SKILLEMALL.ai

AB prompt-crafter

Build AI prompts that actually work — for ChatGPT, Claude, Gemini, or any LLM. Covers 4 frameworks (RACE, Chain-of-Thought, Constraint-Stacking, Few-Shot) with decision logic, 12 real examples, troubleshooting for bad outputs, and production safety rules. Not for image generation (Midjourney/DALL-E) — visual prompting is a different beast.

ClawHub Agent Skills author: Crispyangles v3.1.0 MIT-0 3 files body ≈ 1 252 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 73/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

GeneratorAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
95
Quality 40%
83
Run on models
none yet
Process rating
B
73/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Instruction override medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.

For the author

An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Instruction override en-ignore-previous SKILL.md:130
    Instruction-override phrase ("ignore previous instructions") (quoted — discussed, not commanded)
    4. **Test adversarial inputs.** "Ignore all previous instructions..." is real.
    quoted

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 73/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Result and completion. Output format stated, no completion criterion
  • 100Tools and files. No external tools needed
  • 100Steps. 9 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1252 tokens

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
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 341: enough signal without eating the budget
  • +4Structure: 12 headings
  • +3Step-by-step instructions: 9 items
  • +3Output format is stated explicitly
  • +4Has examples (5 code blocks)
  • +4Reference files are cited in the instructions (1 of 1)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.

External checks

ClawHub: clean
This is a documentation-only prompt-writing guide with no executable behavior or privileged access.
LLM: benign (high) · VirusTotal: · 29 May 2026