agentleFS
Sign inStart free
justinjohnson25600justinjohnson25600/hermes_skills/cybersecurity-skills-index/SKILL.md

cybersecurity-skills-index

Skill14 starsChanged 24 days agoMITView on GitHub

On-demand lookup over 818 security procedure skills; one prompt row.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    EVERY API call. This skill ships them instead as a lookup LIBRARY under references/library/ and turns the skill itself into a router:

    line 19
  2. Very specific:

    Read references/index.json (name, one-line description, domain per skill).

    line 22
  3. Distinctive:

    Follow the chosen upstream skill's procedure.

    line 25
  4. Distinctive:

    Do NOT load more than 3 skills at once.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cybersecurity Skills Index (818 upstream skills)

The upstream library ships 818 separate SKILL.md files. Installing them all as individual Hermes skills would add ~65KB of skill index to EVERY system prompt on EVERY API call. This skill ships them instead as a lookup LIBRARY under references/library/ and turns the skill itself into a router:

  1. Read references/index.json (name, one-line description, domain per skill).
  2. Pick the 1-3 SKILL.md files that match the task; read them with read_file from this skill's own references/library/<name>/SKILL.md.
  3. Follow the chosen upstream skill's procedure. Supporting files live beside it.

Do NOT load more than 3 skills at once; they are procedures, not context.

Domains covered

cybersecurity (818) … (full counts in references/index.json)

Finding skills

  • By task: grep descriptions in references/index.json via search_files.
  • By MITRE technique: references/mappings/mitre-attack/.
  • By NIST CSF / OWASP: references/mappings/nist-csf/, references/mappings/owasp/.

Prerequisites

Upstream skills reference standard security tooling (nmap, ldap3, impacket, yara, volatility3, …). Most are NOT installed by this skill; check before use.

Scope & authorization

These are DEFENSIVE/offensive-security PROCEDURES for authorized engagements, CTF, and lab work. Confirm the engagement is authorized before executing any offensive procedure. No tooling is bundled; nothing executes automatically.

Updating the library

See UPSTREAM.md — refresh references/library + index.json together.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free