CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

bounty-report-formatter

Bug bounty report presentation, reproduction evidence and destination field conventions for HackerOne, Bugcrowd, Immunefi and GitHub Security Advisories.

Quality

82%

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

88%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.

A strong, dense skill body: fully actionable templates and platform mappings, an explicit quality-checklist validation step, and lean prose that assumes Claude's competence. The only refinements are minor redundancy between the template and the checklist, and a possible future split of platform-specific notes into a references file as the skill grows.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows — every section is rules, templates, or examples. Minor tightening is possible: the Quality Checklist restates template constraints already stated inline (e.g., 'Summary is ≤3 sentences' vs. the template's 'Three sentences maximum'), and six example titles where three would teach the pattern. Matches anchor 4 ('minor instances... that could be trimmed'), not anchor 5's 'every token earns its place'.

4 / 5

Actionability

Fully concrete: an exact title format with six real accepted-report examples, a copy-paste-ready report template including CVSS metric/justification table, PoC with expected-vs-baseline responses, a specific remediation diff, and concrete platform mappings (Bugcrowd VRT P1–P4 ranges, the first.org CVSS calculator URL pattern). Matches anchor 5 — specific examples cover the common cases with executable, fill-in-ready material.

5 / 5

Workflow Clarity

A single-purpose formatter skill whose single action is unambiguous: select destination, apply the title convention and template, then verify against the explicit Quality Checklist. The checklist is a genuine validation checkpoint covering every report element, and the boundary note ('Program scope and duplicate disposition belong to the workflow') clarifies scope. Matches anchor 5; no destructive or batch operations apply.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and at ~140 lines the single self-contained file with clear sections (Title Convention, Report Template, Quality Checklist, Platform-Specific Notes) is appropriately organized. Matches anchor 4: good structure with minor organization gaps — platform-specific notes are natural candidates for a references file if the skill grows. Not anchor 5, which assumes well-signaled one-level-deep references or the under-50-line simple-skill case.

4 / 5

Total

18

/

20

Passed

Description

70%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.

A distinct, well-targeted description that names concrete capability areas and all four destination platforms, with strong natural trigger terms. Its main weakness is the absence of an explicit 'Use when...' clause in the description text, which caps completeness and leaves trigger guidance buried in metadata rather than surfaced where it guides skill selection.

Suggestions

Append an explicit trigger clause to the description, e.g.: 'Use when preparing, writing, or submitting a bug bounty report or security writeup to HackerOne, Bugcrowd, Immunefi, or a GitHub Security Advisory.'

Lead with concrete third-person verbs instead of noun phrases, e.g.: 'Formats validated findings into platform-ready bug bounty reports — title conventions, reproduction evidence, CVSS severity justification, and destination-specific field mappings.'

Surface natural trigger synonyms from when_to_use into the description itself: 'submit', 'writeup', 'h1', 'ghsa', 'disclosure', 'triage'.

DimensionReasoningScore

Specificity

The description names the domain (bug bounty reports) and several specific capability areas — 'report presentation, reproduction evidence and destination field conventions' — plus four concrete destination platforms (HackerOne, Bugcrowd, Immunefi, GitHub Security Advisories). It lists several specific capabilities with minor gaps, matching anchor 4; it is not anchor 5 because the capabilities are noun phrases rather than a comprehensive list of concrete actions.

4 / 5

Completeness

The 'what' is clear (presentation, reproduction evidence, and field conventions for four named platforms) but the description text contains no 'Use when...' clause or equivalent explicit trigger guidance, capping completeness at 3 per the judging guidelines. It is not anchor 4 because 'when' is entirely absent from the description rather than merely under-specified.

3 / 5

Trigger Term Quality

Strong natural keywords users would actually say — 'bug bounty report', 'HackerOne', 'Bugcrowd', 'Immunefi', 'GitHub Security Advisories'. A few natural terms are missing from the description itself ('submit', 'writeup', 'h1', 'disclosure', 'triage' appear only in metadata.when_to_use, not in the description field), matching anchor 4 rather than anchor 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Clear niche (platform-specific bug bounty report formatting) with distinct named-platform triggers; minimal conflict risk with other skills. Matches anchor 5 — the platform names make it very unlikely to trigger for the wrong skill.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

Validation — 14 / 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

Total

14

/

16

Passed

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/plugins/verifier/bounty-report/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.