audit-flow

Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export. Use for security audits, compliance documentation, flow tracing, feature ideation, brainstorming, debugging, architecture reviews, or incident post-mortems. Triggers on audit, trace flow, document flow, security review, debug flow, brainstorm, architecture review, post-mortem, incident review.

Quality

88%

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

Quality

Content

77%

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

The body is highly actionable with strong, validated workflow sequencing, but loses points for duplicated safety warnings and a broken progressive-disclosure structure where three of four referenced files (including the required schema.sql) are absent from the bundle.

Suggestions

Ship the missing referenced files (schema.sql, COMMANDS.md, EXAMPLES.md) or remove/inline their content so the mandatory "Read schema.sql" entry point and the Files links resolve to real artifacts.

Consolidate the repeated "NEVER DESTROY DATA" / schema-first guidance (currently stated in the Mandatory Entry Point, FORBIDDEN ACTIONS table, and DB-First Discipline sections) into a single authoritative block to reduce redundancy.

Trim the duplicated DB-exists / never-recreate instructions so the core invariant is stated once and cross-referenced, improving token efficiency.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence (no "what is SQLite/Mermaid" filler) and is mostly efficient, but the schema-first and "NEVER DESTROY DATA" rules are duplicated across the Mandatory Entry Point, FORBIDDEN ACTIONS table, and DB-First Discipline sections, which could be tightened — matching the score-2 "mostly efficient but includes some unnecessary repetition" anchor rather than the fully-lean score 3.	2 / 3
Actionability	Concrete executable commands ("python .claude/skills/audit-flow/scripts/audit.py init\|list\|show\|export\|validate") and complete SQL INSERT examples with real values (e.g. the BRANCHES edges with conditions) are copy-paste ready, matching the score-3 fully-executable anchor.	3 / 3
Workflow Clarity	A clear numbered sequence (mandatory Step 1-3 entry point, interactive workflow steps) is backed by explicit validation checkpoints (DB-exists check before init, "Every 5 tuples → audit.py show", "audit.py validate before export"), forbidden-action guardrails, and a completion checklist — meeting the score-3 sequence-with-validation anchor and avoiding the destructive-ops cap since validation is present.	3 / 3
Progressive Disclosure	References are well-signaled and one level deep ("[COMMANDS.md](COMMANDS.md)", "[EXAMPLES.md](EXAMPLES.md)", "[schema.sql](schema.sql)"), but only scripts/audit.py actually exists in the bundle — schema.sql (the mandatory entry-point file), COMMANDS.md, and EXAMPLES.md are missing, leaving broken links and detail inlined that the absent files were meant to hold, fitting the score-2 "content that should be separate is inline" anchor rather than a clean score-3 split.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 is specific, third-person, and fully covers both capabilities and explicit use-cases/triggers with natural phrasing. It is a strong, low-conflict skill description with no meaningful weaknesses.

Dimension	Reasoning	Score
Specificity	"Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export" lists multiple specific concrete actions (layer-based tracing, SQLite persistence, Mermaid export), matching the score-3 anchor rather than the partial-action score-2 anchor.	3 / 3
Completeness	It explicitly answers both "what" (flow tracing across layers, SQLite persistence, Mermaid export) and "when" ("Use for security audits, compliance documentation..." plus an explicit "Triggers on..." clause), satisfying the score-3 what-AND-when anchor and avoiding the missing-trigger cap of 2.	3 / 3
Trigger Term Quality	"Triggers on audit, trace flow, document flow, security review, debug flow, brainstorm, architecture review, post-mortem, incident review" provides broad coverage of natural terms a user would actually say, exceeding the score-2 "some relevant keywords" bar.	3 / 3
Distinctiveness Conflict Risk	The layer-model flow-tracing niche plus SQLite/Mermaid persistence and distinct audit/post-mortem triggers carve a clear, specialized scope unlikely to fire for unrelated skills, matching the score-3 clear-niche anchor.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: zebbern/claude-code-guide
Path: skills/audit-flow/SKILL.md
Commit: af7d491

Reviewed: about 8 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.