enrichment-module-builder

Build a new Nemesis file enrichment module end-to-end with explicit user approval gates for output mode, library choice, sample files, and integration testing.

1.41x

Quality

67%

Does it follow best practices?

Impact

99%

1.41x

Average score across 3 eval scenarios

Securityby

Risky

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/enrichment-module-builder/SKILL.md

Quality

Content

77%

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

This is a well-structured, highly actionable skill with excellent workflow clarity and explicit validation gates. Its main weakness is length — the document is quite long with verbose recommendation templates and inline code that could be split into referenced files. The actionability is outstanding with executable commands, correct database parameters, schema references, and troubleshooting guidance.

Suggestions

Extract the code templates (analyzer.py template, test template, pyproject.toml template) into separate referenced files to reduce SKILL.md length and improve progressive disclosure.

Condense the 'Present to User' recommendation format blocks — Claude can generate appropriate formatting without being given exact markdown templates for each gate.

Dimension	Reasoning	Score
Conciseness	The skill is quite long (~400+ lines) with some redundancy. The template blocks for presenting recommendations to users are verbose and could be condensed. However, most content is genuinely instructional rather than explaining concepts Claude already knows. The repeated 'STOP' gate reminders and formatted recommendation templates add bulk that could be tightened.	2 / 3
Actionability	The skill provides fully executable code templates (analyzer.py, test files, YARA rules), specific bash commands for testing and database queries, exact container names and connection parameters, and concrete file paths. The code is copy-paste ready with clear placeholder patterns for customization.	3 / 3
Workflow Clarity	The 8-step workflow is clearly sequenced with explicit user approval gates at steps 2, 3, 4, and 8. Each gate has a clear STOP instruction. Step 8 includes detailed validation checkpoints (health check, module loading, file submission, DB verification) with a pass/fail checklist. Error recovery guidance is provided in the troubleshooting section. The completion checklist ensures nothing is skipped.	3 / 3
Progressive Disclosure	The skill references external files (DEVELOPMENT_GUIDE.md, test harness directory, reference module paths) which is good, but the SKILL.md itself is monolithic at ~400+ lines. The detailed code templates, recommendation format blocks, and troubleshooting section could be split into separate referenced files. The reference module table is a nice touch for navigation, but the overall document would benefit from more aggressive splitting.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 identifies a clear, niche domain (Nemesis file enrichment modules) and outlines a multi-step process with approval gates, making it distinctive. However, it lacks an explicit 'Use when...' clause, and the actions described are more about the workflow process than concrete technical capabilities. Adding trigger guidance and more specific action verbs would improve its effectiveness for skill selection.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create a new Nemesis enrichment module, add file type support to Nemesis, or build a file processing pipeline for Nemesis.'

Include more natural trigger terms a user might say, such as 'new file type', 'add enrichment', 'Nemesis plugin', 'file parser', or 'file processing module'.

List more concrete actions the skill performs, e.g., 'scaffolds module boilerplate, selects parsing libraries, generates sample test files, and runs integration tests against the Nemesis platform'.

Dimension	Reasoning	Score
Specificity	The description names a specific domain ('Nemesis file enrichment module') and mentions several concrete steps ('output mode, library choice, sample files, integration testing'), but these are more like process stages than specific actions the skill performs. It doesn't list concrete technical actions like 'parse file headers', 'extract metadata', etc.	2 / 3
Completeness	The 'what' is partially addressed (build a Nemesis file enrichment module with approval gates), but there is no explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied by the nature of the task described, which caps this at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	It includes some relevant terms like 'Nemesis', 'file enrichment module', and 'integration testing', but these are fairly niche. A user might say 'build a Nemesis module' or 'create an enrichment module', but common variations and natural phrasings are not well covered. Terms like 'approval gates' are more process-oriented than search terms a user would naturally use.	2 / 3
Distinctiveness Conflict Risk	The description is highly specific to 'Nemesis file enrichment module' with a distinctive workflow involving explicit user approval gates. This is unlikely to conflict with other skills due to the very specific domain and project name.	3 / 3
	Total	9 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (654 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: SpecterOps/Nemesis
Commit: d072db7

Reviewed: 6 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.