SKILLEMALL.ai
GitHub ↗ RU Sign in

BB falsify

The scientific thinking protocol for AI agents. Use when facing complex, ambiguous, or high-stakes questions where guessing is costly: hypothesis → attempt to break it → evidence → calibrated conclusion.

sickn33/agentic-awesome-skills Hermes author: sickn33 MIT 4 files body ≈ 7 585 tokens Open the sourcegithub.com↗ analyzed 2 d ago

The scientific thinking protocol for AI agents.

As a process B 71/100 · Nearly there — weak spots: result and completion, inputs and preconditions

AnalyzerAI and agentsResearchtype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code Hermes Agent
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
98
Quality 40%
70
Run on models
none yet
Process rating
B
71/100
Nearly there
Inputs and preconditions w 11
0
Result and completion w 14
40
When it triggers w 12
50
the three weakest of ten parameters · all ten

The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Risky intent intent-offensive-security references/mental-models.md:26
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Red Team Analysis | How would an adversary defeat this plan? |
  • low Risky intent intent-offensive-security SKILL.md:132
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)
    Toolbox: *pre-mortem* (it is a year later and this failed — why?), *Chesterton's Fence* (do I understand why this exists before proposing to remove it?), *red team* (how would an adversary defeat this
    quoted

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 203 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning body-long SKILL.md body ≈ 7585 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "risk"
  • note frontmatter-key unknown frontmatter key "source"
  • note frontmatter-key unknown frontmatter key "source_repo"
  • note frontmatter-key unknown frontmatter key "source_type"
  • note frontmatter-key unknown frontmatter key "date_added"
  • note frontmatter-key unknown frontmatter key "tools"
  • note frontmatter-key unknown frontmatter key "license_source"

Process rating: all ten parameters 71/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 7585 tokens
  • 85Steps. 78 steps, 1 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 4 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 12 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
  • +2Single-language instructions
  • +3Description length 203: enough signal without eating the budget
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 78 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

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