CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

verify-fix

Use only when the user explicitly requests verification that a security fix remediates a reported vulnerability. Do not invoke automatically while implementing fixes, reviewing ordinary code changes, or running tests. Do not use for non-security fixes, candidate finding validation, or full repository scans.

66

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 concise, well-structured instruction-only skill with a precise output contract and a clear workflow. Its main weaknesses are the dangling external reference (affecting actionability and progressive disclosure) and the absence of an explicit validation feedback loop in the workflow.

Suggestions

Either ship references/static-finding-assessment.md inside the bundle or inline the minimum assessment checklist so the skill is self-contained and the reference path resolves.

Add an explicit validate-and-escalate loop (e.g., 'If evidence is insufficient to prove fixed or still_vulnerable, mark inconclusive — do not re-run destructive checks') to give the workflow a clear feedback checkpoint.

Specify what counts as evidence in the 'evidence' field (e.g., 'file:line of the closed control, or the failing reproducer command') so the result contract is fully actionable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what a vulnerability or security boundary is, and every section (When to Use, Objective, Assessment Method, Workflow, Result Contract) earns its place, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Provides a concrete 5-step workflow and a copy-paste-ready JSON result contract with defined status values, but the core assessment method depends on an external reference ('../../references/static-finding-assessment.md') that does not exist in the bundle, leaving a gap versus fully self-contained executable guidance.

4 / 5

Workflow Clarity

A clear numbered sequence with implicit checkpoints ('Confirm the current checkout contains the affected component', 'Treat closed tickets... as insufficient proof'), but it lacks an explicit validate-and-retry feedback loop, fitting 'clear sequence with most checkpoints present; minor validation gaps' rather than the explicit-loop anchor at 5.

4 / 5

Progressive Disclosure

Well-organized sections with a clearly signaled one-level-deep reference to an assessment file, but the referenced path does not resolve to a real file in the bundle, so navigation is good but not seamless — matching 'good structure; references mostly clear; minor organization gaps' rather than the easy-navigation anchor at 5.

4 / 5

Total

17

/

20

Passed

Description

75%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 a strong, tightly-scoped trigger statement that clearly answers what and when and sharply limits conflict risk. The only relative weakness is specificity and trigger-term coverage, which name the core action but lack synonyms and multiple concrete actions.

Suggestions

Add a couple of concrete actions or synonyms (e.g., 'patch', 'remediation', 'CVE') to broaden natural trigger-term coverage and lift specificity beyond a single action.

Consider naming the output the user gets (e.g., 'returns a per-finding fixed/still_vulnerable/inconclusive verdict') so the 'what' includes the deliverable, not just the act of verifying.

DimensionReasoningScore

Specificity

Names the domain ('security fix') and one concrete action ('verification that a security fix remediates a reported vulnerability') but does not enumerate multiple specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the several-action anchor at 4.

3 / 5

Completeness

Explicitly answers both what (verify a security fix remediates a reported vulnerability) and when ('Use only when the user explicitly requests verification...') with concrete trigger phrases and detailed exclusion guidance, matching the top anchor.

5 / 5

Trigger Term Quality

Includes relevant natural terms ('verify', 'security fix', 'vulnerability', 'remediates') but omits common synonyms and variations a user might say (patch, remediation, CVE, is it fixed), fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

A clear niche (security-fix verification) with extensive negative-scope guidance ('Do not use for non-security fixes, candidate finding validation, or full repository scans') that minimizes conflict with adjacent skills, matching the minimal-conflict-risk anchor.

5 / 5

Total

16

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

openai/plugins

Path

plugins/codex-security/skills/verify-fix/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.