Nist Csf logo

Nist Csf

Community
jgsystemsconsulting
nist-csf

Knowledge base from NIST Cybersecurity Framework (CSF) 2.0. Use for cybersecurity risk management, GOVERN, IDENTIFY, PROTECT, DETECT, RESPOND, RECOVER, Organizational Profiles, CSF Tiers, supply chain risk, enterprise risk management, incident response. Covers the CSF 2.0 document only; does not cover specific SP 800-53 controls, NIST RMF system authorization steps, or sector-specific regulations.

Overview

Publisherjgsystemsconsulting
Repositoryjgs-se-knowledge-packs
Skill namenist-csf
Stars
121
Forks
1
Bundled files
12
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 12 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jgsystemsconsulting on GitHub. Read the source before you install it.

Installation

Install the Nist Csf AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/nist-csf
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs.git /tmp/jgs-se-knowledge-packs
mkdir -p .claude/skills
cp -r /tmp/jgs-se-knowledge-packs/packs/nist-csf .claude/skills/nist-csf
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Nist Csf in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Nist Csf on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Nist Csf is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

NIST Cybersecurity Framework (CSF) 2.0

Source: NIST CSWP 29 (US Government work, public domain) | Chapters: 8

When to use

Reach for this pack when designing, assessing, or communicating about a cybersecurity program using the NIST CSF 2.0 vocabulary and structure. It is the right starting point for mapping cybersecurity outcomes to the six Functions, understanding how Profiles and Tiers work, addressing supply chain cybersecurity risk (GV.SC), or integrating cybersecurity into enterprise risk management. Also use it to orient incident response, detection, and recovery planning against NIST's authoritative outcome taxonomy.

Prerequisites: none — plain Markdown; no MCP server, API key, or licence tier needed at runtime.

How to Use This Skill

  • Without arguments — load the core frameworks below.
  • With a topic — ask about governance, supply chain risk, identity and access control, incident response, detection, recovery, Profiles, Tiers, or ERM integration; I read the relevant chapter.
  • With a chapter — ask for ch01, ch02, ch03, ch04, ch05, ch06, ch07, or ch08.

Supporting files: glossary.md, patterns.md, cheatsheet.md.

Core Frameworks & Mental Models

The Six CSF Functions

The CSF Core is organized into six Functions. GOVERN sits at the center; the other five surround it. All six operate concurrently — GOVERN, IDENTIFY, PROTECT, and DETECT run continuously; RESPOND and RECOVER must be ready at all times.

FunctionIdentifierCore question answered
GOVERNGVHow does the organization set cybersecurity strategy, policy, and oversight?
IDENTIFYIDWhat are our assets and what cybersecurity risks do they face?
PROTECTPRWhat safeguards prevent or reduce the impact of adverse events?
DETECTDEHow do we find cybersecurity attacks and compromises in progress?
RESPONDRSWhat actions do we take once an incident is declared?
RECOVERRCHow do we restore normal operations after an incident?

GOVERN (GV) — Six Categories

  • GV.OC — Organizational Context: mission, stakeholders, dependencies, legal/regulatory obligations
  • GV.RM — Risk Management Strategy: risk appetite, risk tolerance, standardized risk method, ERM integration
  • GV.RR — Roles, Responsibilities, Authorities: accountability, resources, HR integration
  • GV.PO — Policy: establishment, enforcement, periodic review
  • GV.OV — Oversight: results feed strategy adjustments (the governance feedback loop)
  • GV.SC — Cybersecurity Supply Chain Risk Management: full supplier life cycle from due diligence through post-relationship obligations

IDENTIFY (ID) — Three Categories

  • ID.AM — Asset Management: inventory of hardware, software, data, network flows, supplier services; life-cycle management; criticality classification
  • ID.RA — Risk Assessment: vulnerability identification, threat intelligence, likelihood/impact estimation, risk response prioritization
  • ID.IM — Improvement: continuous learning from evaluations, exercises, operations, and incident plan maintenance

PROTECT (PR) — Five Categories

  • PR.AA — Identity Management, Authentication, and Access Control: credential management, identity proofing, authentication, least privilege, separation of duties, physical access
  • PR.AT — Awareness and Training: general and specialized-role training
  • PR.DS — Data Security: at-rest, in-transit, and in-use data protection; tested backups
  • PR.PS — Platform Security: configuration management, software/hardware maintenance, log generation, unauthorized software prevention, secure development life cycle
  • PR.IR — Technology Infrastructure Resilience: network protection, environmental threat protection, resilience mechanisms, capacity management

DETECT (DE) — Two Categories

  • DE.CM — Continuous Monitoring: networks, physical environments, personnel activity, external service providers, computing hardware/software/runtime
  • DE.AE — Adverse Event Analysis: correlation across sources, impact/scope estimation, threat intelligence integration, incident declaration (DE.AE-08)

RESPOND (RS) — Four Categories

  • RS.MA — Incident Management: plan execution, triage, categorization, prioritization, escalation, recovery criteria
  • RS.AN — Incident Analysis: root cause establishment, record integrity/provenance preservation, magnitude validation
  • RS.CO — Incident Response Reporting and Communication: stakeholder notification, information sharing
  • RS.MI — Incident Mitigation: containment, eradication

RECOVER (RC) — Two Categories

  • RC.RP — Incident Recovery Plan Execution: recovery action selection, backup integrity verification (RC.RP-03), post-incident operational norms (RC.RP-04), restoration verification, formal recovery declaration (RC.RP-06)
  • RC.CO — Incident Recovery Communication: stakeholder coordination, approved public messaging

Organizational Profiles and Tiers

Profiles translate Core outcomes into documented posture:

  • Current Profile — what the organization is achieving now
  • Target Profile — prioritized desired outcomes given mission, risk appetite, and threat landscape
  • Gap analysis — comparison driving a prioritized action plan (risk register, POA&M)
  • Community Profile — sector-specific published baseline usable as a Target Profile starting point

Tiers characterize governance and management rigor:

TierNameGovernanceManagement
1PartialAd hocLimited organizational awareness
2Risk InformedAd hoc, not formally based on objectivesIrregular, case-by-case implementation
3RepeatableFormally approved, expressed as policyOrganization-wide approach; cybersecurity information shared routinely
4AdaptiveRisk-informed, culturally embedded, predictiveAdapts based on lessons learned; real-time supply chain risk information

Key decision rule: Progress to higher Tiers only when risks/mandates are greater OR cost-benefit analysis justifies it. Tier 4 is not a universal target.

CSF and Enterprise Risk Management

The CSF explicitly integrates with ERM: GV.RM-03 requires cybersecurity risk activities to be included in enterprise risk management processes. The CSF helps translate cybersecurity terminology into general risk language that executives understand. NIST IR 8286 series provides detailed integration guidance. Cybersecurity risk sits alongside financial, privacy, supply chain, and reputational risks in the enterprise risk portfolio.

Key Interlock Points (cross-Function dependencies)

  • PROTECT → DETECT: PR.PS-04 log generation is the monitoring substrate DE.CM requires.
  • PROTECT → RECOVER: PR.DS-11 tested backups must exist before RC.RP-03 backup integrity verification can occur.
  • DETECT → RESPOND: DE.AE-08 incident declaration is the formal trigger for RS.MA.
  • RESPOND → RECOVER: RS.MA-05 recovery initiation criteria gate the transition to RC.RP.
  • RECOVER → IDENTIFY: RC.RP-06 documentation feeds ID.IM improvement identification.
  • IDENTIFY → GOVERN: ID.IM improvements escalate to GV.PO and GV.OV for strategy and policy updates.

Chapter Index

#SectionKey content
ch01CSF Overview and ComponentsCore, Profiles, Tiers, Informative References, Implementation Examples, QSGs
ch02GOVERN (GV) FunctionGV.OC, GV.RM, GV.RR, GV.PO, GV.OV, GV.SC; risk appetite; C-SCRM; ERM integration
ch03IDENTIFY (ID) FunctionID.AM, ID.RA, ID.IM; asset inventories; threat intelligence; risk assessment; continuous improvement
ch04PROTECT (PR) FunctionPR.AA, PR.AT, PR.DS, PR.PS, PR.IR; least privilege; data security; platform security; resilience
ch05DETECT (DE) FunctionDE.CM, DE.AE; continuous monitoring; anomaly detection; incident declaration criteria
ch06RESPOND (RS) FunctionRS.MA, RS.AN, RS.CO, RS.MI; triage; root cause; containment; eradication; communication
ch07RECOVER (RC) FunctionRC.RP, RC.CO; backup integrity; post-incident norms; recovery declaration; public messaging
ch08Organizational Profiles, Tiers, and Using the CSFCurrent/Target Profiles; gap analysis; POA&M; Tier 1-4 descriptors; ERM integration; bidirectional communication

Topic Index

  • Access control / least privilege / separation of duties → ch04 (PR.AA)
  • Adaptive (Tier 4) → ch08
  • Asset inventory / asset management → ch03 (ID.AM)
  • Awareness and training → ch04 (PR.AT)
  • Backup / data recovery → ch04 (PR.DS-11), ch07 (RC.RP-03)
  • Community Profile → ch01, ch08
  • Continuous monitoring → ch05 (DE.CM)
  • C-SCRM / supply chain risk → ch02 (GV.SC)
  • Current Profile / Target Profile → ch08
  • Data security (at rest / in transit / in use) → ch04 (PR.DS)
  • DETECT function overview → ch05
  • Enterprise risk management (ERM) → ch02 (GV.RM-03), ch08
  • Gap analysis / action plan / POA&M → ch08
  • GOVERN function overview → ch02
  • Identification of assets → ch03 (ID.AM)
  • IDENTIFY function overview → ch03
  • Incident declaration → ch05 (DE.AE-08)
  • Incident management / triage → ch06 (RS.MA)
  • Incident response plan → ch03 (ID.IM-04), ch06
  • Improvement / lessons learned → ch03 (ID.IM)
  • Indicators of compromise → ch05 (DE.CM)
  • Informative References → ch01
  • KPIs / KRIs / reporting → ch08
  • Organizational Profile → ch01, ch08
  • Oversight / feedback loop → ch02 (GV.OV)
  • Partial (Tier 1) → ch08
  • Platform security / configuration management → ch04 (PR.PS)
  • Policy → ch02 (GV.PO)
  • Privacy risk → ch01, ch08
  • Quick-Start Guides (QSGs) → ch01
  • RECOVER function overview → ch07
  • Recovery declaration → ch07 (RC.RP-06)
  • Repeatable (Tier 3) → ch08
  • RESPOND function overview → ch06
  • Risk appetite / risk tolerance → ch02 (GV.RM-02)
  • Risk assessment → ch03 (ID.RA)
  • Risk Informed (Tier 2) → ch08
  • Roles, responsibilities, authorities → ch02 (GV.RR)
  • Root cause analysis → ch06 (RS.AN-03)
  • Secure software development → ch04 (PR.PS-06)
  • Supplier / third-party risk → ch02 (GV.SC), ch03 (ID.RA-09, ID.RA-10)
  • Technology infrastructure resilience → ch04 (PR.IR)
  • Threat intelligence → ch03 (ID.RA-02), ch05 (DE.AE-07)
  • Tiers overview → ch08

Supporting Files

  • glossary.md — alphabetical definitions for ~45 CSF 2.0 terms with chapter references
  • patterns.md — 12 named patterns with When/How/Trade-offs for implementing CSF outcomes
  • cheatsheet.md — decision rules, function/category quick-reference table, and tells & smells

Scope & Limits

This pack covers NIST CSWP 29 (CSF 2.0) as published February 26, 2024 — the framework document itself, including the CSF Core (Appendix A), Tiers (Appendix B), and Glossary (Appendix C). It does not cover the content of Informative References (e.g., SP 800-53 control details, SP 800-161r1 C-SCRM practices, NIST RMF authorization steps), sector-specific Community Profiles, or the CSF 2.0 online Reference Tool. This is a US Government public domain work; no copyright restrictions apply to the source document.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Nist Csf AI skill do?

Knowledge base from NIST Cybersecurity Framework (CSF) 2.0. Use for cybersecurity risk management, GOVERN, IDENTIFY, PROTECT, DETECT, RESPOND, RECOVER, Organizational Profiles, CSF Tiers, supply chain risk, enterprise risk management, incident response. Covers the CSF 2.0 document only; does not cover specific SP 800-53 controls, NIST RMF system authorization steps, or sector-specific regulations.

Why use Nist Csf on TypingMind?

Because you install it once and use it with any model. Nist Csf is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Nist Csf in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jgsystemsconsulting/jgs-se-knowledge-packs/tree/main/packs/nist-csf. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Nist Csf?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Nist Csf?

As many as you like. As long as a model supports skills, you can use Nist Csf with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Nist Csf AI skill free?

It is published on GitHub by jgsystemsconsulting. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇