Skf audit skill

Skill armelhbobdad/oh-my-skills/.claude/skills/skf-audit-skill

Drift detection between skill and current source code. Use when the user requests to "audit a skill" or "audit skill" for drift.From its SKILL.md

Install

npx -y skills add armelhbobdad/oh-my-skills --skill skf-audit-skill

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

7 stars7 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.2 KB, 730 tokens by cl100k_base, as published. Nobody here has run it

Audit Skill

Overview

Detects drift between an existing skill and its current source code, producing a severity-graded drift report with AST-backed findings and actionable remediation suggestions. Every finding must trace to actual code with file:line citations — structural truth over semantic guessing. Analysis depth adapts based on detected forge tier (Quick/Forge/Forge+/Deep) with graceful degradation. Stack skills are supported: code-mode stacks are audited per-library against their sources; compose-mode stacks check constituent freshness via metadata hash comparison.

Role

You are a skill auditor operating in Ferris Audit mode. This is a deterministic analysis workflow — you enforce the zero-hallucination principle. You bring AST analysis expertise and drift detection methodology, while the source code provides the ground truth.

Workflow Rules

These rules apply to every step in this workflow:

Never fabricate findings — all data must trace to source code with file:line citations
Read each step file completely before taking any action
Follow the mandatory sequence in each step exactly — do not skip, reorder, or optimize
Only load one step file at a time — never preload future steps
Update stepsCompleted in output file frontmatter before loading next step
If any instruction references a subprocess or tool you lack, achieve the outcome in your main context thread
Always communicate in {communication_language}
If {headless_mode} is true, auto-proceed through confirmation gates with their default action and log each auto-decision

Stages

#	Step	File	Auto-proceed
1	Initialize & Baseline	steps-c/step-01-init.md	No (confirm)
2	Re-Index Source	steps-c/step-02-re-index.md	Yes
3	Structural Diff	steps-c/step-03-structural-diff.md	Yes
4	Semantic Diff	steps-c/step-04-semantic-diff.md	Yes (skip at non-Deep)
5	Severity Classification	steps-c/step-05-severity-classify.md	Yes
6	Report	steps-c/step-06-report.md	Yes
7	Workflow Health Check	steps-c/step-07-health-check.md	Yes

Invocation Contract

Aspect	Detail
Inputs	skill_name [required]
Gates	step-01: Confirm Gate [C]
Outputs	drift-report-{timestamp}.md with drift_score and nextWorkflow
Headless	All gates auto-resolve with default action when `{headless_mode}` is true

On Activation

Load config from {project-root}/_bmad/skf/config.yaml and resolve:
- project_name, output_folder, user_name, communication_language, document_output_language
- skills_output_folder, forge_data_folder, sidecar_path
- Generate and store timestamp as YYYYMMDD-HHmmss format. This value is fixed for the entire workflow run.
Resolve {headless_mode}: true if --headless or -H was passed as an argument, or if headless_mode: true in preferences.yaml. Default: false.
Load, read the full file, and then execute ./steps-c/step-01-init.md to begin the workflow.

What ships with it: 9 files

55.6 KB alongside SKILL.md

assets/

drift-report-template.md916 B

references/

severity-rules.md2.4 KB

steps-c/

Gives 0 of the 12 instructions most audit compliance skills give in 730 tokens

Counted across 937 of the 1,487 authors here whose files we hold, read 2026-08-07

Fetch latest guidelines before each reviewin 43 of 937, across 3 files
Group findings by severityin 43 of 937
Check files against all fetched rulesin 42 of 937, across 2 files
Output findings in terse file:line formatin 41 of 937, across 3 files
Ask user which files to review if none specifiedin 41 of 937, across 3 files
Read specified files or prompt user for filesin 39 of 937, across 1 file
Generate the audit reportin 33 of 937, across 30 files
Assign a severity to every findingin 25 of 937
Run automated accessibility scansin 23 of 937, across 13 files
Output a markdown audit reportin 22 of 937
Map findings to WCAG criteriain 20 of 937, across 10 files
Confirm audit scopein 19 of 937, across 9 files

Said here and by no other author read

trace all findings to code with file:line citations
read each step file completely before action
follow the mandatory sequence in each step exactly
load only one step file at a time
update stepsCompleted before loading the next step
achieve missing tool outcomes in main context thread

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.