CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-security-issue

Review an authorized security issue or private GitHub advisory for validity, severity, and a remediation plan.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/review-security-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

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

The body is a lean, operationally dense workflow with exact commands, explicit evidence and authorization gates, and clean routing to the fix skill. Its only gaps are the unspecified review-comment format/severity scale and the unaddressed failure path when authorization cannot be verified. Structure and progressive disclosure are exemplary for a skill of this size.

Suggestions

State the failure path when authorization cannot be verified (e.g., "If authorization cannot be confirmed, stop and report that the review is unauthorized") to close the workflow's one validation gap.

Specify the review comment's expected sections (e.g., validity, severity with rationale, remediation plan) and a severity scale so the deliverable is fully concrete.

DimensionReasoningScore

Conciseness

Every line is operational — authorization scope, exact gh commands, evidence gates, and routing — with no explanation of concepts Claude already knows and no padding. This matches anchor 5: lean, assumes competence, every token earns its place.

5 / 5

Actionability

Concrete, executable commands are provided (`gh api --method GET repos/OWNER/REPO/security-advisories/GHSA-ID`, `gh issue view <id> --json title,body,state,labels,comments`) plus an exact comment prefix, but the review comment's expected structure and the severity scale are unspecified ("give a severity with rationale" names no scale) — minor gaps matching anchor 4 rather than fully-executable anchor 5.

4 / 5

Workflow Clarity

Steps 1-5 are clearly sequenced with explicit gates (verify authorization, evidence check "before technical triage", posting only when authorized), but the failure path when authorization cannot be verified is never stated — only the unverified-prior-discussion case is handled — fitting anchor 4's minor validation gaps rather than anchor 5.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and well-organized sections; external pointers (CONTRIBUTING.md Label Discovery, SECURITY.md, the advisory template, fix-security-issue) are clearly signaled and one level deep, correctly delegating rather than duplicating repo documentation — matching the simple-skill case for a 5.

5 / 5

Total

18

/

20

Passed

Description

66%Weight 40%Scale 1-5

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 tight, specific, and appropriately scoped to its niche, listing three concrete review deliverables. Its main weakness is the missing "Use when..." trigger clause, which caps completeness and leaves trigger conditions implicit. Adding explicit trigger phrasing and common synonyms (vulnerability, GHSA) would raise it further.

Suggestions

Add an explicit trigger clause, e.g. "Use when a maintainer asks to review a reported vulnerability, private GitHub advisory (GHSA), or authorized security issue."

Include natural synonyms such as "vulnerability", "GHSA", or "CVE" so the description matches the phrases users actually say.

Clarify the boundary with the fix workflow (e.g., "reviews and proposes plans only; does not apply fixes") to reduce overlap with fix-security-issue.

DimensionReasoningScore

Specificity

"for validity, severity, and a remediation plan" enumerates three concrete deliverables against named targets ("authorized security issue", "private GitHub advisory"), matching anchor 4's several specific actions with minor coverage gaps. Not 5 because the workflow steps (fetch, verify, post) are not surfaced, and not 3 since it goes beyond 1-2 concrete actions.

4 / 5

Completeness

The "what" is clear (review for validity, severity, remediation plan) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3; the "when" is only weakly implied by "authorized".

3 / 5

Trigger Term Quality

Natural terms like "security issue", "private GitHub advisory", "review", "severity", and "remediation plan" give good keyword coverage, but common variants users would say — "vulnerability", "GHSA", "CVE" — are missing, matching anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

"private GitHub advisory" and "authorized" carve a specific niche, but "review ... for a remediation plan" creates minor overlap risk with closely related fix/security-review skills (e.g., the fix-security-issue skill the body routes to), fitting anchor 4 rather than 5's minimal-conflict clear niche.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository

NVIDIA/OpenShell

Path

.agents/skills/review-security-issue/SKILL.md

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.