AI.MD v4 — The Complete AI-Native Conversion System workflow skill. Use this skill when the user needs Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
Instrucciones de origen · Vista previa de solo lectura
name
ai-md
description
AI.MD v4 — The Complete AI-Native Conversion System workflow skill. Use this skill when the user needs Convert human-written CLAUDE.md into AI-native structured-label format. Battle-tested across 4 models. Same rules, fewer tokens, higher compliance and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
AI.MD v4 — The Complete AI-Native Conversion System
Overview
This public intake copy packages plugins/antigravity-awesome-skills-claude/skills/ai-md from https://github.com/sickn33/antigravity-awesome-skills into the native Omni Skills editorial shape without hiding its origin.
Use it when the operator needs the upstream workflow, support files, and repository context to stay intact while the public validator and private enhancer continue their normal downstream flow.
This intake keeps the copied upstream files intact and uses the external_source block in metadata.json plus ORIGIN.md as the provenance anchor for review.
AI.MD v4 — The Complete AI-Native Conversion System
Imported source sections that did not map cleanly to the public headings are still preserved below or in the support files. Notable imported sections: What Is AI.MD?, Special Techniques Discovered During Battle-Testing, AI-Native Template, Anti-Patterns, Real-World Results, Limitations.
When to Use This Skill
Use this section as the trigger filter. It should make the activation boundary explicit before the operator loads files, runs commands, or opens a pull request.
Use when your CLAUDE.md is long but AI still ignores your rules
Use when token usage is too high from verbose system instructions
Use when you want to optimize any LLM system prompt for compliance
Use when migrating rules between AI tools (Claude, Codex, Gemini, Grok)
Is this a TRIGGER? (What input activates this behavior?)
Is this an ACTION? (What should the AI do?)
Operating Table
Situation
Start here
Why it matters
First-time use
metadata.json
Confirms repository, branch, commit, and imported path through the external_source block before touching the copied workflow
Provenance review
ORIGIN.md
Gives reviewers a plain-language audit trail for the imported source
Workflow execution
SKILL.md
Starts with the smallest copied file that materially changes execution
Supporting context
SKILL.md
Adds the next most relevant copied source file without loading the entire package
Handoff decision
## Related Skills
Helps the operator switch to a stronger native skill when the task drifts
Workflow
This workflow is intentionally editorial and operational at the same time. It keeps the imported source useful to the operator while still satisfying the public intake standards that feed the downstream enhancer flow.
Phase 6: Run multi-model test (minimum 2 models, 8 questions)
Report: Show before/after scores
Confirm the user goal, the scope of the imported workflow, and whether this skill is still the right router for the task.
Read the overview and provenance files before loading any copied upstream support files.
Load only the references, examples, prompts, or scripts that materially change the outcome for the current request.
Imported Workflow Notes
Imported: Why It Works: How LLMs Actually Process Instructions
LLMs don't "read" — they attend. Understanding this changes everything.
Mechanism 1: Attention Splitting
When multiple rules share one line, the model's attention distributes across all tokens equally.
Each rule gets a fraction of the attention weight. Some rules get lost.
When each rule has its own line, the model processes it as a distinct unit.
Full attention weight on each rule.
# ONE LINE = attention splits 5 ways (some rules drop to near-zero weight)
EVIDENCE: no-fabricate no-guess | 禁用詞:應該是/可能是 → 先拿數據 | Read/Grep→行號 curl→數據 | "好像"/"覺得"→自己先跑test | guess=shame-wall
# FIVE LINES = each rule gets full attention
EVIDENCE:
core: no-fabricate | no-guess | unsure=say-so
banned: 應該是/可能是/感覺是/推測 → 先拿數據
proof: all-claims-need(data/line#/source) | Read/Grep→行號 | curl→數據
hear-doubt: "好像"/"覺得" → self-test(curl/benchmark) → 禁反問user
violation: guess → shame-wall
Mechanism 2: Zero-Inference Labels
Natural language forces the model to INFER meaning from context.
Labels DECLARE meaning explicitly. No inference needed = no misinterpretation.
# AI must infer: what does (防搞混) modify? what does 例外 apply to?
GATE-1: 收到任務→先用一句話複述(防搞混)(長對話中每個新任務都重新觸發) | 例外: signals命中「處理一下」=直接執行
# AI reads labels directly: trigger→action→exception. Zero ambiguity.
GATE-1 複述:
trigger: new-task
action: first-sentence="你要我做的是___"
persist: 長對話中每個新任務都重新觸發
exception: signal=處理一下 → skip
yields-to: GATE-3
Key insight: Labels like trigger:action:exception: work across ALL languages.
The model doesn't need to parse Chinese/Japanese/English grammar to understand structure.
Labels are the universal language between humans and AI.
Mechanism 3: Semantic Anchoring
Labeled sub-items create matchable tags. When a user's input contains a keyword,
the model matches it directly to the corresponding label — like a hash table lookup
instead of a full-text search.
# BURIED: AI scans the whole sentence, might miss the connection
加新功能→第一句問schema | 新增API/endpoint=必確認health-check.py覆蓋
# ANCHORED: label "new-api:" directly matches user saying "加個 API"
MOAT:
new-feature: 第一句問schema/契約/關聯
new-api: 必確認health-check.py覆蓋(GATE-5)
Real proof: This specific technique fixed a test case that failed 5 consecutive times
across all models. The label new-api: raised Codex T5 from ❌→✅ on first try.
AI.MD is a methodology for converting human-written CLAUDE.md (or any LLM system instructions)
into a structured-label format that AI models follow more reliably, using fewer tokens.
The paradox we proved: Adding more rules in natural language DECREASES compliance.
Converting the same rules to structured format RESTORES and EXCEEDS it.
Human prose (6 rules, 1 line) → AI follows 4 of them
Structured labels (6 rules, 6 lines) → AI follows all 6
Same content. Different format. Different results.
Examples
Example 1: Ask for the upstream workflow directly
Use @ai-md to handle <task>. Start from the copied upstream workflow, load only the files that change the outcome, and keep provenance visible in the answer.
Explanation: This is the safest starting point when the operator needs the imported workflow, but not the entire repository.
Example 2: Ask for a provenance-grounded review
Review @ai-md against metadata.json and ORIGIN.md, then explain which copied upstream files you would load first and why.
Explanation: Use this before review or troubleshooting when you need a precise, auditable explanation of origin and file selection.
Example 3: Narrow the copied support files before execution
Use @ai-md for <task>. Load only the copied references, examples, or scripts that change the outcome, and name the files explicitly before proceeding.
Explanation: This keeps the skill aligned with progressive disclosure instead of loading the whole copied package by default.
Example 4: Build a reviewer packet
Review @ai-md using the copied upstream files plus provenance, then summarize any gaps before merge.
Explanation: This is useful when the PR is waiting for human review and you want a repeatable audit packet.
Best Practices
Treat the generated public skill as a reviewable packaging layer around the upstream repository. The goal is to keep provenance explicit and load only the copied source material that materially improves execution.
Keep the imported skill grounded in the upstream repository; do not invent steps that the source material cannot support.
Prefer the smallest useful set of support files so the workflow stays auditable and fast to review.
Keep provenance, source commit, and imported file paths visible in notes and PR descriptions.
Point directly at the copied upstream files that justify the workflow instead of relying on generic review boilerplate.
Treat generated examples as scaffolding; adapt them to the concrete task before execution.
Route to a stronger native skill when architecture, debugging, design, or security concerns become dominant.
Troubleshooting
Problem: The operator skipped the imported context and answered too generically
Symptoms: The result ignores the upstream workflow in plugins/antigravity-awesome-skills-claude/skills/ai-md, fails to mention provenance, or does not use any copied source files at all.
Solution: Re-open metadata.json, ORIGIN.md, and the most relevant copied upstream files. Check the external_source block first, then restate the provenance before continuing.
Problem: The imported workflow feels incomplete during review
Symptoms: Reviewers can see the generated SKILL.md, but they cannot quickly tell which references, examples, or scripts matter for the current task.
Solution: Point at the exact copied references, examples, scripts, or assets that justify the path you took. If the gap is still real, record it in the PR instead of hiding it.
Problem: The task drifted into a different specialization
Symptoms: The imported skill starts in the right place, but the work turns into debugging, architecture, design, security, or release orchestration that a native skill handles better.
Solution: Use the related skills section to hand off deliberately. Keep the imported provenance visible so the next skill inherits the right context instead of starting blind.
Related Skills
@00-andruia-consultant - Use when the work is better handled by that native specialization after this imported skill establishes context.
@00-andruia-consultant-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
@10-andruia-skill-smith - Use when the work is better handled by that native specialization after this imported skill establishes context.
@10-andruia-skill-smith-v2 - Use when the work is better handled by that native specialization after this imported skill establishes context.
Additional Resources
Use this support matrix and the linked files below as the operator packet for this imported skill. They should reflect real copied source material, not generic scaffolding.
Resource family
What it gives the reviewer
Example path
references
copied reference notes, guides, or background material from upstream
references/n/a
examples
worked examples or reusable prompts copied from upstream
examples/n/a
scripts
upstream helper scripts that change execution or validation
scripts/n/a
agents
routing or delegation notes that are genuinely part of the imported package
agents/n/a
assets
supporting assets or schemas copied from the source package
assets/n/a
Imported Reference Notes
Imported: Special Techniques Discovered During Battle-Testing
Technique 1: Bilingual Label Strategy
Labels in English, output strings in the user's language.
English labels are shorter AND more universally understood by all models.
But the actual text the AI produces must stay in the user's language.
action: first-sentence="你要我做的是___" ← AI outputs Chinese
format: must-be-line-1 ← structural constraint in English
banned: 應該是/可能是 ← forbidden words stay in original language
Why this works: English label vocabulary (trigger, action, exception) maps directly
to concepts in every model's training data. Chinese grammar labels (觸發條件, 執行動作, 例外情況)
are less standardized across models.
Technique 2: State Machine Gates
Instead of treating rules as a flat list, model them as a state machine:
Each gate has a trigger (input state)
Each gate has an action (transition)
Gates have priority (which fires first when multiple match)
Gates have yields-to (explicit conflict resolution)
Input arrives → Read all rules → Try to figure out which one applies → Maybe miss one
Technique 3: XML Section Tags for Semantic Boundaries
Using <gates>, <rules>, <rhythm>, <conn> as section delimiters
creates hard boundaries that prevent rule-bleed (where the model confuses
which section a rule belongs to).
