CtrlK
BlogDocsLog inGet started
Tessl Logo

triage-finding

Use when the user supplies or imports existing security findings, vulnerability reports, or security/vulnerability Jira/Linear tickets from scanners, advisories, GitHub, Atlassian Rovo, Linear, or similar backlog sources and wants static repo-impact triage. Do not use for discovery, duplicate-bug triage, validation, or fixes.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, checkpointed multi-step workflow, but it is somewhat verbose due to repeated boundary criteria and references three external files that are not present in the bundle. Tightening the duplicated gate sections and resolving or removing the broken external references would raise conciseness and progressive disclosure.

Suggestions

Consolidate the repeated source/boundary/confirmation criteria from 'SECURITY.md Guidance Gate', 'Surface and Boundary Gate', and 'Verdict Rules' into a single section to reduce verbosity.

Fix or remove the three non-existent external references (../../references/static-finding-assessment.md, ../../references/security-guidance.md, ../../schemas/findings.schema.json) so progressive disclosure points only to real files.

Consider moving the long Inputs field list and the App Surface output-contract field list into a reference file to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

The body is skill-specific policy with no basic-concept pedagogy, but boundary/confirmation criteria are repeated across 'SECURITY.md Guidance Gate', 'Surface and Boundary Gate', and 'Verdict Rules', so it is mostly efficient yet could be tightened.

2 / 3

Actionability

As an instruction-only skill it provides concrete, copy-ready guidance: explicit source_type enum values, triage_item_id format, the full triage-finding/v0 output contract fields, and the exact app-tool name open_codex_security_triage_results, so absence of code is not penalized.

3 / 3

Workflow Clarity

A 14-step workflow with intake branches and explicit validation checkpoints ('stop without emitting triage JSON' on missing source, missing ticket content, or unavailable auth) plus per-input output preservation gives clear sequencing with feedback loops for the batch operation.

3 / 3

Progressive Disclosure

Local references (references/ticket-intake.md, github-rest-intake.md, triage-result-contract.md) are one-level-deep and well-signaled, but three external paths referenced in the body do not exist in the bundle: ../../references/static-finding-assessment.md, ../../references/security-guidance.md, and ../../schemas/findings.schema.json.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, well-triggered, complete, and clearly differentiated, with an explicit 'Use when...' clause and a 'Do not use for...' boundary. It uses neutral third-person voice throughout. This is a strong, anchor-matching description.

DimensionReasoningScore

Specificity

Names multiple concrete intake actions ('supplies or imports existing security findings, vulnerability reports, or security/vulnerability Jira/Linear tickets') and the concrete action of 'static repo-impact triage', matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('static repo-impact triage' of supplied findings) and when via the 'Use when the user supplies or imports...' clause, plus an explicit 'Do not use for...' boundary, the top anchor for both what AND when.

3 / 3

Trigger Term Quality

Covers natural terms a user would say — 'security findings, vulnerability reports', 'Jira/Linear tickets', 'scanners, advisories, GitHub, Atlassian Rovo, Linear' — giving good coverage of natural trigger language rather than jargon.

3 / 3

Distinctiveness Conflict Risk

The 'Do not use for discovery, duplicate-bug triage, validation, or fixes' clause carves a clear niche distinct from sibling skills, making wrong-skill triggering unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.