SKILLEMALL.ai
GitHub ↗ RU Sign in

BB fable-safe-prompt

Rewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent.

sickn33/agentic-awesome-skills Hermes author: sickn33 MIT 1 file body ≈ 1 141 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Rewrite allowed prompts to reduce false-positive safety triggers without bypassing policy or changing intent.

As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting

GeneratorAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code Hermes Agent
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
98
Quality 40%
76
Run on models
none yet
Process rating
B
75/100
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

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.
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 SKILL.md:29
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Apply when the prompt touches: cyber/auth/exploits/malware/pentesting/credentials; bio/chem/medical/disease/lab topics; or any "show your reasoning" instruction.
  • low Risky intent intent-offensive-security SKILL.md:72
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    4. If the task is genuinely offensive (pentest, exploit repro, malware analysis): say plainly no edit makes it Fable-safe — use an Opus 4.8 fallback or vetted Mythos, not Fable 5.

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 109 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • 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 75/100

  • 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
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 100Tools and files. Tools declared in frontmatter
  • 100Steps. 12 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1141 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
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 109: 120–800 characters recommended
  • +2Single-language instructions
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 12 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.