CtrlK
BlogDocsLog inGet started
Tessl Logo

triage-validation

Finding validation before writing any report — 7-Question Gate (all 7 questions), 4 pre-submission gates, always-rejected list, conditionally valid with chain table, CVSS 3.1 quick reference, severity decision guide, report title formula, 60-second pre-submit checklist. Use BEFORE writing any report. One wrong answer = kill the finding and move on. Saves N/A ratio.

69

Quality

83%

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

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.

A dense, highly actionable triage skill with excellent sequenced validation checkpoints; main weaknesses are redundancy between two overlapping lists and a lack of progressive disclosure for a body this size.

Suggestions

Resolve the 7-vs-8 mismatch: either rename to 'THE 8-QUESTION GATE' or fold the Q8 identity check into the existing seven so the section title matches its contents.

Merge or cross-reference the NEVER SUBMIT list and COMMON N/A CLASSES table, which cover the same findings (XSS, SSRF, IDOR, CORS, rate limit, open redirect) twice, to recover conciseness.

Move the CVSS 3.1 quick reference and the large lookup tables into a references/ file (e.g., CVSS.md) referenced from SKILL.md to improve progressive disclosure for a skill of this length.

DimensionReasoningScore

Conciseness

The body is lean and never re-explains concepts Claude already knows, but the NEVER SUBMIT list and the COMMON N/A CLASSES table overlap heavily (XSS, SSRF, IDOR, CORS, rate limit, open redirect each appear twice), which could be consolidated.

2 / 3

Actionability

Highly actionable for an instruction-only skill: a copy-paste-ready HTTP request template (Q1), concrete kill signals in every row, explicit decision rules, and checklists throughout.

3 / 3

Workflow Clarity

The 7-Question Gate and the 4 pre-submission gates are clearly sequenced with explicit kill/STOP and ALL-must-PASS checkpoints plus feedback loops (kill -> move on, re-validate); the only blemish is that the section is titled 'THE 7-QUESTION GATE' yet lists Q1-Q8.

3 / 3

Progressive Disclosure

Sections are well-organized with clear headers, but the skill is a ~300-line monolithic SKILL.md with no references/scripts/assets bundle; the CVSS 3.1 quick reference and the large lookup tables are inline content that could be split into reference files.

2 / 3

Total

10

/

12

Passed

Description

90%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.

A strong, specific, distinctive description with explicit trigger guidance; the only deduction is for second-person imperative voice in the trigger clause.

Suggestions

Rewrite 'Use BEFORE writing any report. One wrong answer = kill the finding and move on.' in third person (e.g., 'Apply before writing any report; one wrong answer kills the finding.') to satisfy the voice guideline and recover the specificity point.

Consider adding the user-facing trigger phrasing users actually say, such as 'Use when deciding whether to report or kill a finding', to broaden natural trigger coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete components ('7-Question Gate', '4 pre-submission gates', 'chain table', 'CVSS 3.1 quick reference', 'report title formula'), which would be a 3, but the imperative 'Use BEFORE writing any report' is second-person voice, penalized by one level per the rubric guideline.

2 / 3

Completeness

Clearly answers both what ('Finding validation before writing any report') and when ('Use BEFORE writing any report'), with an explicit trigger clause present.

3 / 3

Trigger Term Quality

Good coverage of natural domain terms a bug-bounty hunter would say: 'Finding validation', 'writing any report', 'kill the finding', 'N/A ratio', alongside explicit trigger guidance.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (pre-report finding validation/triage) with distinctive triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

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
shuvonsec/claude-bug-bounty
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.