triage Skill
Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner output and writes TRIAGE.json + TRIAGE.md sorted by what actually needs engineering attention. Use when asked to "triage findings", "validate Published by anthropics in defending-code-reference-harness.
What is triage Skill?
Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner output and writes TRIAGE.json + TRIAGE.md sorted by what actually needs engineering attention. Use when asked to "triage findings", "validate Published by anthropics in defending-code-reference-harness. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Security review
- Documentation
- Security review use cases
- Documentation use cases
Technical details
- Install or run with Copy skill directory
When to use triage Skill
- Use it for security review.
- Use it for documentation.
Built with
Editorial notes
Source
- Creator: anthropics
- Repository: anthropics/defending-code-reference-harness
- Skill file: .claude/skills/triage/SKILL.md
What it does
Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner. Takes a directory or file of scanner output and writes TRIAGE.json + TRIAGE.md sorted by what actually needs engineering attention. Use when asked to "triage findings", "validate
Skill instructions
triage Adversarial triage of raw security-scanner output. Does four jobs: verify each finding is real, deduplicate across runs and scanners, rank survivors by derived exploitability rather than the scanner's claimed severity, and route each to a component owner. Output is a short, ranked, owned list instead of a raw dump. Invoke with /triage <findings-path [--auto] [--votes N] [--repo PATH] [--fp-rules FILE]. Arguments (parse from $ARGUMENTS; positional $1/$2 expansion is not stable across runtimes): - findings path (first positional, required): a JSON file, a directory of JSON files, a VULN-FINDINGS.json, a pipeline results/<target/<ts/ directory, or a markdown report. - --auto: skip the interview and use defaults. Default mode is interactive. - --votes N: verifier votes per finding (default 3; use 1 for a quick pass, 5 for high-stakes batches). - --repo PATH: path to the target codebase, read-only (default cwd). Verification needs source access; the skill stops with an error if the c
Explore related resources
Frequently asked questions
What is triage?
triage is a open-source AI agent skill with Copy skill directory. Triage a batch of raw security findings. Verify each is real, collapse duplicates, re-rank by derived exploitability, and tag with an owner.
Who is triage best for?
triage is best for reusing agent instructions, scripts, and references, security review workflows, documentation workflows.
How do I install triage?
Install or run triage using Copy skill directory. Check triage for the latest setup command.
Is triage actively maintained?
triage may need a closer maintenance check before production use.
Auto-fetched from GitHub.
