Menü
Execute the DESIGN phase of the lifecycle via the `agf` CLI — ADRs, architecture decisions, contract coverage, Code Intelligence impact analysis
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | graph-design |
| description | Execute the DESIGN phase of the lifecycle via the `agf` CLI — ADRs, architecture decisions, contract coverage, Code Intelligence impact analysis |
| triggers | ["graph-design"] |
| version | 2.0.0 |
| author | Diego Nogueira |
| date | "2026-04-04T00:00:00.000Z" |
DESIGN phase via the agf CLI (zero MCP). Defines architecture, creates ADRs, validates contract coverage before planning.
agf phase reports DESIGNagf context <id> → agf node add (decision) → agf edge add → agf insights → agf gate design → agf phase plan
agf context <epic or requirement id>
agf search "<architecture keywords>"
Review requirements/constraints/risks from ANALYZE.
agf insights
agf code impact <file>
Understand what design decisions will affect.
agf node add --type decision
Description format:
## Status: Accepted
## Context: [why needed]
## Decision: [what + how]
## Consequences: [trade-offs, follow-up, risks accepted]
Common: tech stack, storage, API design, comms patterns, error handling, testing, deploy model.
agf edge add <from> <to> --type <rel>
Types: decision→requirement, decision→epic, decision→risk, decision→decision.
Define contracts as constraint nodes:
agf node add --type constraint
agf memory write <name>
agf insights
Verify ADR completeness/quality and interface coverage across components.
agf gate design
Criteria: key decisions as ADR nodes, decisions linked to requirements, no orphan requirements, interface contracts defined. On failure, add missing ADRs/edges.
agf phase plan
Follow the CLI next-action hint.
Phase: DESIGN → PLAN
ADRs: N decisions Contracts: M constraints
Impact: K modules analyzed Coverage: J/T requirements addressed
Gate: design_ready N/100
Status: Ready for PLAN
Loop link → PLAN (graph-plan):
agf decomposeto break epics into atomic tasks.
agf node add for nodes; run impact analysis on existing codebasesAGENTS.md and use apply_patch for manual edits.Economia de tokens. Os levers compartilhados por todas as skills —
--select,agf retrieve-command,agf exec chain, reuso antes de criação — vivem em_shared.md→ Token Economy. Fonte única: um parágrafo repetido em trinta arquivos é o trigésimo primeiro que envelhece sozinho.
Accessibility compliance audit using WCAG 2.2 AA standards, ARIA validation, screen reader testing, keyboard navigation, color contrast analysis, and i18n readiness
Execute the ANALYZE phase of the lifecycle via the `agf` CLI — PRD creation, requirements, Definition of Ready (7 checks), cross-project learning
API governance and design audit using OpenAPI/Swagger spec generation, REST maturity model, contract validation, and breaking change detection
Architecture governance using C4 Model, ADR lifecycle, Architecture Fitness Functions, layer boundary enforcement, and drift detection
Human-in-the-loop PLANNING skill — investigates the project (graph + git + harness/gaps) and runs the whole ANALYZE→DESIGN→PLAN chain in one faceted loop to produce a COMPLETE PRD injected as graph backlog (epics, tasks, testable AC) for a separate agent to implement. Applies the project's planning methodologies — Impact Mapping + OKR per epic, JTBD, MoSCoW, WSJF/Cost-of-Delay, User Story Mapping, Example Mapping (Rules/Examples → Given-When-Then AC), SPIDR splitting, INVEST, Definition of Ready, Risk Matrix; the full catalogue lives in the skill body. Stops for the human after each complete PRD and iterates the next cycle from the project's own findings (dogfood). Does NOT implement. Triggers — graph-backlog-generation, gerar backlog, criar PRD, planejar feature, detalhar épico, novo ciclo, "plan the next thing", "what should we build next".
Automated bug discovery through static analysis, LSP diagnostics, pattern detection, regression hotspot analysis, and error catalog mining