agentleFS
Sign inStart free
GstMirabalGstMirabal/Token-Optimized-Agent-Pipeline/skills/contract-writer/SKILL.md

contract-writer

Skill1 starsChanged 10 days agoMITView on GitHub

Documentary reverse engineering — extracts structured API contracts (I/O payloads, headers, status codes, auth) directly from implementation code into standardized Markdown tables under docs/contracts/.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 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.

  • 2

    Very specific

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

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

    Diagram Alignment: Ensure that any endpoint or service described in a contract is also reflected in the global_topology.md using Mermaid.

    line 30
  2. Very specific:

    Compliance Rule: No manual contract writing is allowed.

    line 33
  3. Distinctive:

    Language Isolation: All generated documentation MUST be in Technical English.

    line 34

≈ “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

🛠️ Local Skill: Contract Writer (v1.0.0)

Domain

  • Category: Documentation / Reverse Engineering
  • Origin: Custom synthesis for AI-driven API contract generation.
  • Status: ACTIVE_LOCAL
  • Sovereignty: local (Project-Specific)

Technical Logic

This skill provides the procedural protocol for Documentary Reverse Engineering. It enables a subagent to extract structured technical agreements (I/O, Payloads, Auth) directly from operated code files (.py, .ts, .go, etc.) without human intervention.

Procedures

1. Payload Synthesis

  • Logic Extraction: The agent must identify data classes (Pydantic, Interfaces, JSDoc) to reconstruct JSON request/response bodies.
  • Schema Mapping: Map nested objects to flat Markdown descriptions for LLM readability.

2. Interface Normalization

  • Metadata Harvesting: Extract Headers, Query Parameters, and HTTP Status Codes from the implementation logic.
  • Contract Format: Force output into standardized Markdown tables:
    FieldTypeRequiredDescription

3. Topological Sync

  • Diagram Alignment: Ensure that any endpoint or service described in a contract is also reflected in the global_topology.md using Mermaid.

Governance Audit

  • Compliance Rule: No manual contract writing is allowed; all .md contracts must be generated using this protocol to ensure 1:1 parity with the codebase.
  • Language Isolation: All generated documentation MUST be in Technical English.

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