메뉴
Refactoring audit via the `agf` CLI — SOLID/DRY/McCabe + token economy. Run on code smells, accumulated debt, before closing REVIEW, or during VALIDATE gating.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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
| name | graph-quality |
| description | Refactoring audit via the `agf` CLI — SOLID/DRY/McCabe + token economy. Run on code smells, accumulated debt, before closing REVIEW, or during VALIDATE gating. |
| triggers | ["graph-quality"] |
| version | 2.0.0 |
| author | auto-generated |
| date | "2026-06-16T00:00:00.000Z" |
| category | REVIEW |
| phase | REVIEW |
| tokens | ~544 |
| phases | ["REVIEW","VALIDATE"] |
Refactoring audit (SOLID/DRY/McCabe) + token economy. Drive via the agf CLI — zero MCP. Load context with agf context <id> first.
agf harness --violations → agf quality → agf insights
REVIEW-phase agf commands:
| Command | What it does |
|---|---|
agf quality | Gate 95/95 (tests + logs) |
agf harness --violations | Violations per weak dimension |
agf compress discover | Output-compression opportunities (token cut) |
agf insights | Complexity + duplication (McCabe, DRY) |
agf harness --violations (missing types, empty catches, console.log)agf quality (95/95: tests + logs over src/)agf insights (McCabe, duplication, naming)agf compress discoveragf harness to confirm no regressionPhase: QUALITY (REVIEW parallel)
Violations: N found, M addressed
Quality Gate: 95/95 — pass/fail
Complexity: McCabe avg X, duplication Y%
Token Economy: Z opportunities
Harness: score X (no regression)
Status: Quality gate passed
Parallel to REVIEW → HANDOFF. After tasks, agf savings / agf metrics --economy-report → agf learning → calibrate next turn.
agf skill show graph-reviewagf skill show graph-validateAGENTS.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.