audit-context-building

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

Quality

55%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/audit-context-building/SKILL.md

The canonical home for this skill is audit-context-building in sickn33/agentic-awesome-skills

Quality

Content

56%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 body is well-sequenced into clear phases with a completeness gate, but it is padded with redundant sections and defers its most concrete artifacts (output template, worked example, checklist) to bundle files that are absent from the skill. The result is a structured but incomplete and somewhat verbose skill.

Suggestions

Create the referenced bundle files (FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md) under references/, or inline their content — currently they are dead links.

Inline a single complete worked micro-analysis example so the output format is immediately usable without the missing example file.

Merge redundant sections (Purpose/How This Skill Behaves, Do not use for/Non-Goals, Stability Rules/Rationalizations) to cut token cost while preserving the actionable structure.

Dimension	Reasoning	Score
Conciseness	Mostly structured and efficient, but several sections restate the same philosophy ('Purpose' vs 'How This Skill Behaves', 'Do not use for' vs 'Non-Goals', 'Stability & Consistency Rules' vs 'Rationalizations') and explain concepts Claude already knows (First Principles, 5 Whys, invariants); could be tightened.	3 / 5
Actionability	Provides concrete checklists and quantitative thresholds (min 3 invariants, min 5 assumptions), but the actual output template and worked example are deferred to OUTPUT_REQUIREMENTS.md and FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, which are not present in the bundle, leaving the guidance incomplete.	3 / 5
Workflow Clarity	Clear three-phase sequence (Orientation → Function Analysis → Global Understanding) with a completeness checklist acting as a validation gate and explicit contradiction-handling rules; not a 5 because the checklist detail lives in a missing referenced file.	4 / 5
Progressive Disclosure	Section structure is clear and references are explicitly signaled and one-level-deep, but the referenced files (FUNCTION_MICRO_ANALYSIS_EXAMPLE.md, OUTPUT_REQUIREMENTS.md, COMPLETENESS_CHECKLIST.md) do not exist in references/, so the disclosure is effectively broken dead links rather than a working split.	3 / 5
	Total	13 / 20 Passed

Description

53%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 clearly states what the skill does and carves out a fairly distinct pre-audit niche, but it lacks an explicit 'Use when...' trigger and leans on abstract phrasing rather than enumerated concrete actions. Trigger-term coverage omits common synonyms users would actually say.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases (e.g., 'Use when preparing for a security audit, architecture review, or threat model, or when you need bottom-up comprehension before finding bugs').

List several specific concrete actions instead of one (e.g., 'trace call chains, map state invariants, document assumptions, and reconstruct workflows line-by-line').

Include natural trigger synonyms users would say — 'audit', 'code review', 'trace', 'threat model' — to improve discoverability.

Dimension	Reasoning	Score
Specificity	Names the domain ('line-by-line code analysis', 'build deep architectural context') and one concrete action, but does not enumerate several specific actions; 'ultra-granular' and 'deep architectural context' are abstract rather than concrete verbs.	3 / 5
Completeness	The 'what' is clear (line-by-line analysis to build context), but the 'when' is only weakly implied via 'before vulnerability or bug finding' rather than an explicit 'Use when...' trigger clause, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	Contains relevant keywords ('code analysis', 'vulnerability', 'bug finding') but misses common synonyms a user would naturally say such as 'audit', 'review', 'trace', or 'threat model'.	3 / 5
Distinctiveness Conflict Risk	The pre-audit context-building niche ('before vulnerability or bug finding') is mostly distinct from the actual audit/finding skills, with only minor overlap risk against general code-review skills; not a 5 because 'code analysis' is still broad.	4 / 5
	Total	13 / 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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/audit-context-building/SKILL.md
Commit: debb2ec

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.