agentleFS
MegapromptingMegaprompting/torque-loop/skills/build/SKILL.md

build

Skill10 starsChanged 4 months agoMITView on GitHub

Force artifact production — stop talking and make the thing. Use when a target is locked and something concrete must exist. Produces the smallest usable v0 (spec, prompt, checklist, test-suite, decision-record, code-patch, qa-ledger, or operating-procedure) with explicit holes and a 5-point working test.

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 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.
  • 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

  • synaptiaiSkill

    gate

    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

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 143 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When editing a repo, match the neighbors: Read adjacent files first.

    line 34
  2. Very specific:

    Build against the map: If /ratchet:map left an unknown-map artifact (.ratchet/unknowns-map.md), build against it — and when the code …

    line 43
  3. Very specific:

    Build-for-learn (probe mode): If the active task is a probe (a live kind:"probe" artifact — see templates/probe-card.md), you are building …

    line 54
  4. Very specific:

    Do not declare it done. The next move is /ratchet:attack — an unattacked artifact is a guess, not a deliverable.

    line 91

“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

/ratchet:build — make the thing

Analysis is not progress. This command exists to end deliberation and produce an artifact. The output is never a description of what you would build — it is the build.

Step 0 — Load state

ratchet status
ratchet snapshot repo

Artifact kind

Take the kind from the argument if given, else infer it from the objective:

spec · prompt · checklist · test-suite · decision-record · code-patch · qa-ledger · operating-procedure

Templates for records live in the plugin's templates/ directory — mirror their shape.

Procedure

  1. Build the smallest usable v0. The minimum a real user could use today. Cut every part that is not load-bearing for the locked proof-of-done. No gold-plating, no speculative generality.
  2. When editing a repo, match the neighbors. Read adjacent files first; mirror their idiom, naming, and comment density. New style is a defect.
  3. State the holes. List every gap, shortcut, and unverified claim explicitly. A named hole is honesty; a hidden one is a defect the auditor will find.
  4. Write a 5-point working test. Concrete pass/fail checks a stranger could run. If you cannot write the test, you do not yet understand the artifact — say so and narrow scope.

Build against the map. If /ratchet:map left an unknown-map artifact (.ratchet/unknowns-map.md), build against it — and when the code contradicts what the map assumed, do not silently absorb it. Record a deviation (templates/deviation-note.md) as a decision, openLoop, or defect, and add it to the map's Deviations during build section. The map is a living record through the build, not a pre-build formality.

Re-score on surprise. Two deviations — or one that reshapes the locked target — mean the aperture was scored too low. Re-run ratchet score aperture; if it now says Pre-build map: required, stop building and run /ratchet:map. Patching deeper into unmapped terrain is the confident-build-into-fog the dial exists to refuse.

Build-for-learn (probe mode). If the active task is a probe (a live kind:"probe" artifact — see templates/probe-card.md), you are building to learn, not to keep:

  • Build only the smallest artifact that produces the card's proof-of-learning; stay inside its allowed surfaces; stop at its stop condition.
  • The probe's completion is a map/state delta — a decision, assumption, open loop, or defect — never a code diff. Probe code existing is not implementation progress; do not claim it as such.
  • Then dispose: revert the code and ratchet retract <probe-id> --reason "disposed: …". Keeping probe code is a promotion — a fresh build-for-keep under the full proof/seam gates, never a default. Undisposed probes drain confidence and flag the cold-start scan.

For large or code-heavy artifacts, delegate to the ratchet-builder subagent.

Output contract

ARTIFACT: <title> (<kind>, v0)
<the artifact itself — inline, or a file path you wrote>
EXPLICIT HOLES:
- ...
5-POINT WORKING TEST:
1. ...
2. ...
3. ...
4. ...
5. ...

Serialize

ratchet artifact add '{"title":"<title>","kind":"<kind>","status":"v0","path":"<path or empty>","holes":["...","..."]}'
ratchet state append openLoops '{"text":"deviation: map said X, code revealed Y — needs user judgment","status":"open"}'   # only if the build diverged from the map
ratchet state set phase build

Do not declare it done. The next move is /ratchet:attack — an unattacked artifact is a guess, not a deliverable.

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.