predict
FeaturedPre-implementation multi-persona adversarial analysis for gflow-cli proposals. Five expert personas independently evaluate a proposed change before a single line of code is written, then converge on a GO / CAUTION / STOP verdict. Invoke before any high-stakes decision: new transport, auth change, selector redesign, schema migration, API surface change, or backlog item requiring an investigation gate.
Install
Quality Score: 87/100
Skill Content
Details
- Author
- ffroliva
- Repository
- ffroliva/gflow-cli
- Created
- 4 months ago
- Last Updated
- today
- Language
- Python
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
plan
Creates a structured task-by-task implementation plan for a gflow-cli feature. Gathers predict/scenario context, asks ≤3 clarifying questions, decomposes the feature into atomic committable tasks with step and test checklists, and writes docs/superpowers/plans/<YYYY-MM-DD>-<slug>/PLAN.md. Invoke after /gflow:predict returns GO or CAUTION and /gflow:scenario output is available.
scenario
Pre-implementation edge-case and scenario explorer for gflow-cli. Decomposes a proposed feature or change across 13 structured dimensions specific to gflow-cli's failure surfaces (WAF/reCAPTCHA, Playwright selectors, auth token lifecycle, batch resume, data layer safety, cross-platform paths). Produces a severity-ranked scenario table to feed into the PLAN spec and the test matrix before EXECUTE begins.
prepare
Pre-implementation analysis — strategic brainstorm, impact mapping, SOLID extension checks, DRY reuse discovery, complexity tiering, and (for complex work) decomposition into an atomic, parallel-safe backlog. TRIGGER when the user wants pre-implementation analysis/decomposition before coding ("prepare", "analyze before building", "think through this", "decompose this task", "plan the work"). DO NOT TRIGGER when: the user already has a clear plan and just wants to build it → use /implement; the request is "add another <X> like the existing one" in a project that already has that shape → use /scaffold; or requirements are still unclear/ambiguous → use /analyst first.