system-design-doc
Skill13 starsChanged 5 months agoMITView on GitHub
Captures the system context a PM needs for feasibility — affected components, dependencies on teams/systems, constraining NFRs, integration risks — feeding PRD §9-10 and the dev estimate. Use with the dev lead at estimation time, or when the user says "system design", "architecture constraints", "what does this touch", "технические зависимости", "системный дизайн". NOT a full engineering design doc.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Vishnu373/claude-skillstheir own version, first seen Nov 16, 2026
- lamxy/agent-prompt-rules-systemtheir own version, first seen Oct 20, 2026
- tizee/skillstheir own version, first seen Mar 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- lamxy/agent-prompt-rules-system★ 4same name
- tizee/skills★ 2same name
- Vishnu373/claude-skills★ 0same name
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 repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ambiguity-resolverSkill
- challengeSkill
- deep-thinkSkill
- design-critique-templateSkill
- experiment-designSkill
- ingestSkill
- interview-analysisSkill
- multi-source-signal-synthesiserSkill
- next-advisorSkill
- pipeline-stepsSkill
- post-launch-reviewSkill
- problem-structuringSkill
- product-requirements-docSkill
- setup-initiativeSkill
- solution-scoringSkill
- strategic-narrative-generatorSkill
- technical-spec-documentSkill
- tracking-and-funnelsSkill
- ui-pattern-librarySkill
- user-persona-builderSkill
- user-story-generatorSkill
- user-testingSkill
The file
Files
System Design (PM view)
Boundary: this skill = what the system looks like and what constrains the
initiative (feasibility input, PRD §9–10). What will be built for this
initiative belongs to technical-spec-document.
This is a conversation WITH the dev lead, not a document Claude invents. Claude structures; the dev lead supplies facts. Anything Claude infers without the dev lead is INFERRED — mark it and list it as an open question.
What to capture (in priority order)
- System context — which existing components/services does the solution touch? One list: component → what changes.
- Dependencies — teams, internal platforms, external vendors the
initiative needs. For each: owner + what exactly + lead time. These
become
dependencies[]in status.json (owner, deadline, blocks) — offer to create them immediately. - Constraining NFRs — load, latency, privacy/compliance, platform parity. Only the ones that could change the solution shape or the estimate; skip textbook lists.
- Risks and unknowns — the "we won't know until we open it" list; each unknown widens the estimate — ask the dev lead to size the widening.
- Integration points for tracking — where the analytics events (from
tracking-and-funnels) will be emitted; flag anything the solution makes unmeasurable.
Output
output/dev-estimate.md §Architecture (or PRD §9–10 directly): context
list, dependency table, constraining NFRs, risk register with estimate
impact.
Anti-patterns
- Infrastructure detail (servers, databases, configs) the PM neither needs nor can verify.
- Presenting Claude-guessed architecture as fact — without the dev lead everything here is INFERRED.
- NFR laundry lists — only constraints that change decisions.
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.

