SKILLEMALL.ai
GitHub ↗ RU Sign in

CD nist-ai-rmf

Apply the NIST AI Risk Management Framework (NIST AI 100-1 + the NIST AI 600-1 Generative AI Profile) to a specific AI system, governance question, or impact assessment. Three modes — consult, governance plan, full assessment — all cite Subcategories (`GOVERN 1.1`) and Profile Action IDs (`GV-1.2-001`) verbatim. Use when the user mentions the AI RMF, NIST RMF, NIST AI 100-1, NIST AI 600-1, GenAI Profile, the four functions (Govern / Map / Measure / Manage), the trustworthy AI characteristics, the 12 GAI risks (confabulation, harmful bias, information integrity, CBRN, data privacy, etc.), or asks "what does NIST say about X" for an AI system.

lawve-ai/awesome-legal-skills Agent Skills author: lawve-ai 21 files body ≈ 2 487 tokens Open the sourcegithub.com↗ analyzed 70 min ago

Apply the NIST AI Risk Management Framework (NIST AI 100-1 + the NIST AI 600-1 Generative AI Profile) to a specific AI system, governance question, or impact…

As a process D 47/100 · Unfinished process — References files that are not bundled: references/templates/<mode>.md

ProcedureInfrastructureAI and agentsResearchtype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
89/100
safety, quality, tests
Safety 60%
96
Quality 40%
79
Run on models
none yet
Process rating
D
47/100
Unfinished process
References files that are not bundled: references/templates/<mode>.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. 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 · 4

✓ No critical or high findings

Medium and low: 4
  • low Risky intent intent-offensive-security references/gai-profile/glossary.md:109
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    On an ad hoc or more structured basis, organizations can design and use a variety of channels to engage external stakeholders in product development or review. Focus groups with select experts can pro
  • low Risky intent intent-offensive-security references/gai-profile/glossary.md:121
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    The quality of AI red-teaming outputs is related to the background and expertise of the AI red team itself. Demographically and interdisciplinarily diverse AI red teams can be used to identify flaws i
  • low Risky intent intent-offensive-security references/gai-profile/glossary.md:217
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Glazunov, S. et al. (2024) Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models. Project Zero. https://googleprojectzero.blogspot.com/2024/06/project-naptime.html
  • low Risky intent intent-offensive-security references/templates/assessment.md:58
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Address `MEASURE 2.7` — security & resilience evaluation — before production deployment. (Specifically: complete penetration testing of the prompt boundary.)

Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/templates/<mode>.md
  • note frontmatter-key unknown frontmatter key "audience"
  • note frontmatter-key unknown frontmatter key "owner"
  • note frontmatter-key unknown frontmatter key "last_verified"
  • note frontmatter-key unknown frontmatter key "freshness_window"
  • note frontmatter-key unknown frontmatter key "freshness_category"
  • note frontmatter-key unknown frontmatter key "verified_against"
  • note frontmatter-key unknown frontmatter key "verification_notes"

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: references/templates/<mode>.md
  • 0Tools and files. 1 referenced file(s) missing: references/templates/<mode>.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 5 mutating operations with no state check
  • 40Consistency. Frontmatter name (nist-ai-rmf) differs from the folder (nist-ai-rmf-rafal-fryc)
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Failures and branches. 8 branches
  • 85Steps. 43 steps, 1 vague phrases
  • 100Execution cost. Instruction body is 2487 tokens
  • low 10 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)
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 649: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 43 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.