agentsclimarketplace

Phronesis

Skill broomva/skills/skills/strategy/phronesis

Broomva agent-skills monorepo — 48 Tier-2 skills compatible with Claude Code, Codex, Cursor, Gemini CLI, Goose, Copilot. Layout follows anthropics/skills (agentskills.io spec). Install: npx skills add broomva/skills --skill <name>.

Install
npx -y skills add broomva/skills --skill phronesis

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

AI-native advisory practice for the Broomva ecosystem. Encodes top-firm consulting methodology (Three Horizons, MIT CISR digital maturity, JTBD, Value Proposition Canvas, RICE/ICE/WSJF, NPV + Real Options, QuantumBlack ML lifecycle, Wardley Mapping) as runnable typed primitives. Produces 7 Discovery-grade deliverables in two modes — consultant CLI or autonomous Life Runtime endpoint. Use when: (1) running an AI/digital consulting engagement, (2) building a maturity assessment, (3) generating prioritized use-case dossiers, (4) designing an innovation roadmap, (5) modeling ROI for AI initiatives, (6) designing controlled pilots, (7) extracting reusable IP from completed engagements. Triggers on 'consulting', 'consultancy', 'advisory', 'fast discovery', 'discovery sprint', 'AI maturity', 'digital maturity', 'use case ideation', 'use case prioritization', 'innovation roadmap', 'roi model', 'consultoría', 'evaluación de madurez', 'hoja de ruta'.

SKILL.md

4.9 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

phronesis — AI-native Advisory Practice

Status: Phase 1 complete (v0.1.2-pre) — substrate + 15 active frameworks + 5 stages + 7 deliverables + L1–L5 linter + M7 extraction pipeline. Phase 2 engagement-driven (M4 stage CLI + M5 autonomous-mode stub-to-real path). Track progress: docs/methodology.md (canonical reference), docs/adr/0001-0008, and the design spec at ~/broomva/docs/superpowers/specs/2026-05-06-phronesis-design.md.

What it does

Runs AI/digital consulting engagements through 5 stages:

  1. Intake — stakeholder map, interview guide, strategic thesis (kills "hagamos algo de IA" — Bision empirical 100% failure)
  2. Maturity Scan — MIT CISR + Gartner AI dimensions, gap analysis, capability heatmap
  3. Use-Case Ideation — JTBD + VPC, with IdeationSource diversity check
  4. Prioritization — RICE/ICE/WSJF, ROI Model with sensitivity, Impact-Effort Matrix
  5. Roadmap Synthesis — Three Horizons, QuantumBlack ML lifecycle pilots, baselines captured

Each stage has a non-negotiable human-review gate.

When to invoke this skill

  • User asks for AI/digital consulting work — maturity assessment, roadmap, use-case prioritization
  • User mentions Spanish-language equivalents: "consultoría", "evaluación de madurez", "hoja de ruta"
  • User describes a Fast Discovery, discovery sprint, or strategic-thesis-finding engagement
  • User wants to extract reusable IP from a completed engagement (cross-engagement learning)

When NOT to invoke this skill

  • User wants generic "do AI for me" without scope — phronesis explicitly refuses to start without a strategic thesis
  • User wants implementation work, not advisory — phronesis produces plans and recommendations, not running systems
  • User wants change-management or organizational design — that's D-scope (deferred to a later phase)
  • User wants only personal-decision support — use strategy-skills instead

Commands (CLI mode — most land in M4)

phronesis init <tenant> --industry <industry> --region <iso> --sponsor "Name (Role)" --scope "..."
phronesis intake --interview "..." --transcript path/to/file.md
phronesis intake --thesis "..."         # captures StrategicThesis (L1)
phronesis review intake --approve | --revise
phronesis scan --frameworks mit-cisr-digital,gartner-ai
phronesis ideate --frameworks jobs-to-be-done,value-prop-canvas
phronesis prioritize --frameworks rice --roi unit-economics,real-options
phronesis roadmap --frameworks three-horizons --pilot-design quantumblack-ml
phronesis render --all
phronesis lint                          # P3, P7, P8, L1-L5 enforcement (blocking)
phronesis status
phronesis bookkeep <slug>               # extract anonymized learnings to research/entities/

Five C-level failure modes structurally prevented

Bision-observedFrequencyLinter ruleType primitive
Sin tesis estratégica100%L1 STRATEGIC_THESIS_REQUIREDStrategicThesis
Casos mal priorizados87%L2 DIVERSE_IDEATION_SOURCESIdeationSource
Datos no preparados74%L3 DATA_READINESS_GATEDataReadinessAssessment
Desconexión negocio-tech61%L4 ADOPTION_METRIC_REQUIREDAdoptionMetric
Sin medición de ROI48%L5 BASELINE_REQUIREDBaselineSection

Documentation

  • Methodology: docs/methodology.md — canonical methodology reference (10 sections: stages, deliverables, frameworks, gates, linter, anonymization, modes, discovery loop, IP extraction)
  • ADRs: docs/adr/0001- through 0008-
  • Design spec: ~/broomva/docs/superpowers/specs/2026-05-06-phronesis-design.md
  • Linear: Phronesis project
  • Quickstart: (M4 — pending stage CLI commands) docs/quickstart.md

Gives 0 of the 12 instructions most roadmap strategy skills give in ~1.0k tokens

Counted across 591 of the 672 authors here whose files we hold, read 2026-08-06

  • read product marketing context before asking questionsin 21 of 591, across 10 files
  • base price on perceived value, not costin 15 of 591, across 4 files
  • compact after finalizing a planin 14 of 591, across 9 files
  • differentiate tiers using features, limits, or supportin 14 of 591, across 3 files
  • use Van Westendorp to find acceptable price rangein 13 of 591, across 2 files
  • use MaxDiff to identify highly valued featuresin 13 of 591, across 2 files
  • map topics to buyer journey stagesin 12 of 591, across 6 files
  • Extract domain capabilities and classify subdomainsin 11 of 591, across 1 file
  • Define bounded contexts around consistency and ownershipin 11 of 591, across 1 file
  • Establish a ubiquitous language glossary and anti-termsin 11 of 591, across 1 file
  • Capture context boundaries in ADRs before implementationin 11 of 591, across 1 file
  • Open the strategic design template if neededin 11 of 591, across 1 file

Said here and by no other author read

  • capture a strategic thesis before starting
  • require human review at each stage gate
  • run the linter to enforce structural rules
  • generate deliverables across five engagement stages
  • extract anonymized learnings after engagements
  • refuse work lacking scope or a strategic thesis

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.