agentleFS
Sign inStart free
GstMirabalGstMirabal/Token-Optimized-Agent-Pipeline/skills/mass-standardizer/SKILL.md

mass-standardizer

Skill1 starsChanged 10 days agoMITView on GitHub

Batch-normalizes the flat skills/ library — detects skills missing the Three-File Skill Standard (README.md, SKILL.md, /scripts/) and injects the missing artifacts from templates, keeping manifest_skills.json in sync.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Every skill: SKILL.md with name/description frontmatter.

    line 21
  2. Very specific:

    Meta-Harvesting: Read the corresponding entry in manifest_skills.json to extract the skill's official name, description, category, and tags.

    line 25
  3. Very specific:

    Strict Parity: Verify that every standardized skill has its path, category, and tags correctly reflected in manifest_skills.json.

    line 34
  4. Distinctive:

    Rule 1 Compliance: All generated documents MUST be in Technical English and follow the kebab-case naming convention.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sub-Role Skill: Mass Standardizer

Base Profile

Name: mass-standardizer Category: Infrastructure / Automation Description: Automotive engine for the batch normalization of the pipeline's skill library following the skill-creator standard.

Technical Logic

This skill implements a Template-Driven Scaffolding pattern. It scans the skill library for structural gaps (missing README.md, SKILL.md, or /scripts/ folders) and surgically injects the required artifacts using standardized templates and manifest metadata.

Procedures

1. Gap Analysis (Skill Library Audit)

  • Scanning: Iterate through the flat skills/ directory (and profiles/*/skills/ when auditing profiles).
  • Detection: Apply the Three-File Skill Standard (agents.md §3 three_file_standard):
    • Every skill: SKILL.md with name/description frontmatter.
    • Executable skills (those shipping /scripts/): additionally README.md and scripts/__init__.py.

2. Context Extraction

  • Meta-Harvesting: Read the corresponding entry in manifest_skills.json to extract the skill's official name, description, category, and tags.
  • Logic Mapping: For SKILL.md, extract any existing procedural comments in the code to seed the "Technical Logic" section.

3. Template Injection

  • README Synthesis: Apply the official readme-standardizer/assets/template.md.
  • SKILL Synthesis: Generate the YAML frontmatter and standard sections (Base Profile, Cycles, Governance).
  • Structure Enforcement: For executable skills only — those already shipping /scripts/, per the split declared in §1 above — ensure a valid __init__.py exists for Python package compliance. A knowledge skill's /scripts/ directory is never instantiated: agents.md §3 prohibits padding it with empty scaffolding, so shipping one is what makes a skill executable rather than something this protocol can confer.

4. Manifest Synchronization

  • Strict Parity: Verify that every standardized skill has its path, category, and tags correctly reflected in manifest_skills.json.

Governance Audit

  • Jurisdiction: This skill is exclusively operated by the Skill Architect or the Orchestrator during refactor phases.
  • Rule 1 Compliance: All generated documents MUST be in Technical English and follow the kebab-case naming convention.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free