design
Skill2 starsChanged 30 days agoMITView on GitHub
Settle how a specified work item will be built before any code is written. Writes the modules, their interfaces and how each fails, each choice with its reason and the smaller option, the slices in order, the checks beyond this machine and what is cut if time is short into the item's design file.
197 other projects use a version of this.
Adopted by
Most recently taken up by
- dialog-db/dialog-dbtheir own version, first seen Nov 9, 2026
- BermanRoman/promt-seo-geotheir own version, first seen Nov 8, 2026
- anorth/agent-skillstheir own version, first seen Nov 8, 2026
- gspencergoog/skillstheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- Integralist/agent-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use banner-design, ui-styling and 9 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.
seikaikyoSkillbanner-design
Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.
Also in 38 projects that use this
MicrosoftSkillui-styling
Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.
Also in 39 projects that use this
seikaikyoSkillbrand
Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.
Also in 43 projects that use this
mayankjain1815-commitsSkillinfra-audit
Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.
Also in 3 projects that use this
JetBrainsSkillslides
Create and edit presentation slide decks (`.pptx`) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.
Also in 42 projects that use this
AnthropicSkilldesign-system
Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system.
Also in 49 projects that use this
Other versions197 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 197
- nextlevelbuilder/ui-ux-pro-max-skill★ 147ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- tokio-rs/toasty★ 3.3ksame name
- PaulWoitaschek/Voice★ 3.3ksame name
- joye61/pic-smaller★ 2.9ksame name
- oxsecurity/megalinter★ 2.6ksame name
- Infisical/agent-vault★ 2.5ksame name
- static-web-server/static-web-server★ 2.4ksame name
- SethGammon/Citadel★ 927same name
- Ohh-889/skyroc-admin★ 795same name
187 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 repository7 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- checkpointSkill
- implementSkill
- onboardSkill
- prepSkill
- researchSkill
- standardsSkill
The file
Files
The work item: $ARGUMENTS
Write the design of a work item that has a spec, before its code is written, or revise the design when a build has shown it wrong. The spec says what is built and why. The design says how, in the repos it touches, and in what order. A small item needs none: /context-central:implement <item> builds from the spec alone.
Run context-central draft <path>... before a file of the map is read, edited, written or handed to an agent. A path is counted from the map's folder, or is an absolute path the plugin printed. For each it prints the absolute path of the file to use: the map's own, or in a git work tree whose map is in the main checkout a draft in the work tree, which starts as a copy of the map's file where the map has one. A file is in the work tree only once it has been drafted: where one is not there, draft it before saying that the map lacks it. context-central take puts the drafts into the map and removes them from the work tree: run it where a step says so and before a command that reads those files from the map, and after it run context-central draft on a file again before it is read or edited. It prints took <path> for each draft it took and kept <path>: <why> for one it left. A kept line that names a file to compare with means the map's file is not the one the draft was made from: read that file where it stands, with no draft of it, bring into the draft what it has and the draft lacks, then run context-central take --over <path>. A closing answer names a file by its place in the map, never by a draft's path, and a draft still kept goes under Needs a fix with its reason.
1. Load the item
Run context-central resolve <item> --absolute. Where it answers no context map found, no map covers this folder yet: run context-central init --plain --dry-run, show the person the lines it prints and ask once whether to make that plain map. Only a yes makes it: on a yes, run context-central init --plain and start this step again. On a no, stop and say that /context-central:onboard sets a map up. If either command refuses, stop and say what it said. Otherwise the item exists only when the first line reads Context for work item <item>:; any other answer is a near match, so stop and say the item was not found. In a map this step has just made, that is every item: say that /context-central:prep <item> makes the item and writes its spec. Read the state file, the SPEC.md beside it and the code map note, when the state file names one. With no spec, stop and suggest /context-central:prep <item>. When DESIGN.md is already there, this is a revision: read it, keep what still holds, change it where it stands, and mark a slice that is already built as built. Where Done in the state file holds lines of the form Built at <short commit>: <slice>, a build with no design made them: mark those slices as built in the design, with those commits.
Run context-central work adopt <item> before anything is written to the item. It gives an item kept as a note of its own a state file beside that note and leaves the note as it is; for an item that has a state file it changes nothing and says so. Never pass --all, and never write to the older note. If the command refuses, write nothing to the item: stop and say what it said. When it adopted the item, say so in step 5.
2. Load the standards
Run context-central config --get repos, then context-central standards <repo> for each repo the work touches. The repos are the ones the code map is headed with. With no code map, ask the person which repos the work touches. Read each standards file, the Design part first, and the map's note of each of those repos, repos/<repo>.md, where there is one: it holds the repo's traps. A standards note names the commit its lines were read at: where a file a rule cites has changed since, say so. Where a repo has none recorded, the design rests on the instruction files and on what the code already does, and says so. Where the command answers no repo "<repo>" in this estate, read the repos it lists: where one is this repo under another spelling, run the command again with that name. Otherwise the map does not register the repo: the design rests on the same there, and the repo's folder is the checkout that holds its code, which is the one the session is in or else one the person is asked for.
3. Read the code the design will meet
Delegate bulk reading to the context-central:reader agent. Give it each repo's folder, which is the root that context-central standards <repo> --json gives: the work tree, where the session is in a git work tree of that repo. For a repo the map does not register it is the folder settled in step 2. Give it the anchors of the code map, which are counted from the repo's root, and the question each one answers. With no code map, its first question is where the modules the spec names live. Read for what is already there to build on: the modules the change meets, their interfaces, how a neighbouring feature of the same shape was built, where its tests sit, and, for each interface whose failures rest on a dependency, that dependency's source at the version the repo pins, or a run of it.
Then, for each repo whose context-central standards <repo> printed - design: <skill> under Step skills for repo <repo>: in step 2, invoke that skill with design and the item as its arguments, and write what it returns into the parts of step 4. Where that skill cannot be found or cannot be invoked, say so under Needs a fix and go on without it.
4. Write the design
Save DESIGN.md beside the spec, headed with each repo, under the name the map registers it by where it does, its commit (git rev-parse --short HEAD, run in that repo's folder) and the date, with these seven parts in this order:
- Shape: the modules that change and the ones that are new, what each is for, and what may call what.
- Interfaces: each new or changed interface as it will be written in its repo, with what it takes, what it returns and how it fails on the failing inputs: the empty, the largest, the repeated and the failing case, and for a call that leaves the process the unreachable, the slow and the refused. A failure that rests on a dependency is written as that dependency's source at the version the repo pins, or a run of it, shows; what neither shows goes under Checks beyond this machine.
- Choices: each choice a bullet of its own in bold, with lines nested under it, one label to a line:
- Why:its reason and the rule in the standards it follows (as the standards file'spath:line),- Turned down:the option turned down, and- Smaller:the smaller option weighed, ornone. A choice that departs from a rule says so and why on itsWhy:line. Where the smaller option is turned down for now,- Not now: <why>and- Revisit when: <trigger>follow it. - Slices: the order of the build. Each slice is one behaviour through every layer it touches, in the one repo it names, with the test seam of the spec it starts from, the Interfaces headings it builds and the seams it covers. Every test seam of the spec is either started from by a slice, named under the slice that covers it, or named as not covered with the reason. A built slice ends with one line,
Built at <short commit>. - Checks beyond this machine: what the design assumes and only a system this machine cannot reach can show, each run once by hand before the work is switched on anywhere shared, or
none. - If time is short: the order in which the work is cut, and what is never cut, or
none. - Anchors:
path:line, counted from the root of the repo it names, for each place the build starts from or must not break.
The design names files and lines, which the spec does not, so it carries the commit it was written at. It adds no requirement: something the spec does not ask for goes back to the person as a question, not into the design. Every requirement of the spec lands in at least one slice. A seam with no slice and no reason is a question too.
5. Show it
Link the design from "Where the detail lives" in the state file, as [DESIGN.md](DESIGN.md), unless the link is there, and rewrite "Where it stands" and "Next" to say the item is designed and how much of it is built, keeping what a build wrote there about its branch and about a slice left uncommitted. Run context-central take. Then close in this shape, where a line in angle brackets is a kind of point, given once for each there is and left out where there is none:
<one line saying the item is designed, and how much of it is built>
**Needs a fix**
- <a point where the design could not follow the spec>
- **Recommended:** <what would fix it, where the run found it>.
- <a rule whose cited file has changed since the rule was read>
- <a draft still kept, with its reason>
**Yours to decide**
- <a point where the design departs from the standards, and why>
- **Recommended:** <the answer, and why>.
- <a question the spec does not answer>
- **Recommended:** <the answer, and why>.
- <a repo the map does not register, whose design rests on its own files>
- **Recommended:** name it under `repos` in the map's `estate.json`, with its `path` where its folder is not the estate root's folder of that name, then `/context-central:standards <repo>`.
**Fine as it is**
- <the slices in their order, in short, with the ones already built>
- <a choice, in short>
- <the adoption, where there was one>
**Not known**
- <a check beyond this machine>
Design: <its path>. Next: <what holds the build back, where something does: first a point where the design could not follow the spec, then a question the spec does not answer; else in a fresh session `/context-central:implement <item>`; or a fresh session alone where every slice is built>.The groups come in that order, and a group with no point is left out. Inside a group what matters most comes first. A point is one thing in one sentence: two things that could be acted on apart are two points. A point's recommendation is the first line under it, never on the point's own line, and a point under Needs a fix has one wherever the run found what would fix it. The parts of one thing go under it after that. A group shows five points at most, each with all its parts. Where it holds more, one more line follows the five: and <N> more in <file>, naming the one file that holds all of the rest, or, where no one file does, and <N> more: <the rest, in short>. Nothing that asks something of the person goes outside its group, and nothing is said before the first line or after the last. The person approves by starting the build.
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.

