integration-selection-analysis
Skill0 starsChanged 2 months agoMITView on GitHub
Determine exactly how concrete clients/adapters/protocols/backends are selected, with mandatory counterexample search and promotion gates before routing rules enter canonical decision matrices.
In this repository33 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- adversarial-baseline-auditSkill
- architecture-drift-detectionSkill
- architecture-reconstruction-and-diagramsSkill
- artifact-detailed-designSkill
- baseline-source-of-truth-maintenanceSkill
- claim-verification-and-promotionSkill
- configuration-source-traceSkill
- contract-impact-test-designSkill
- current-state-tdd-synthesisSkill
- design-artifact-decompositionSkill
- design-artifact-decomposition-verificationSkill
- detailed-design-verificationSkill
- full-reverse-engineeringSkill
- implementation-readiness-certificationSkill
- incident-root-cause-analysisSkill
- observability-traceability-analysisSkill
- patch-impact-reviewSkill
- persistence-schema-reverse-engineeringSkill
- post-readiness-adversarial-auditSkill
- regression-test-designSkill
- requirement-compliance-reviewSkill
- resolve-high-impact-unknownsSkill
- resume-reverse-engineeringSkill
- reverse-engineering-bootstrapSkill
- reverse-engineering-coverage-auditSkill
- run-engineering-workflowSkill
- runtime-binding-verificationSkill
- runtime-flow-analysisSkill
- technical-design-proposalSkill
- technical-design-verificationSkill
- wbs-generationSkill
- wbs-verificationSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 37
Every routing rule begins as candidate.
- Very specific: line 47
Before adding a row to 00_master_decision_matrix.md:
- Distinctive: line 52
search all relevant branches
- Very specific: line 60
If any condition is unresolved, keep it in 00_hypotheses.md, not canonical matrix.
≈ “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.
Files
Integration Selection Analysis — 4.0
Core Question
Under exactly what conditions is each concrete implementation selected?
Search
Find:
- abstractions
- all implementations
- factories/providers/registries
- DI/container wiring
- config
- enums/constants
- target/model/version branches
- operation-specific routing
- fallback paths
Separate Dimensions
Do not merge:
- operation selection
- target/entity selection
- mode selection
- concrete implementation selection
- protocol/transport selection
- fallback selection
Candidate Rule
Every routing rule begins as candidate.
Example candidate:
For operation X and target Y, condition Z selects Client A.Promotion Gate for Routing
Before adding a row to 00_master_decision_matrix.md:
- trace caller to selector
- identify concrete implementation
- verify active wiring
- search all relevant branches
- search alternate implementations
- inspect config-driven behavior
- inspect fallback
- scope the rule narrowly
- assign Evidence ID
- mark Promotion Status=PROMOTED
If any condition is unresolved, keep it in 00_hypotheses.md, not canonical matrix.
Architecture Model Requirement
Update:
docs/reverse-engineering/models/integration_catalog.md
docs/reverse-engineering/diagrams/04_integration_boundaries.mdThe catalog must classify every known material external integration with:
| Integration | Caller/Owner | Abstraction | Selector/Binding | Concrete Implementation | Protocol/Boundary | Config | Failure/Fallback | Evidence |
04_integration_boundaries.md must contain a Mermaid diagram showing application components, selection/binding points, concrete integrations, and external systems/processes. Include Evidence Anchors.
A list of client/factory class names is not sufficient integration architecture.
Output
docs/reverse-engineering/integration-selection.md
Update:
- evidence ledger
- hypotheses/open questions
- canonical matrix only for promoted rows
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
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.