agentleFS
tuana-vntuana-vn/system-reverse-engineer/.github/skills/current-state-tdd-synthesis/SKILL.md

current-state-tdd-synthesis

Skill0 starsChanged 2 months agoMITView on GitHub

Synthesize verified reverse-engineering evidence and architecture models into a consumer-facing CURRENT_STATE_TDD.md that explains current responsibilities, dependencies, runtime flows, boundaries, state, variants, failure behavior, and evidence without turning the audit report into the baseline.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use these headings in this order:

    line 38
  2. Very specific:

    If a section is not applicable, write NOT_APPLICABLE plus the evidence supporting that classification.

    line 61
  3. Distinctive:

    Do not duplicate five large diagrams in every artifact.

    line 75
  4. Distinctive:

    Do not declare synthesis complete until:

    line 112

≈ “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

Current-State TDD Synthesis — 4.0

Mission

Produce the canonical consumer-facing current-system technical design:

docs/reverse-engineering/CURRENT_STATE_TDD.md

This document is the durable input for later Design Agent work.

The readiness audit is a separate artifact. Do not make an audit table the primary baseline document.

Consumer Test

A backend developer unfamiliar with the repository should be able to understand, within approximately 15–20 minutes:

  • system boundary and purpose;
  • major component responsibilities;
  • dependency direction;
  • primary runtime flows;
  • external integration boundaries;
  • state/persistence ownership;
  • lifecycle/concurrency behavior;
  • configuration/runtime selection;
  • failure/error behavior;
  • build/runtime structure;
  • material unknowns and evidence anchors.

Required TDD Sections

Use these headings in this order:

# Current-State Technical Design
## 1. System Context
## 2. Architecture Overview
## 3. Component Responsibilities
## 4. Runtime Entry Points
## 5. Primary Runtime Flows
## 6. Integration Architecture
## 7. Persistence and State Ownership
## 8. Background Processing and Lifecycle
## 9. Configuration and Runtime Selection
## 10. Error, Retry, and Fallback Behavior
## 11. Security Boundaries
## 12. Observability
## 13. Build and Runtime Model
## 14. Critical Current-System Rules
## 15. Runtime Variants and Alternate Paths
## 16. Known Unknowns and External Blockers
## 17. Evidence and Diagram Index

If a section is not applicable, write NOT_APPLICABLE plus the evidence supporting that classification.

Diagram Integration

Reference the mandatory diagram artifacts from the relevant TDD sections:

diagrams/01_system_context.md
diagrams/02_component_architecture.md
diagrams/03_primary_runtime_sequence.md
diagrams/04_integration_boundaries.md
diagrams/05_state_persistence_lifecycle.md

Do not duplicate five large diagrams in every artifact. The TDD may embed the most important diagram and link the rest by repository-relative path.

Evidence Precision

Material current-state statements must use evidence precise enough to re-open quickly:

Preferred:

path + symbol/method/config key + optional line/range

Minimum for source-backed material claims:

repo-relative path

Class name alone is not a sufficient source anchor when a path can be determined.

Synthesis Rules

Prefer:

relationship > inventory
behavior > file count
responsibility > package list
runtime selection > implementation existence
state ownership > entity dump
consumer usability > audit verbosity

Large schema tables, exhaustive class inventories, and exhaustive evidence ledgers belong in supporting model/evidence artifacts. Summarize the important meaning in the TDD.

Completion Gate

Do not declare synthesis complete until:

[ ] all required sections exist
[ ] all 5 mandatory diagram artifacts exist and are referenced
[ ] all material subsystems are represented in component catalog
[ ] primary runtime flows are represented in runtime flow catalog
[ ] all known external integrations are represented in integration catalog
[ ] behavior-changing configuration selectors are represented in configuration model
[ ] persistence/state ownership is represented or explicitly NOT_APPLICABLE
[ ] material current-state claims use repo-relative evidence paths
[ ] unresolved HIGH/CRITICAL items remain explicit

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.