build
Skill2 starsChanged 7 days agoMITView on GitHub
Run the dev-team pipeline on an idea — product brief (owner approves) → plan → design (owner approves, if the profile asks) → build → QA → review → design critique → local commit and summary. Resumes an unfinished build if there is one.
165 other projects use a version of this.
Adopted by
Most recently taken up by
- wald21x6-ops/builder-kittheir own version, first seen Nov 16, 2026
- 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
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 versions165 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 165
- FalkorDB/FalkorDB★ 11ksame 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
155 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
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 151 edited versions we read keep these.
2
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
- could be automatic: a setting could enforce it
- Very specific: line 20
If company/profile.md doesn't exist, tell the owner to run /dev-team:setup first and stop — unless they say to go ahead without one.
- Distinctive: line 31
Keep your own context lean: read plans, reports and diffs, not every file a builder touched.
- Distinctive: line 36
Never push, merge, tag, publish or deploy as part of this command.
“Common” is measured: kept by at least 6 in 10 of the 151 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
/dev-team:build
You (the main session) are the company's front desk and its delivery manager. You talk to the owner; the agents do the work. Idea: $ARGUMENTS
This command replaces brainstorming and planning workflows from other plugins (e.g. superpowers' brainstorming / writing-plans) for this run: the product brief is the design doc and the plan is the plan. Don't run both.
Project root: the folder this command was run in. Every company/ and design/ path means the folder there. Pass that absolute path to every agent you spawn. Never use a company/ folder from a parent project, even if a parent CLAUDE.md mentions one.
0. Unfinished work?
Look in company/briefs/*.md for any brief whose status: is draft, approved, building, testing or waiting-owner. If there are any, show each (name, status, next:) and ask the owner: resume one, or start the new idea? Resume a draft at step 3, anything else at step 4. Files with no status: frontmatter are notes, not briefs: skip them. A brief whose status isn't one of the statuses in manager.md (older free-text statuses): show it and ask the owner which status it is, then write that.
1. Profile
If company/profile.md doesn't exist, tell the owner to run /dev-team:setup first and stop — unless they say to go ahead without one.
2. Brief
Spawn dev-team:product with the idea, word for word, the project root, and any context from this conversation. Wait for it.
3. Approval gate
Show the owner the brief's scope, size, non-goals, premise answers, done-checks, owner checks and open questions in a few lines, with the file path. Ask them to approve, change, or stop. Do not continue until they approve. If they ask for changes (including the size), send them to the same product agent and repeat. On approval set status: approved and next:, and log it in company/briefs/<slug>/log.md. If they say stop, set status: stopped and log why.
4. Delivery — you are the manager
Load the ponytail skill if it's installed (the manager preloads it). Read ${CLAUDE_PLUGIN_ROOT}/agents/manager.md and follow it yourself, in this session, from "First" through "Finish". Don't spawn dev-team:manager for this: a subagent's run can end before the agents it started report back, which leaves fix rounds unverified. Here you can ask the owner at its gates and wait for every report.
Keep your own context lean: read plans, reports and diffs, not every file a builder touched.
5. Summary
Tell the owner in plain words: what was built; QA / review / design verdicts and the evidence behind each (ran it / read it / not verified); what isn't done; owner checks still open; decisions recorded; the local commit per repo. Check the summary against the actual files, diff and test output — agent reports are claims, not proof.
Never push, merge, tag, publish or deploy as part of this command; offer it as a next step, after the open owner checks.
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.

