product
Skill3 starsChanged 7 months agoMITView on GitHub
Stage 1 orchestrator — guides Product Discovery: manifesto → requirements → architecture. Scans artifacts, skips completed steps, dispatches sub-skills in sequence.
14 other projects use a version of this.
Adopted by
Most recently taken up by
- Astatide1337/Skillstheir own version, first seen Nov 8, 2026
- PeterPartridge/CooperativeAICodingtheir own version, first seen Nov 8, 2026
- Mark-Life/agent-skillstheir own version, first seen Nov 6, 2026
- gabros20/product-skilltheir own version, first seen Nov 1, 2026
- malinskibeniamin/skillstheir own version, first seen Nov 1, 2026
- simscal/sapiens-dtjtheir own version, first seen Oct 20, 2026
Other versions14 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 14
- nitinjain999/platform-skills★ 71same name
- malinskibeniamin/skills★ 4same name
- Mark-Life/agent-skills★ 4same name
- alex-voloshin-dev/ai-skills★ 2same name
- PeterPartridge/CooperativeAICoding★ 2same name
- tikhomirovv/agents-knowledge★ 2same name
- Astatide1337/Skills★ 1same name
- donatassimkus/claude-ai-skills★ 1same name
- gabros20/product-skill★ 1same name
- LukeJMadden/Veltrix-skills★ 1same name
4 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- skills/setup/templates/AGENTS.mdAGENTS.md
- skills/setup/templates/CLAUDE.mdCLAUDE.md
- add-supervisorSkill
- architectureSkill
- core-loopSkill
- doSkill
- implementationSkill
- investigateSkill
- manifestoSkill
- planSkill
- qualitySkill
- requirementsSkill
- researchSkill
- reviewSkill
- setupSkill
- specificationSkill
- specSkill
- subagents-disciplineSkill
- tasksSkill
- updateSkill
- workflowSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
If the user provides $ARGUMENTS, analyze them for:
- Very specific: line 22
Manifesto: check for docs/MANIFESTO.md
- Very specific: line 23
PRD: check for docs/PRD.md or docs/prd/*.md — read for Status: APPROVED
- Very specific: line 24
Architecture: check for docs/*architecture*.md or docs/ARCHITECTURE.md — read for Status: APPROVED
- Very specific: line 46
Ask: "Do you have a manifesto, or would you like help creating one with /manifesto?"
- Distinctive: line 47
If manifesto exists → show path, proceed to next step
- Very specific: line 48
If user wants help → dispatch: Skill(skill="manifesto")
- Distinctive: line 49
If user wants to skip → warn this is optional but recommended, proceed </on-step>
- Distinctive: line 61
Wait for completion, then re-scan state.
“Common” is measured: kept by at least 6 in 10 of the 13 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Product (Stage 1 Orchestrator)
Guide the user through Stage 1 — Product Discovery. Sequences the atomic skills and tracks progress.
<on-init>
If the user provides $ARGUMENTS, analyze them for:
- `status` — show current stage state only
- A specific step name to jump to (e.g., `architecture`)
</on-init><on-state>
Scan the filesystem to determine Stage 1 state:- Manifesto: check for
docs/MANIFESTO.md - PRD: check for
docs/PRD.mdordocs/prd/*.md— read forStatus: APPROVED - Architecture: check for
docs/*architecture*.mdordocs/ARCHITECTURE.md— read forStatus: APPROVED
Display:
Stage 1 — Product Discovery
{check} Manifesto {path or "not found"}
{check} PRD {path} ({status})
{check} Architecture {path} ({status})Where {check} is:
[done]— artifact exists and is APPROVED[exists]— artifact exists but not yet APPROVED[missing]— not found[warning]— missing but a later step was already done</on-state>
<on-step name="manifesto">
**Manifesto** — Product vision, principles, governing laws.This is typically a manual step — the user writes it directly.
Ask: "Do you have a manifesto, or would you like help creating one with /manifesto?"
- If manifesto exists → show path, proceed to next step
- If user wants help → dispatch:
Skill(skill="manifesto") - If user wants to skip → warn this is optional but recommended, proceed
</on-step>
<on-step-skip if="manifesto_done">
Manifesto already exists at `{path}`. Moving to next step.
</on-step-skip><on-step name="requirements">
**PRD** — Product Requirements Document.Dispatch: Skill(skill="requirements")
Wait for completion, then re-scan state.
</on-step>
<on-step-skip if="requirements_done">
PRD already exists and is APPROVED at `{path}`. Moving to next step.
</on-step-skip><on-step name="architecture">
**Architecture** — High-level system design, tech stack, structural decisions.Dispatch: Skill(skill="architecture")
Wait for completion, then re-scan state.
</on-step>
<on-step-skip if="architecture_done">
Architecture already exists and is APPROVED at `{path}`. Moving to next step.
</on-step-skip><on-complete>
Re-scan and display final Stage 1 state.Stage 1 — Product Discovery: COMPLETE
[done] Manifesto {path}
[done] PRD {path} (APPROVED)
[done] Architecture {path} (APPROVED)</on-complete><on-next>
Stage 1 complete. Recommend proceeding to Stage 2 with `/specification` or `/plan` to define the first phase.
</on-next>Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

