build
Skill0 starsChanged 25 days agoMITView on GitHub
Turn the chosen direction into a working prototype inside the host repo: handoff to WORK.md, one task at a time with tests, and verification against the track's criteria. Use it after the direction is chosen, for the next task, or before a checkpoint, freeze or demo.
163 other projects use a version of this.
Adopted by
Most recently taken up by
- librosdeia/builder-method-claude-plugintheir own version, first seen Nov 15, 2026
- TJaenichen/claude-code-harnesstheir own version, first seen Nov 15, 2026
- ryannel/skillstheir own version, first seen Nov 15, 2026
- RohiRIK/skillstheir own version, first seen Nov 15, 2026
- stericishere/skillstheir own version, first seen Nov 15, 2026
- Soe-Reh/soes-skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use backprop, finances and 10 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.
JuliusBrusseeSkillbackprop
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Also in 4 projects that use this
GerardoRdz96Skillfinances
Use when Gera talks about his money — logging an expense ("I spent X on Y"), checking where he stands this pay-period, closing a period, planning debt payoff, onboarding his financial picture, or asking for budgeting/finance opinions. Servy's financial brain. Triggers — "I spent", "log this expense", "where am I this period", "close the period", "how's my budget", "debt plan", "should I pay off", "finances onboard", "/finances".
Also in 3 projects that use this
cpiprintSkillfavicon
Generate favicons from a source image
Also in 3 projects that use this
madeehahassanSkillGo-Live
Pre-launch checklist. Use before making any app public, sharing a link externally, or announcing a product launch. Adapts to Claude Code, claude.ai, and Cowork.
Also in 3 projects that use this
JuliusBrusseeSkilldeepen
Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent rewrites. Triggers when the user says "deepen this", "improve the design", "this module feels shallow", "pull complexity down", "use spare budget on the codebase", or invokes /ck:deepen. Leans on the codebase-design skill's deep-module vocabulary when present.
Also in 3 projects that use this
synaptiaiSkillgate
Create a BDSK review_gate artifact. Defines a checkpoint that controls whether generated output may proceed toward acceptance. Use when defining quality, security, or scope gates for execution plans.
Also in 5 projects that use this
Other versions163 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 163
- FalkorDB/FalkorDB★ 10ksame name
- microsoft/microsoft-ui-xaml★ 8.6ksame name
- NexaAI/nexa-sdk★ 8.5ksame name
- hathach/tinyusb★ 7.3ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- pytorch/TensorRT★ 3ksame name
- oxsecurity/megalinter★ 2.6ksame name
- iPlug2/iPlug2★ 2.4ksame name
153 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.
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 149 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
If the choice is not recorded, ask only which proposal is the base and what to import from the others.
- Distinctive: line 12
If the brief links a "Final direction" board, read it and its comments: it is the visual specification.
- Distinctive: line 20
Create WORK.md with: problem and scenario, direction, stack and patterns (one line, from the brief), data, non-goals, input/output …
- Very specific: line 31
Run the next ready task you own in WORK.md.
- Distinctive: line 39
Check only this track. Build the checklist from the acceptance criteria, scoring and penalties in the brief, then add: end to end on the …
“Common” is measured: kept by at least 6 in 10 of the 149 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
Build
Arguments: $ARGUMENTS (handoff, next or verify) Reply in the user's language. Read BRIEF.md and WORK.md if it exists.
handoff
If the choice is not recorded, ask only which proposal is the base and what to import from the others.
If the brief links a "Final direction" board, read it and its comments: it is the visual specification.
Inspect the host repo: commands, UI, auth, roles, tenancy, persistence, forms, document store, real providers.
The brief's "Stack and patterns" is a constraint: every task uses that stack and follows those patterns, so code
written by different people fits together. A deviation is a decision recorded in WORK.md. With an empty repo, the
first task scaffolds that stack; there are no host components to protect yet, so shadcn init is fine there.
The datasets in the brief's "Data" section are the demo's only data: their format is a contract, and loading them into
the app through the host's persistence (seed or fixture) is a task. Changing a dataset after the contract freeze is a
recorded decision, because boards, tests and deck depend on the same numbers.
Create WORK.md with: problem and scenario, direction, stack and patterns (one line, from the brief), data, non-goals, input/output contracts, integrations, authorization
boundaries, vertical tasks with one owner each (split a task that spans two owners), files per owner, acceptance
criteria taken from the track, status and evidence. Mark assumptions and blockers. Never assume host APIs that do not
exist: endpoints the track needs are new contracts, written in WORK.md and frozen at the contract freeze. Adapt the direction to the host, do not paste a parallel app.
Porting the board into the app with host components is the designer's task, accepted when the page matches the board.
Where the board and the host design system differ, keep the host components and carry the board's look in tokens scoped
to the new page; changing the global theme needs the team's OK. Record the choice.
Plan how to switch user and role for tests and demo (the host's demo login, or browser profiles): nobody bypasses
protections or writes cookies by hand. Commit WORK.md: it is the shared reference.
next
Run the next ready task you own in WORK.md. Read the code and tests, add a positive and a negative check, make the
smallest change through existing adapters and components, following the brief's stack and patterns (with shadcn: add
only after --dry-run and --diff, never init, apply or a preset change on existing components without the team's
OK; the scaffold task of a new repo is the exception), run real commands, update your rows in WORK.md with evidence and limits.
A task that touches a frozen contract: stop and record the decision first. When the task is verified, commit code and
WORK.md together, so the rest of the team starts from the real state.
verify
Check only this track. Build the checklist from the acceptance criteria, scoring and penalties in the brief, then add:
end to end on the real server; authorization and isolation between users, roles or tenants when the track has them;
error and empty states; the host test runner; caches, exports and public artifacts; no secrets in pages or logs;
no invented numbers in UI or narration: every number shown comes from a dataset in the brief or from the running app. Use the browser when available, never instead of tests.
UI: compare the integrated page with the chosen board and run impeccable's audit if it is installed. Do not fix other
people's files: add each problem to the task list in WORK.md, with its owner, so next picks it up.
Classify each requirement as verified, failed, not verified or not applicable, with evidence. Commit WORK.md.
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.

