Miller Patterns Audit

VerifiedSafe

Use pattern extractors to audit code shapes like routes, attributes, directives, and SQL structures across multiple languages.

Sby Skills Guide Bot
DevelopmentIntermediate
7/23/2026
Claude Code
#static-analysis#code-structure#mcp#pattern-matching#codebase-audit

Recommended for

Automated summary

Queries the Miller extractor pattern catalog to retrieve recognized structural facts (routes, htmx attributes, Alpine directives, SQL DDL/DML, document structure) instead of scanning raw code.

Strengths

  • Clear four-step workflow: list observed IDs, search, summarize, then inspect source at the reported lines
  • Composable filters by path, language, where clause, and workspace_id enable targeted or cross-workspace audits
  • List output surfaces follow-up calls (Next: / next_actions) derived from the IDs actually observed
  • The summary operation lets you size a pattern before committing to a broad audit

Limitations

  • Not a general-purpose AST query engine: only shapes already supported by the extractor can be found
  • Entirely bounded by the catalog (194 pattern IDs across 36 languages); a missing shape requires adding extractor support first
  • Empty results may be caused by filters, so path, language, or where must be loosened before concluding a pattern is absent
When to use it

Use it when a question concerns structural facts the extractor catalog knows about and a raw text grep would be too imprecise.

When not to use it

Avoid it for arbitrary AST matching, free-form source text search, or documentation prose, which belong to search(mode="source") or search(mode="content") instead.

Security analysis

Safe
Quality score92/100

The skill only uses declared read-oriented MCP tools for pattern listing, searching, inspection, and workspace comparison. It does not instruct destructive actions, command execution, secret exfiltration, obfuscation, or safety bypasses.

No concerns found

How this analysis is made

Examples

Inventaire des routes minimal API
List the ASP.NET minimal API route patterns in this workspace, then search for verb=GET only and tell me which files and lines define them.
Audit htmx dans les vues
Find all htmx attributes used under Views/** — start with patterns(operation="list") and then search htmx.attribute.v1 filtered on name=hx-get.
Résumé de la structure Markdown
Summarize markdown.heading.v1 under docs/** so I can see the heading structure before reading any file.

name: miller-patterns-audit description: Use when an agent needs extractor-recognized code-shape facts such as routes, htmx attributes, Alpine directives, SQL DDL/DML, or data-document structure. user-invocable: true arguments: "<pattern family, path, language, or metadata filter>" allowed-tools: mcp__miller__patterns, mcp__miller__search, mcp__miller__inspect, mcp__miller__workspace

Miller Patterns Audit

The current extractor catalog contains 194 pattern IDs across 36 languages. Use patterns when the question is about known structural facts emitted by julie-extractors, not arbitrary AST matching. Start by listing observed pattern IDs in the selected workspace, then search the relevant ID with path, language, and metadata filters.

Workflow

  1. Discover available IDs:
patterns(operation="list")
patterns(operation="list", language="razor")

List output includes Next: / JSON next_actions derived from observed IDs. Prefer those follow-up calls before inventing a raw text grep.

  1. Search a concrete pattern:
patterns(operation="search", pattern_id="aspnet.minimal_api.route.v1", where="verb=GET")
patterns(operation="search", pattern_id="htmx.attribute.v1", where="name=hx-get", path="Views/**")
patterns(operation="search", pattern_id="alpine.directive.v1", where="directive=x-data", path="Views/**")
patterns(operation="search", pattern_id="sql.merge_statement.v1")
  1. Summarize before broad audits:
patterns(operation="summary", pattern_id="markdown.heading.v1", path="docs/**")
patterns(operation="summary", pattern_id="json.property.v1", language="json")
  1. Inspect source only after the pattern rows identify a file and line:
inspect(target="<path from pattern row>")

Good Uses

  • List ASP.NET minimal API routes without scanning source text.
  • Find htmx or Alpine usage in Razor/HTML views.
  • Audit SQL DDL/DML, including MERGE, JSON/YAML/TOML keys, or Markdown structure.
  • Compare code-shape facts across registered workspaces with workspace_id.

Limits

  • patterns is not a raw AST query engine.
  • Pattern IDs come from the extractor catalog; if a shape is missing, add extractor support first.
  • No-match output can include near matches and active-filter guidance. If the pattern exists but filters remove every row, loosen path, language, or where.
  • Use search(mode="source") for arbitrary source text and search(mode="content") for docs/config prose.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/miller-patterns-audit-mrx3xxp7/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/miller-patterns-audit-mrx3xxp7' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/miller-patterns-audit-mrx3xxp7/download' --output '.skill-downloads/miller-patterns-audit-mrx3xxp7/SKILL.md.part' && mv '.skill-downloads/miller-patterns-audit-mrx3xxp7/SKILL.md.part' '.skill-downloads/miller-patterns-audit-mrx3xxp7/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): mcp__miller__patterns, mcp__miller__search, mcp__miller__inspect, mcp__miller__workspace

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/miller-patterns-audit-mrx3xxp7/SKILL.md' && test -s '.skill-downloads/miller-patterns-audit-mrx3xxp7/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/miller-patterns-audit' && cp -R '.skill-downloads/miller-patterns-audit-mrx3xxp7' '.claude/skills/miller-patterns-audit'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/miller-patterns-audit-mrx3xxp7'

openskills read 'miller-patterns-audit-mrx3xxp7'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/miller-patterns-audit-mrx3xxp7/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills