agentleFS
zyphr-labszyphr-labs/bounty-harness/.claude/skills/technique-kb/SKILL.md

technique-kb

Skill1 starsChanged 3 months agoMITView on GitHub

This is a thin human-facing router. Use skill.yaml as the source of truth for exact commands, inputs, outputs, and workflow chaining.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Start with validate to verify all technique YAML files against the schema.

    line 16
  2. Very specific:

    Use match to find techniques applicable to a specific domain profile.

    line 17
  3. Very specific:

    Use search to query by keyword, category, severity, or standard ID.

    line 18
  4. Distinctive:

    If a workflow has no script reference, treat it as a manual or tool-native workflow.

    line 20
  5. Distinctive:

    Not applicable — this skill produces technique matching data, not vulnerability findings.

    line 30
  6. Distinctive:

    All techniques include standards mappings, detection signals, and false-positive rules.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Technique Knowledge Base

Overview

Structured knowledge base of every attack technique. Stores preconditions, detection signals, payload families, false-positive rules, required evidence, severity mappings, and standards references (WSTG, ASVS, API Top 10, VRT, CWE). The planner uses this KB to determine WHICH techniques apply to WHICH surfaces before running any tooling.

This is a thin human-facing router. Use skill.yaml as the source of truth for exact commands, inputs, outputs, and workflow chaining.

Quick Reference

  • Skill: technique-kb
  • Severity range: info, low, medium, high, critical
  • Required tools: python3, jq
  • Expected input files: none
  • Scope check: not applicable — read-only technique definitions.

Workflow Selection

  • Start with validate to verify all technique YAML files against the schema.
  • Use match to find techniques applicable to a specific domain profile.
  • Use search to query by keyword, category, severity, or standard ID.
  • Runbooks: use runbooks/.
  • If a workflow has no script reference, treat it as a manual or tool-native workflow.

Available Workflows

WorkflowPurposeScript pathsPrimary outputsEvidence
validateValidate all technique YAML files against the canonical schema..claude/skills/technique-kb/scripts/technique_validator.py$OUTDIR/technique-kb/validation.txt$OUTDIR/technique-kb/evidence/
matchMatch techniques to domain archetypes and attack surfaces..claude/skills/technique-kb/scripts/technique_matcher.py$OUTDIR/technique-kb/matches.json$OUTDIR/technique-kb/evidence/
searchSearch techniques by keyword, category, severity, or standard ID..claude/skills/technique-kb/scripts/technique_search.py$OUTDIR/technique-kb/search_results.json$OUTDIR/technique-kb/evidence/

Evidence Required

  • Not applicable — this skill produces technique matching data, not vulnerability findings.
  • All techniques include standards mappings, detection signals, and false-positive rules.

References

  • Source of truth: skill.yaml
  • Runbooks: runbooks/
  • Technique schema: technique_schema.yaml
  • Standards: WSTG, ASVS, API Top 10, VRT, CWE

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.