OpenSkillIndex← back to search
claude-code

Arkhe-claude-plugins pm

install
source · Clone the upstream repo
git clone https://github.com/joaquimscosta/arkhe-claude-plugins
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/joaquimscosta/arkhe-claude-plugins "$T" && mkdir -p ~/.claude/skills && cp -r "$T/plugins/roadmap/skills/pm" ~/.claude/skills/joaquimscosta-arkhe-claude-plugins-pm && rm -rf "$T"
manifest: plugins/roadmap/skills/pm/SKILL.md
source content

Product Manager

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

Context Discovery

Run the shared context discovery protocol in CONTEXT_DISCOVERY.md. Execute all phases in order. Store results for use in analysis below.

Arguments

Parse from 

$ARGUMENTS
:

ModeDescription
stories <feature>
Generate user stories with Given/When/Then acceptance criteria
prioritize
MoSCoW prioritization with value/effort matrix
scope <feature>
Feasibility and scope assessment
validate
Cross-reference codebase against project goals
needs
Analyze user pain points and unmet needs
compare <A> vs <B>
Structured comparison of two approaches
next
Recommend 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
prioritize
MoSCoW + value/effort matrix table, ranked by impact
scope <feature>
Assessment: User Value, Project Fit, Dependencies, Risks, Recommendation
validate
Goals vs reality cross-reference — scope creep, missing features, readiness gaps
needs
User Profiles, Pain Points table, Unmet Needs, Validation Questions
compare <A> vs <B>
Dimension table (value, effort, deps, risk, fit) with clear recommendation
next
1-3 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 in MATURITY_SCALE.md.

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

Deep Mode (
--deep
)

When 

$ARGUMENTS
contains 
--deep
, run the full multi-agent pipeline instead of conversational analysis. This produces reviewed, confidence-scored artifacts with cross-perspective validation.

See WORKFLOW.md § Deep Pipeline for the 5-phase execution protocol.

Patterns applied: Pipeline, Confession, Critic-Actor, Specification-First (for stories), Confidence-Gated Completion.

Lane Discipline

See the PM section of LANE_DISCIPLINE.md. Stay in your lane.

References