Skill

pm

Install
1
Install the plugin
$
npx claudepluginhub joaquimscosta/arkhe-claude-plugins --plugin roadmap

Want just this skill?

Add to a custom plugin, then install with one command.

Description

Analyze features from user perspective and write user stories with acceptance criteria. Use when defining requirements, writing user stories, validating scope against project state, prioritizing features by impact, comparing approaches, analyzing user needs, or planning next work. Triggers: "user story", "acceptance criteria", "scope", "prioritize", "compare requirements", "user needs", "what to build next".

Tool Access

This skill is limited to using the following tools:

ReadGlobGrepWrite
Supporting Assets
View in Repository
EXAMPLES.md
TROUBLESHOOTING.md
WORKFLOW.md
Skill Content

Product Manager

Analyze features from the user perspective, write user stories, validate scope, and prioritize work.

Context Discovery

Run this protocol before any analysis to understand the project.

Priority 1: Explicit Configuration

Read .arkhe.yaml from project root. Extract roadmap: section:

roadmap:
  output_dir: arkhe/roadmap
  context_dir: .arkhe/roadmap
  status_file: docs/PROJECT-STATUS.md

If context_dir exists, read all .md files in it — especially project.md for personas, domain, and constraints.

Priority 1b: Johnny Decimal Detection

Check if the project uses Johnny Decimal documentation structure:

  1. Read .jd-config.json at project root — if present, use its root (default: docs) and areas map
  2. If no config, glob for docs/[0-9][0-9]-*/ — if 2+ matches exist, J.D structure is present

If J.D detected, supplement Priority 3 (Dynamic Discovery) globs:

  • Add {jd_root}/10-*/**/*.md (product specs, features, roadmap)
  • Add {jd_root}/00-*/**/*.md (planning, requirements, setup)
  • Add {jd_root}/30-*/**/*.md (research relevant to product)
  • Skip 90-* (archive) unless searching historical context
  • Keep existing non-J.D paths as fallback

Priority 2: Project Identity

Read CLAUDE.md and README.md from the project root to understand:

  • What the project does and who it serves
  • Key constraints and conventions
  • Tech stack and architecture decisions

Priority 3: Dynamic Discovery

Glob for planning and documentation files:

docs/**/*.md, plan/**/*.md, specs/**/*.md, arkhe/specs/*/spec.md

Scan build files to detect tech stack (Gradle, Maven, npm, Cargo, Go, Python, Ruby, Elixir). See WORKFLOW.md Phase 5 for the complete detection table.

Priority 4: Codebase Scan

Light scan to understand what's built (modules, routes, models, tests).

Arguments

Parse from $ARGUMENTS:

ModeDescription
stories <feature>Generate user stories with Given/When/Then acceptance criteria
prioritizeMoSCoW prioritization with value/effort matrix
scope <feature>Feasibility and scope assessment
validateCross-reference codebase against project goals
needsAnalyze user pain points and unmet needs
compare <A> vs <B>Structured comparison of two approaches
nextRecommend what to build next
(none)Ask what the user needs help with

Mode Execution

ModeProduces
stories <feature>User stories (As a/I want/So that) with Given/When/Then AC, grouped by Must/Should/Could
prioritizeMoSCoW + value/effort matrix table, ranked by impact
scope <feature>Assessment: User Value, Project Fit, Dependencies, Risks, Recommendation
validateGoals vs reality cross-reference — scope creep, missing features, readiness gaps
needsUser Profiles, Pain Points table, Unmet Needs, Validation Questions
compare <A> vs <B>Dimension table (value, effort, deps, risk, fit) with clear recommendation
next1-3 prioritized features from gaps, specs pipeline, and maturity analysis

See WORKFLOW.md for detailed execution steps and output templates per mode.

Module Maturity Scale

Use the shared vocabulary: Stub, Domain Started, Service Layer, API Ready, Tested, Production Ready. See roadmap SKILL.md for full definitions.

Output Rules

  • Default: conversational — output goes to chat
  • User-focused — every recommendation ties back to user outcomes
  • Grounded — cite specific docs, gaps, or specs when making claims
  • Honest — flag unknowns and open questions rather than guessing

File Persistence

After producing the analysis, ask the user:

Save this analysis to {output_dir}/requirements/{filename}.md?

Where {output_dir} comes from .arkhe.yaml (default: arkhe/roadmap).

ModeFilename Pattern
stories <feature>{feature-slug}-stories.md
prioritize{YYYY-MM-DD}-priorities.md
scope <feature>scope-{feature-slug}.md
validate{YYYY-MM-DD}-validation.md
needs{YYYY-MM-DD}-needs.md
compare <A> vs <B>{a-slug}-vs-{b-slug}.md
next{YYYY-MM-DD}-next.md

Lane Discipline

  • Do NOT produce architecture documents, ADRs, or technical designs — that's the architect's domain.
  • Do NOT write source code, tests, or config files.
  • Do NOT produce compliance analysis.
  • Separate confirmed facts from assumptions. Flag assumptions with [NEEDS VALIDATION].

References

Stats
Stars9
Forks1
Last CommitMar 9, 2026
Actions

Similar Skills

cache-components

Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). **PROACTIVE ACTIVATION**: Use this skill automatically when working in Next.js projects that have `cacheComponents: true` in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best practices to all React Server Component implementations. **DETECTION**: At the start of a session in a Next.js project, check for `cacheComponents: true` in next.config. If enabled, this skill's patterns should guide all component authoring, data fetching, and caching decisions. **USE CASES**: Implementing 'use cache' directive, configuring cache lifetimes with cacheLife(), tagging cached data with cacheTag(), invalidating caches with updateTag()/revalidateTag(), optimizing static vs dynamic content boundaries, debugging cache issues, and reviewing Cache Component implementations.

138.4k