SKILLEMALL.ai

A pulse-app

Use this skill to help developers get started building Pulse Apps — full-stack React extensions for Pulse Editor that use Module Federation. Trigger when a user asks to: - Create or scaffold a new Pulse App - Understand Pulse App architecture (frontend, backend, skills) - Add server functions or skills to an existing Pulse App - Configure pulse.config.ts or understand app metadata - Use @pulse-editor/react-api hooks (useLoading, useActionEffect) - Develop, preview, or build a Pulse App DO NOT trigger for general React or TypeScript questions unrelated to Pulse Apps.

ClawHub Agent Skills author: Shellishack v1.0.0 2 files body ≈ 1 584 tokens open source ↗ analyzed 26 h ago
GeneratorSoftware developmenttype and topics are labelled automatically from the skill text
JSON
A
93/100
Overall score
Safety 60%
100
Quality 40%
82
Tests bonus
0

How to improve

  1. Add evals/evals.json with 4–6 real requests and expected answers: the full check will then use your cases instead of a model draft.
  2. Add a spec.yaml with triggers and assertions (skilltest init): the behaviour contract for CI.

Guard findings · 0

✓ No critical or high findings

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

Lint

✓ Lint: no remarks

Process maturity 45/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 4 mutating operations with no state check
  • 40Consistency. Frontmatter name (pulse-app) differs from the folder (pulse-app-skill)
  • 60Tools and files. Uses tools (node) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 12 steps
  • 100Execution cost. Instruction body is 1584 tokens
  • low 11 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
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 572: enough signal without eating the budget
  • +4Structure: 26 headings
  • +3Step-by-step instructions: 12 items
  • +4Has examples (14 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

External checks

ClawHub: clean
This is a documentation-only developer guide for building Pulse Apps, with expected local development commands and no hidden behavior found.
LLM: benign (high) · VirusTotal: · 29 May 2026