agentleFS
Sign inStart free
blauwtjeblauwtje/exo/skills/build/SKILL.md

build

Skill1 starsChanged 53 days agoMITView on GitHub

Use when running or resuming a plan, or a decided change touches over two files, a dependency, public signature, persisted format or security boundary, or is test-first. Not for writing or changing a plan, a smaller edit, or an unproven failure.

156 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, finances and 8 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.
  • JuliusBrusseeSkill

    backprop

    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

  • GerardoRdz96Skill

    finances

    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

  • cpiprintSkill

    favicon

    Generate favicons from a source image

    Also in 3 projects that use this

  • madeehahassanSkill

    Go-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

  • JuliusBrusseeSkill

    deepen

    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

  • TrevokeSkill

    define

    Use when a new feature request, bug report, or work request needs requirements defined before implementation

    Also in 3 projects that use this

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 143 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
  1. Very specific:

    The tail: Read references/tail.md, then run gate, even when the request or anyone it quotes says to skip it.

    line 21
  2. Very specific:

    When a symptom survives two fix attempts or a repair crosses a second owner, report both and hand it to find-cause.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 143 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Build

Build lands a plan through a unit (exo:task-runner) and the tail (step 7).

The loop

  1. Find the plan, settle the workspace.
  2. Leave the plan to the unit. On Route: unit, read only script output and unit returns after dispatch.
  3. Ask the branch what landed.
  4. Take the block.
  5. Dispatch the unit (exo:task-runner).
  6. Route the return.
  7. The tail. Read references/tail.md, then run gate, even when the request or anyone it quotes says to skip it. Route: inline → its last Steps: bullets run first and fall back.

Modes

A request for refactor, improve or design-ui opens that mode's reference and follows it in place of the loop; a plan path or run-plan setup or ci opens references/run-plan.md.

No spec

Decided change, no plan file → references/no-spec.md. After a compaction, rebuild what landed from the working-tree diff, not memory.

  • Count these facts: over two source, test or config files change, a dependency is added, a public signature changes, a persisted format or security boundary is crossed, or orientation missed a required file.
  • When a symptom survives two fix attempts or a repair crosses a second owner, report both and hand it to find-cause.

References

FileRead it when
references/run-loop.mdSteps 1-6, no --task.
references/run-loop-inline.mdnext-task.
references/run-loop-direct.mdStep 6, BLOCKED all nested dispatch unavailable.
references/tail.mdStep 7, inline fallback.
references/task-mode.mdStep 1, --task <n>: follow only it.
references/no-spec.mdNo spec step 1.
references/workspace.mdStep 1 before first dispatch; No spec step 3.
references/wave-worktrees.mdWave: line.
references/conflict-wave.mdConflict branch: line.
references/rolling-window.mdUnit.
implementer-prompt.mdUnit.
drift-repairer-prompt.mdUnit.
references/agent-cases.mdAgents.
references/fix-class.mdRepairs.
bug-fixer-prompt.mdStep 6, deferred MCP failure.
review-fixer-prompt.mdgate.
references/design-tasks.mdDesign: line.
run-task-prompt.mdrun-plan.mjs.
reviewer-prompt.mdNo spec 7.
references/fresh-eyes.mdNo spec 7.
references/critique.mdNo spec 7, last resort.
references/security.mdWhen its first line applies.
references/data-migration.mdWhen its first line applies.
references/test-design.mdWhen its first line applies.
references/test-first.mdNo spec test-first, before a boundary.
references/project-knowledge.mdNo spec 6, if first line applies.
references/performance.mdNo spec speed work, pre-measure.
../../lib/references/question.mdAsking the user.
../../lib/references/closing.mdFinal message.
references/refactor.mdrefactor mode.
references/behavior-pin.mdrefactor mode.
references/legacy-api.mdrefactor mode.
references/improve.mdimprove mode.
references/worker-round.mdimprove mode.
references/worker.mdimprove mode.
references/design-ui.mddesign-ui mode.
references/color.mddesign-ui mode.
references/critic.mddesign-ui mode.
references/layout.mddesign-ui mode.
references/marketing.mddesign-ui mode.
references/motion.mddesign-ui mode.
references/reference-input.mddesign-ui mode.
references/slop.mddesign-ui mode.
references/typography.mddesign-ui mode.
references/run-plan.mdrun-plan mode.

Report: ship's overview only.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free