audit-context-building

Enables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/audit-context-building/SKILL.md

Quality

Content

45%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.

The skill is well-sequenced with validation checkpoints, but it is verbose with repeated framing and, critically, points to bundle files that are absent. The broken references and padding pull it below its potential.

Suggestions

Provide the referenced bundle files (FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md) and the function-analyzer agent, or inline their essential content and remove the dangling references.

Deduplicate repeated framing: merge the two 'When active, Claude will' lists in sections 1 and 2 and consolidate the non-goals that appear in both 'When to Use' and 'Non-Goals'.

Add at least one concrete worked example (a short analyzed function with the required invariants/assumptions) inline so the directive guidance has an executable anchor.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: 'When active, Claude will' is restated in near-identical form across sections, the rationalizations table and repeated non-goals re-explain concepts, and 5 Whys/5 Hows are reintroduced multiple times.	2 / 5
Actionability	Structured checklists and explicit quality thresholds (min 3 invariants, min 5 assumptions) give concrete guidance, but it stays at the directive level with no executable examples, so it is actionable in shape but incomplete in specifics.	3 / 5
Workflow Clarity	Phases 1->2->3 are clearly sequenced with a Completeness Checklist acting as a validation gate ('complete when all checklist items satisfied'), though an explicit fix-and-retry feedback loop is only weakly implied.	4 / 5
Progressive Disclosure	The body references FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md, and a function-analyzer agent, but none of these bundle files exist, leaving one-level-deep references that are broken rather than navigable.	2 / 5
	Total	11 / 20 Passed

Description

58%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 conveys a clear, mostly distinct purpose with concrete actions, but lacks an explicit 'Use when' trigger clause and has only moderate natural keyword coverage. It sits at a competent-but-not-exemplary level.

Suggestions

Add an explicit 'Use when ...' trigger clause naming natural user phrases (e.g., 'Use when preparing for a code audit, security review, or architecture review before bug finding').

Include more natural trigger synonyms users would say, such as 'code review', 'audit', 'code comprehension', or 'threat modeling'.

Tighten the action list to read as concrete deliverables (e.g., 'produces per-function purpose, inputs/outputs, invariants, and cross-function dependency maps').

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('line-by-line code analysis', 'build deep architectural context'), but stops short of the comprehensive, crisp action list of a 5.	4 / 5
Completeness	The 'what' is clear but there is no explicit 'Use when...' trigger clause, only a weakly implied 'before vulnerability or bug finding'; per guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords exist ('vulnerability or bug finding', 'architectural context') but common natural variants like 'code review', 'audit', or 'code comprehension' are missing.	3 / 5
Distinctiveness Conflict Risk	The 'ultra-granular line-by-line ... before vulnerability finding' framing carves a fairly distinct niche with minor overlap risk against general code-review skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/audit-context-building/SKILL.md
Commit: b1aebac

Reviewed: ~18 hours 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.