Menu
Execute the ANALYZE phase of the lifecycle via the `agf` CLI — PRD creation, requirements, Definition of Ready (7 checks), cross-project learning
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Accessibility compliance audit using WCAG 2.2 AA standards, ARIA validation, screen reader testing, keyboard navigation, color contrast analysis, and i18n readiness
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
Bug discovery + structured fix (5-Whys) with regression test, driven by the `agf` CLI — zero MCP
| name | graph-analyze |
| description | Execute the ANALYZE phase of the lifecycle via the `agf` CLI — PRD creation, requirements, Definition of Ready (7 checks), cross-project learning |
| triggers | ["graph-analyze"] |
| version | 2.0.0 |
| author | Diego Nogueira |
| date | "2026-04-04T00:00:00.000Z" |
ANALYZE phase via the agf CLI (zero MCP). Creates the PRD, defines requirements, imports them into the graph. Entry point of the 9-phase lifecycle.
agf phase reports ANALYZE[agf search] → agf import-prd <file> / agf node add → agf edge add → agf gate analyze → agf phase design
agf search "<errors | estimates | adrs | patterns>"
agf memory read <name>
Gather: problem statement, target users, MVP features, NFRs, constraints.
Import: agf import-prd <file>
Or write prd.md (vision, problem, objectives, architecture, functional + non-functional requirements, risks) then agf import-prd prd.md.
agf node add --type requirement
agf node add --type epic
agf edge add <from> <to> --type <rel>
Types: requirement→epic, epic→milestone, requirement→requirement.
agf node add --type risk
agf node add --type constraint
Link risks to the requirements/epics they affect.
agf memory write <name>
agf gate analyze
| # | Check |
|---|---|
| 1 | has_requirements — ≥1 epic/requirement |
| 2 | has_acceptance_criteria — tasks/AC exist |
| 3 | no_orphans |
| 4 | no_cycles |
| 5 | has_constraints — ≥1 |
| 6 | has_risks — ≥1 |
| 7 | prd_quality_score ≥ 60 |
On failure, fix and re-run.
agf phase design
Follow the CLI's next-action hint.
Phase: ANALYZE → DESIGN
PRD: imported (N reqs, M epics, K risks, J constraints)
Gate: prd_quality N/100; ready 7/7
Status: Ready for DESIGN
Loop link → DESIGN (graph-design):
agf context <epic>to start ADRs.
agf node add to create nodesAGENTS.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.