recon-reporting

Recon output formatting — report structure, CVSS v4.0 scoring (primary), MITRE ATT&CK mapping, finding prioritization, Markdown output, detection gap tracking, handoff checklists.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/recon/reporting/SKILL.md

Quality

Content

71%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 thorough, highly actionable recon-reporting knowledge base with concrete templates, CVSS vectors, and MITRE mappings, but it is a monolithic 496-line document with internal redundancy and no progressive disclosure via separate reference files. Splitting the heavy reference sections and de-duplicating the directory layout would materially improve it.

Suggestions

Move the CVSS 4.0 metric reference (§4) and MITRE ATT&CK mapping table (§7) into separate reference files (e.g. references/cvss-4.0.md, references/mitre-mapping.md) and link to them one level deep, keeping SKILL.md as an overview.

De-duplicate the directory layout that appears in both §5 (Storage Layout) and §10 (File Management) — keep a single canonical tree.

Trim padded prose such as the opening 'Effective reconnaissance is only as valuable as the intelligence it communicates' and the 'core red team deliverable that distinguishes operational red teaming' sentence, which explain concepts Claude already knows.

Dimension	Reasoning	Score
Conciseness	Mostly dense, valuable reference (CVSS 4.0 metric groups, specific vectors, MITRE technique IDs, naming conventions), but the directory layout is duplicated in §5 and §10, the evidence and detection-gap tables appear both in the §2 example and re-specified in §5/§6, and padded sentences like 'Effective reconnaissance is only as valuable as the intelligence it communicates' could be trimmed; not a 4 because the redundancy is non-trivial.	3 / 5
Actionability	Provides copy-paste-ready finding templates with exact YAML frontmatter fields, concrete file-naming rules ('findings/FIND-{NNN}.md', 'FIND-{NNN}_{tool}.txt'), specific CVSS 4.0 vectors per finding type, and exact tool output flags (-oN, -o); the guidance is fully executable and covers the common cases.	5 / 5
Workflow Clarity	Sections are numbered 1–12 giving an implicit sequence, the §12 handoff checklist is an explicit verification gate, and §11 defines a report→opplan feedback loop; not a 5 because there is no single unified end-to-end report-generation workflow tying the sections together with explicit checkpoints.	4 / 5
Progressive Disclosure	Well-organized into clear numbered sections, but the 496-line skill is monolithic with no bundle files — the CVSS scoring reference, MITRE mapping, and finding template are large reference blocks that could live in separate files loaded on demand; not a 4 because content that should be split is fully inline with no one-level-deep references.	3 / 5
	Total	15 / 20 Passed

Description

66%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 enumerates a comprehensive, domain-specific set of capabilities but never tells Claude when to invoke the skill, and it relies on noun phrases instead of action verbs. Adding a 'Use when...' trigger clause would raise completeness and distinctiveness.

Suggestions

Append an explicit trigger clause, e.g. 'Use when generating or writing a recon/pentest report, scoring findings with CVSS, mapping findings to MITRE ATT&CK, prioritizing findings, or preparing red-team handoff.'

Reframe the capability list as third-person action verbs ('Structures recon reports, scores findings with CVSS v4.0, maps findings to MITRE ATT&CK...') to match the top specificity anchor.

Add common synonyms users might say ('pentest report', 'vulnerability report', 'red team report', 'engagement report') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'report structure, CVSS v4.0 scoring (primary), MITRE ATT&CK mapping, finding prioritization, Markdown output, detection gap tracking, handoff checklists' — seven concrete capability areas, comprehensive in coverage but expressed as noun phrases rather than the action verbs the top anchor expects ('Extract text...', 'fill forms').	4 / 5
Completeness	Gives a clear 'what' (the enumerated capabilities) but has no 'Use when...' clause or equivalent explicit trigger guidance, which the rubric caps at 3; not a 4 because 'when' is entirely absent rather than weakly implied.	3 / 5
Trigger Term Quality	Contains natural domain terms a red-team/recon user would say ('recon', 'report', 'CVSS', 'MITRE ATT&CK', 'findings', 'handoff') with good coverage; missing common synonyms like 'pentest report', 'vulnerability report', or 'red team report', so not a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a distinct niche (recon/red-team reporting with CVSS 4.0 + MITRE ATT&CK + detection-gap tracking) with minor overlap risk against other security-reporting skills; not a 5 because noun-based phrasing weakens the distinctness of its triggers.	4 / 5
	Total	15 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: PurpleAILAB/Decepticon
Path: packages/decepticon/decepticon/skills/standard/recon/reporting/SKILL.md
Commit: 31e1c8e

Reviewed: 9 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.