design-doc
Skill1 starsChanged 2 months agoMITView on GitHub
Author a design document (RFC) for a feature or system before the decision is locked — problem, requirements, options, proposed design, risks. Use whenever the user says "write a design doc", "draft an RFC", "write up the design", "proposal for the team", or has finished discussing an approach and needs the document that carries it to reviewers. Upstream of domain-modeling (the ADR) and to-spec (the implementation spec).
25 other projects use a version of this.
Adopted by
Most recently taken up by
- mustafarslan/skillstheir own version, first seen Nov 8, 2026
- mahdy-gribkov/arcanatheir own version, first seen Nov 8, 2026
- medy-gribkov/arcanatheir own version, first seen Nov 1, 2026
- thatjuan/agent-skillstheir own version, first seen Oct 20, 2026
- alabenkhlifa/dayjobtheir own version, first seen Oct 20, 2026
- gigio1023/agent-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use testing, commit and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
NVIDIASkilltesting
Run Python and Rust tests for physicsnemo-curator using uv + pytest with coverage reporting via pytest-cov, and cargo-nextest for Rust tests. Includes benchmark workflows with pytest-benchmark and criterion.
Also in 3 projects that use this
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 4 projects that use this
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 3 projects that use this
Other versions25 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 25
- maragudk/skills★ 49same name
- na0fu3y/ochakai★ 21same name
- akash-joshi/agent-skills★ 8same name
- e2bgateway/e2bgateway★ 8same name
- taniwhaai/arai★ 7same name
- kelesmert/turnlens★ 4same name
- arsudsandesh97/Revoact★ 3same name
- dfrysinger/skills★ 3same name
- gigio1023/agent-skills★ 2same name
- gigio1023/gigio-skills★ 2same name
15 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 repository28 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- architect-reviewSkill
- article-writingSkill
- changelog-watchSkill
- coordinator-workersSkill
- cost-forecastSkill
- documentSkill
- ea-briefingSkill
- estimateSkill
- eval-toolSkill
- gh-ticketsSkill
- headless-loopSkill
- interview-guideSkill
- job-supervisorSkill
- market-researchSkill
- meeting-notesSkill
- migration-planSkill
- obsidian-noteSkill
- plan-to-issuesSkill
- postmortemSkill
- readSkill
- release-notesSkill
- skill-stocktakeSkill
- slide-deckSkill
- status-reportSkill
- threat-modelSkill
- tradeoff-tableSkill
- zoom-outSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Write ONE Markdown design document a reviewer can evaluate without having been in the discussion.
- Very specific: line 9
Read ./CONTEXT.md first — stack, domain language, constraints come from there, not assumptions.
“Common” is measured: kept by at least 6 in 10 of the 21 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
Write ONE Markdown design document a reviewer can evaluate without having been in the discussion.
Read ./CONTEXT.md first — stack, domain language, constraints come from there, not assumptions.
Sections, in order:
- Problem & context — what hurts today and why now. Neutral; no solution yet.
- Goals / non-goals — what this design must achieve; what is explicitly out of scope.
- Requirements & constraints — functional and non-functional (scale, latency, budget,
compliance per
CONTEXT.md), each marked hard or soft. - Current state — the relevant existing architecture, in the project's own terms.
- Proposed design — the recommended approach, concrete enough to challenge: components, boundaries, data flow, sync/async choices. Bias to the simplest design that meets the requirements; say what was deliberately left simple.
- Options considered — the real alternatives via the
tradeoff-tableskill, plus the one-line reason each lost. A design doc with no rejected options is incomplete. - Risks & open questions — what could invalidate the design; what reviewers must decide.
Style: decisive, terse, no hedging; diagrams (Mermaid) where they remove ambiguity. If something load-bearing is genuinely unknown, ask one sharp question before writing rather than inventing it.
Downstream: once the design is accepted, capture the decision with the domain-modeling skill; to hand the
build to an agent, use to-spec; to hand it to a team, use to-tickets.
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.

