product-plan
Define the full product vision — audience, positioning, features, roadmap, and UX direction — through a structured interview.
Skill by RubenGlez
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/rubenglez-product-plan
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/product-plan
What's inside
- Skill name
product-plan- Description
- Define the full product vision — audience, positioning, features, roadmap, and UX direction — through a structured interview. Use after ideate, or directly when the idea is already validated and you're ready to spec the product.
- License
- MIT
- Instructions
- 76 lines in SKILL.md · view on GitHub
Files (2)
- REFERENCE.md
- SKILL.md
SKILL.md (first lines)
# Product Plan ## Step 1: Read the project Before asking anything, gather all available context: **Ideation output** — read `.harness/product/idea.md` if it exists: - Extract: concept, problem, market landscape, competitor list, viability verdict - These questions are already answered — do not re-ask them in the interview **Existing product docs** — read `.harness/product/` for prior decisions to update rather than re-litigate **Codebase** — if code already exists: - Read README.md for stated goals and audience - Scan the feature surface: routes, screens, commands, or API endpoints - Check the roadmap or issue tracker if present (`gh issue list`) - Note what's implemented, what's stubbed, and what's conspicuously absent **Starting mid-flow on an existing project**: if code exists but `.harness/` is absent, treat this as step 2 — `/ideate` was skipped. Read the codebase and README to reconstruct what `idea.md` would have said, then proceed. Synthesize into a one-paragraph internal picture. Do not share this — use it to skip already-answered questions and form sharper hypotheses. ## Step 2: Interview Interview the user relentlessly — one question at a time. For every question, state a concrete recommendation or hypothesis first. Never ask a bare question. Lead with your position — "My read is X. Do you agree?" — so the user reacts to a specific claim. **Be a realist, not a cheerleader.** Surface the truth, not validation: name failure modes, push back on optimistic answers, make vague audiences concrete, call out weak moats. Work through these dimensions in order; skip any already answered. See [REFERENCE.md](REFERENCE.md) for detailed questions per dimension: 1. The idea 2. Target audience 3. Market and competition *(skip if idea.md covers it)* 4. Value and differentiation 5. Validation 6. Features 7. UX and design ## Step 3: Report After the interview, produce a report with these sections: - **Audience** — who it's for, who the early adopter is, why they care - **Value Proposition** — for whom, the key benefit, the core differentiator, why users switch (synthesize from dimensions 4 and 5) - **Market Positioning** — category, differentiation, competitive gap - **Competitive Analysis** — top 3–5 competitors, strengths, weaknesses - **Direction Assessment** — go / conditional go / no-go with 2–3 reasons - **Prioritized Feature Backlog** — must-have / should-have / nice-to-have - **UX and Design Direction** — core workflow, interaction model, design register - **Key Risks** — 2–3 assumptions most likely to be wrong and how to test them ## Step 4: Write docs ### Doctier bootstrap (once per repo) `.harness/` is tracked in git as age-encrypted blobs via doctier. If `.doctier.yml` exists at the repo root, skip this — the repo is already set up. If `.harness/` already exists but is gitignored (a pre-doctier project), follow the adoption recipe in the migrate-docs skill's REFERENCE.md instead. Otherwise, run the bootstrap in [../_shared/doctier-bootstrap.md](../_shared/doctier-bootstrap.md). ### Spawn the doc writer Spawn a subagent to write all product docs. Pass the full report as context — it cannot read the conversation. > **Runtime note:** if your runtime can't spawn a subagent (e.g. Codex), write the docs yourself in this session — see [../_shared/runtime-parallelism.md](../_shared/runtime-parallelism.md). Rules: all files go under `.harness/product/`; update existing rather than overwrite; omit sections with no source; never link to `.harness/` from public docs. Prefer updating existing docs over creating new ones: do not create a file whose content is only a few lines — fold thin sections into an existing doc instead. The subagent writes: `product.md`, `roadmap.md`, `competitors.md`, `ux.md` (if UI discussed), and `CONTEXT.md` (domain glossary). On a project that already has product docs, update in place and merge overlapping files rather than adding new ones. See [REFERENCE.md](REFERENCE.md) for templates. After the subagent finishes, confirm every file written. Refresh the doc index and commit — worktrees and future sessions only see committed `.harness/` content: ```bash doctier agents --write git add .harness AGENTS.md && git commit -m "docs: product plan" ``` Recommend: "Run /dev-plan to define the architecture and generate feature specs."
From RubenGlez/harness, MIT.
More from RubenGlez/harness
- 0.552score
metrics
RubenGlez
Measure traction and discoverability across all non-archived GitHub repos and their publications (npm, App Store, Play Store, web properties), judge each…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
prototype
RubenGlez
Build throwaway code to answer a specific design question before committing to an implementation approach.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
write-a-skill
RubenGlez
Create new harness skills with proper structure, progressive disclosure, and bundled resources.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
task
RubenGlez
Make a small change to a shipped product — a bug fix, behavior tweak, or micro-feature — as one verified slice, syncing the affected feature spec on the way…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
migrate-docs
RubenGlez
Discover all documentation in the repo, classify each file, transform content to match harness templates, and migrate everything to the correct location.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
next-step
RubenGlez
Recommends the next harness skill to use by inspecting the repo, docs, git state, and recent work.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
dev-plan
RubenGlez
Analyze product docs and the codebase to decide architecture, tech stack, and implementation approach, then generate a technical spec for every must-have…
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
qa
RubenGlez
Test implemented features against their acceptance criteria, fix simple failures, and write a QA report.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
update-docs
RubenGlez
Update all project documentation to reflect the current state of the codebase.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
implement
RubenGlez
Classify planned features as autonomous or human-approval-required, then implement the current phase as parallel vertical slices — one subagent per feature.
SkillBFreshness: B★ 1Claude Code +9 - 0.497score
address-cves
RubenGlez
Find and fix high and critical application dependency CVEs across all non-archived GitHub repositories available to the authenticated gh CLI user.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
evolve
RubenGlez
Define what to add, change, or extend on an existing product through a product-level interview, then update the harness docs and hand off to dev-plan.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 12, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/RubenGlez/harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from RubenGlez
- 0.552score
metrics
RubenGlez
Measure traction and discoverability across all non-archived GitHub repos and their publications (npm, App Store, Play Store, web properties), judge each…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
task
RubenGlez
Make a small change to a shipped product — a bug fix, behavior tweak, or micro-feature — as one verified slice, syncing the affected feature spec on the way…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
next-step
RubenGlez
Recommends the next harness skill to use by inspecting the repo, docs, git state, and recent work.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
migrate-docs
RubenGlez
Discover all documentation in the repo, classify each file, transform content to match harness templates, and migrate everything to the correct location.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
prototype
RubenGlez
Build throwaway code to answer a specific design question before committing to an implementation approach.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
write-a-skill
RubenGlez
Create new harness skills with proper structure, progressive disclosure, and bundled resources.
SkillBFreshness: B★ 1Claude Code +9
Cite this page
product-plan skill. Agent Mart. https://agentmart.dev/skills/rubenglez-product-plan (last updated 2026-10-24)