts/configs/app_desktop.yaml, scripts/configs/app_xxx.yaml

ProcedureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
100
Quality 40%
49
Run on models
none yet
Process rating
F
38/100
Will not run
References files that are not bundled: scripts/hello_flexarm.yaml, scripts/configs/app_desktop.yaml, scripts/configs/app_xxx.yaml
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Give AI agents physical eyes and a hand to operate any smartphone.… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 9760 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: scripts/hello_flexarm.yaml
  • warning missing-ref reference to a missing file: scripts/configs/app_desktop.yaml
  • warning missing-ref reference to a missing file: scripts/configs/app_xxx.yaml
  • warning missing-ref reference to a missing file: scripts/run_xxx.yaml
  • note frontmatter-key unknown frontmatter key "requirements"

Process rating: all ten parameters 38/100

Will not run. References files that are not bundled: scripts/hello_flexarm.yaml, scripts/configs/app_desktop.yaml, scripts/configs/app_xxx.yaml
  • 0Tools and files. 4 referenced file(s) missing: scripts/hello_flexarm.yaml, scripts/configs/app_desktop.yaml, scripts/configs/app_xxx.yaml
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (FlexArm Robot Controller) differs from the folder (flexarm-robot-arm)
  • 40Execution cost. Instruction body is 9760 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 60Steps. 92 steps, 4 vague phrases
  • 100When it triggers. States when to use and when not to
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • low 14 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 448: enough signal without eating the budget
  • +4Structure: 100 headings
  • +3Step-by-step instructions: 92 items
  • +4Has examples (83 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.

External checks

ClawHub: clean
The skill is a coherent local controller for a real phone robot arm, with sensitive but disclosed capabilities that users should handle carefully.
LLM: benign (medium) · VirusTotal: · 9 Jun 2026