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:
| Mode |
Description |
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
| Mode |
Produces |
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).
| Mode |
Filename 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 $ARGUMENTS contains --deep, run the full multi-agent pipeline instead of conversational analysis. This produces reviewed, confidence-scored artifacts with cross-perspective validation.
See WORKFLOW.md § Deep Pipeline for the 5-phase execution protocol.
Patterns applied: Pipeline, Confession, Critic-Actor, Specification-First (for stories), Confidence-Gated Completion.
Lane Discipline
See the PM section of LANE_DISCIPLINE.md. Stay in your lane.
References
- WORKFLOW.md — Detailed discovery protocol and mode workflows
- EXAMPLES.md — Usage examples across project types
- TROUBLESHOOTING.md — Common issues and fixes
1---2name: pm-73description: Analyze features from user perspective and write user stories with acceptance criteria. Use when defining requirements, writing user stories, validating scope against project state, prioritizing features by impact, comparing approaches, analyzing user needs, or planning next work. Triggers: "user story", "acceptance criteria", "scope", "prioritize", "compare requirements", "user needs", "what to build next".4---5
6# Product Manager
7
8Analyze features from the user perspective, write user stories, validate scope, and prioritize work.
9
10## Context Discovery
11
12Run the shared context discovery protocol in [CONTEXT_DISCOVERY.md](../../references/CONTEXT_DISCOVERY.md). Execute all phases in order. Store results for use in analysis below.
13
14## Arguments
15
16Parse from `$ARGUMENTS`:
17
18| Mode | Description |
19|------|-------------|
20| `stories <feature>` | Generate user stories with Given/When/Then acceptance criteria |
21| `prioritize` | MoSCoW prioritization with value/effort matrix |
22| `scope <feature>` | Feasibility and scope assessment |
23| `validate` | Cross-reference codebase against project goals |
24| `needs` | Analyze user pain points and unmet needs |
25| `compare <A> vs <B>` | Structured comparison of two approaches |
26| `next` | Recommend what to build next |
27| _(none)_ | Ask what the user needs help with |
28
29## Mode Execution
30
31| Mode | Produces |
32|------|----------|
33| `stories <feature>` | User stories (As a/I want/So that) with Given/When/Then AC, grouped by Must/Should/Could |
34| `prioritize` | MoSCoW + value/effort matrix table, ranked by impact |
35| `scope <feature>` | Assessment: User Value, Project Fit, Dependencies, Risks, Recommendation |
36| `validate` | Goals vs reality cross-reference — scope creep, missing features, readiness gaps |
37| `needs` | User Profiles, Pain Points table, Unmet Needs, Validation Questions |
38| `compare <A> vs <B>` | Dimension table (value, effort, deps, risk, fit) with clear recommendation |
39| `next` | 1-3 prioritized features from gaps, specs pipeline, and maturity analysis |
40
41See [WORKFLOW.md](WORKFLOW.md) for detailed execution steps and output templates per mode.
42
43## Module Maturity Scale
44
45Use the shared vocabulary in [MATURITY_SCALE.md](../../references/MATURITY_SCALE.md).
46
47## Output Rules
48
49- **Default: conversational** — output goes to chat
50- **User-focused** — every recommendation ties back to user outcomes
51- **Grounded** — cite specific docs, gaps, or specs when making claims
52- **Honest** — flag unknowns and open questions rather than guessing
53
54## File Persistence
55
56After producing the analysis, ask the user:
57
58> **Save this analysis to `{output_dir}/requirements/{filename}.md`?**
59
60Where `{output_dir}` comes from `.arkhe.yaml` (default: `arkhe/roadmap`).
61
62| Mode | Filename Pattern |
63|------|-----------------|
64| `stories <feature>` | `{feature-slug}-stories.md` |
65| `prioritize` | `{YYYY-MM-DD}-priorities.md` |
66| `scope <feature>` | `scope-{feature-slug}.md` |
67| `validate` | `{YYYY-MM-DD}-validation.md` |
68| `needs` | `{YYYY-MM-DD}-needs.md` |
69| `compare <A> vs <B>` | `{a-slug}-vs-{b-slug}.md` |
70| `next` | `{YYYY-MM-DD}-next.md` |
71
72## Deep Mode (`--deep`)
73
74When `$ARGUMENTS` contains `--deep`, run the full multi-agent pipeline instead of conversational analysis. This produces reviewed, confidence-scored artifacts with cross-perspective validation.
75
76See [WORKFLOW.md](WORKFLOW.md) § Deep Pipeline for the 5-phase execution protocol.
77
78**Patterns applied**: Pipeline, Confession, Critic-Actor, Specification-First (for stories), Confidence-Gated Completion.
79
80## Lane Discipline
81
82See the PM section of [LANE_DISCIPLINE.md](../../references/LANE_DISCIPLINE.md). Stay in your lane.
83
84## References
85
86- [WORKFLOW.md](WORKFLOW.md) — Detailed discovery protocol and mode workflows
87- [EXAMPLES.md](EXAMPLES.md) — Usage examples across project types
88- [TROUBLESHOOTING.md](TROUBLESHOOTING.md) — Common issues and fixes
majiayu000