final-report

Final engagement report generation — executive summary, technical report, findings aggregation, attack path narrative, detection gap matrix, remediation roadmap.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/decepticon/final-report/SKILL.md

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.

The body is highly actionable with a clearly sequenced workflow and explicit verification checkpoints, but it is a long monolith that explains security concepts Claude already knows and keeps large templates inline rather than factoring them into reference files.

Suggestions

Remove or heavily trim the Glossary section — terms like ATT&CK, CVSS, EDR, WAF, SIEM, C2, OSINT and Kill Chain are already known to Claude and cost tokens the conciseness rubric penalizes.

Factor the executive-summary and technical-report templates into separate files under references/ (e.g. references/executive-summary.md, references/technical-report.md) and link to them from SKILL.md so the body is an overview rather than a 400-line monolith.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, concrete templates and rules, but it pads tokens Claude does not need — most visibly the Glossary defining ATT&CK, CVSS, EDR, WAF, SIEM, C2, OSINT and Kill Chain, which the rubric explicitly penalizes as concepts Claude already knows.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: exact file paths, frontmatter field lists, a runnable bash mkdir command, severity→CVSS defaults, precise filename conventions (report/<severity><NN>-<slug>.md), and complete report templates — fully actionable for an instruction/template skill.	3 / 3
Workflow Clarity	The workflow is a clearly numbered 8-step sequence expanded into Step 1–4 sections, with an explicit pre-write Quality Checklist and conditional edge-case handling (missing CVSS, empty attack paths, unverified findings) serving as validation checkpoints for this batch generation task.	3 / 3
Progressive Disclosure	Sections are well organized, but the skill is a 500-line monolith with no bundle files (references/ absent); the two large report templates are inline walls of content that could be split into separate reference files, so it is not a clean overview pointing one level deep.	2 / 3
	Total	10 / 12 Passed

Description

67%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.

The description is specific and distinctive about a pentest final-report generation niche, but lacks an explicit 'Use when' trigger clause and leans on jargon over natural user phrasing, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit 'Use when...' trigger clause to the description (e.g., 'Use when the engagement is complete and all OPPLAN objectives are passed or blocked, or when the user asks to generate the final report') to lift completeness to 3.

Surface natural trigger terms users would actually say ('generate report', 'final report', 'engagement writeup', 'pentest report', 'red team report') instead of only internal jargon like 'findings aggregation' and 'detection gap matrix'.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'executive summary, technical report, findings aggregation, attack path narrative, detection gap matrix, remediation roadmap' — matching the score-3 anchor that rewards several specific concrete actions rather than vague language.	3 / 3
Completeness	It clearly answers 'what' the skill does but contains no explicit 'when'/'Use when' trigger clause in the description field; per the rubric a missing 'Use when' clause caps completeness at 2 (the when guidance lives in metadata.when_to_use, not the description).	2 / 3
Trigger Term Quality	Terms like 'executive summary' and 'technical report' are natural, but most of the list ('findings aggregation', 'attack path narrative', 'detection gap matrix') is domain jargon and the description omits common user variations such as 'pentest report' or 'generate report', so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	The pentest/red-team final-report niche with distinctive components (attack path narrative, detection gap matrix, remediation roadmap) is a clear niche unlikely to fire for unrelated skills, matching the score-3 anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

Warnings & errors only

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

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (518 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/decepticon/final-report/SKILL.md
Commit: e34afba

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

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.