audit-context-building

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

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

50%

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

The skill is a well-structured, phased analysis framework with concrete checklists and thresholds, but it is verbose with redundant sections and critically references three bundle files that are not present, leaving key navigation and the worked example broken.

Suggestions

Create the referenced bundle files (FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md) or inline their content and drop the dead 'See X.md' links.

Merge the redundant 'When active, Claude will' lists in Sections 1 and 2 and remove the Non-Goals duplication of the 'Do not use for' list to cut tokens.

Add at least one inline worked example (e.g., a short function micro-analysis) so the required output format is concrete rather than only described.

Dimension	Reasoning	Score
Conciseness	The body is mostly process guidance rather than basic-concept explanation, but it is padded with repetition (Section 1 and Section 2 list near-identical 'When active, Claude will' bullets; Non-Goals repeats the 'Do not use for' list) and could be tightened considerably.	2 / 3
Actionability	Concrete checklists, a structured per-function format, and numeric thresholds (3 invariants, 5 assumptions) give actionable guidance, but the one concrete walkthrough is deferred to FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, which does not exist, leaving the example missing.	2 / 3
Workflow Clarity	Phases 1-3 are clearly sequenced and a completeness checklist provides a soft gate, but validation is self-reported rather than a concrete feedback loop, and the referenced COMPLETENESS_CHECKLIST.md file is absent.	2 / 3
Progressive Disclosure	Sections are well-organized and references are clearly signaled, but three referenced files (FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md) do not exist in any bundle directory, producing dead references alongside long inline content.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 communicates a clear niche (pre-audit context building) but is weighed down by buzzwords, lacks an explicit 'Use when' trigger, and uses jargon-heavy phrasing rather than natural user terms. It is functional but not exemplary.

Suggestions

Replace buzzwords ('ultra-granular', 'deep architectural context') with plain concrete actions, e.g. 'Performs line-by-line code analysis to map functions, state, and data flow before security audits.'

Add an explicit trigger clause: 'Use when preparing for security auditing, threat modeling, or architecture review before vulnerability discovery.'

Include natural user-facing terms ('audit', 'review my code', 'threat model') so the skill triggers on how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	Names concrete actions ('line-by-line code analysis', 'build deep architectural context') but pads them with buzzwords ('ultra-granular', 'deep') and is not comprehensive, matching the 'names domain and some actions' anchor rather than the multiple-specific-actions level.	2 / 3
Completeness	It states what the skill does and gives only an implied when ('before vulnerability or bug finding') with no explicit 'Use when...' trigger clause, which caps completeness at 2 per the guideline.	2 / 3
Trigger Term Quality	Relevant terms ('code analysis', 'vulnerability', 'bug finding') appear but phrasing is jargon-heavy ('ultra-granular', 'architectural context') and misses natural variations a user would say ('audit my code', 'review for bugs').	2 / 3
Distinctiveness Conflict Risk	The pre-audit context-building niche is somewhat specific, but 'code analysis' is generic and could overlap with other code-review or auditing skills.	2 / 3
	Total	8 / 12 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/antigravity-awesome-skills
Path: skills/audit-context-building/SKILL.md
Commit: 1a0329b

Reviewed: 1 day 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.