CtrlK
BlogDocsLog inGet started
Tessl Logo

sast-report

Consolidate all SAST vulnerability results from the sast/ folder into a single final report ranked by severity and confidentiality impact. Reads all *-results.md files and produces sast/final-report.md. Run after all vulnerability detection skills complete. Use when asked to generate a final report, consolidate findings, or summarize security results.

76

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The content is a well-structured, actionable single-file skill with a precise output template and clear sequencing. Its one gap is the absence of an explicit verification checkpoint for the consolidation step, which is appropriate for a batch aggregation task.

Suggestions

Add a verification checkpoint after Step 2 (e.g., 'Confirm every existing *-results.md file was read and its VULNERABLE/LIKELY VULNERABLE findings extracted before sorting') to satisfy the batch-operation feedback-loop expectation and lift workflow clarity.

Include a reconciliation check in Step 4 that the Executive Summary counts match the number of findings rendered in each severity section.

Note explicitly what to do if a result file is malformed or missing required fields (e.g., skip and log vs. halt), to make the batch workflow's error handling concrete.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows; the severity table and exact output template are domain-specific details that earn their tokens. It is not below 3 because there is no padded preamble or redundant explanation.

3 / 3

Actionability

It provides an exact, copy-paste-ready markdown output template plus a concrete input-file discovery list, explicit extraction fields, and a defined sort order — fully executable guidance.

3 / 3

Workflow Clarity

The four steps (discover, extract, score/sort, write) are clearly sequenced, but there is no explicit validation/verification checkpoint confirming all result files were read or that summary counts match findings; per the rubric this caps batch workflows at 2. It is above 1 because the sequence itself is unambiguous with stated prerequisites.

2 / 3

Progressive Disclosure

The skill is a single self-contained SKILL.md with well-organized sections (inclusions, severity ranking, execution steps, template, reminders) and no nested or misdirected references, fitting the well-organized single-file pattern.

3 / 3

Total

11

/

12

Passed

Description

100%

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, trigger-rich, and complete, clearly stating both the concrete actions performed and the natural language conditions under which to invoke the skill. It is concise yet distinguishable from the individual SAST detection skills.

DimensionReasoningScore

Specificity

Multiple concrete actions are named: "Consolidate all SAST vulnerability results", "ranked by severity and confidentiality impact", and "produces sast/final-report.md" — matching the multiple-specific-actions anchor rather than the domain-only level 2.

3 / 3

Completeness

It explicitly answers both what (consolidate/rank/produce the report) and when via a clear "Use when asked to generate a final report, consolidate findings, or summarize security results" trigger clause.

3 / 3

Trigger Term Quality

Natural user phrasings are well covered: "generate a final report", "consolidate findings", and "summarize security results", plus "SAST vulnerability results" — terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

It carves a clear niche (post-detection consolidation into one report) and explicitly states it runs after the detection skills, making conflict with those skills 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
utkusen/sast-skills
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.