agentleFS
IvanGomezMartinezIvanGomezMartinez/MatStudyLab/.agents/skills/build/SKILL.md

build

Skill2 starsChanged 3 months agoMITView on GitHub

Scan import/ and catalog optical script bundles into codes/ incrementally.

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

12 rules. 0 are common, 4 are distinctive, and 8 are very specific to this project.

  • 0

    Common

    Most of the 143 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 8

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read LORE.md, AGENTS.md, docs/spec.md, and CONTEXT.md before acting.

    line 9
  2. Very specific:

    Read and execute .agents/skills/matstudylab-bootstrap/SKILL.md before any other step.

    line 15
  3. Distinctive:

    Do not proceed until bootstrap completes (skip, setup/update, or warn-and-continue).

    line 16
  4. Very specific:

    After Step 0, branch on the bootstrap outcome.

    line 22
  5. Very specific:

    If LORE.md is missing or lacks companion .md language / git workflow, ask the user and write answers to LORE.md from docs/templates/LORE.md.

    line 83
  6. Very specific:

    Run .agents/skills/grill-me/SKILL.md (→ /grilling) on the catalog plan: types, bundle names, 1:1 vs N:1, files to move, and what stays in …

    line 99
  7. Distinctive:

    Completion criterion: every bundle has a resolved homonym decision.

    line 118
  8. Very specific:

    If LORE git workflow is own-repo, propose a commit after user OK (catalog: <type>/<bundle>).

    line 137
  9. Very specific:

    Never modify codes/ without explicit user confirmation per bundle.

    line 143
  10. Very specific:

    Never delete from import/ except files cataloged in this session.

    line 144
  11. Distinctive:

    Never delete or overwrite measurement data outside the confirmed bundle folder move.

    line 145
  12. Distinctive:

    Never auto-install Node or run package managers for the user.

    line 146

“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

Onboard lab scripts from import/ into codes/<type>/<bundle>/ with user confirmation at each step. The only /build write path into codes/ is a confirmed catalog move — never edit existing catalog bundles in situ.

Read LORE.md, AGENTS.md, docs/spec.md, and CONTEXT.md before acting.

English is the default for HITL copy below. Localize only when LORE.md or a /build language choice says so.

Step 0 — Bootstrap (mandatory)

Read and execute .agents/skills/matstudylab-bootstrap/SKILL.md before any other step. Do not proceed until bootstrap completes (skip, setup/update, or warn-and-continue).

Completion criterion: bootstrap outcome identified (skip, setup/update OK, or warn-and-continue).

Step 1 — Skills HITL

After Step 0, branch on the bootstrap outcome. Canonical English strings live in .scratch/skills-auto-provisioning-v2/assets/prototype-node-gate-messages.md (Scenarios A–G). Prefer those exact texts.

Preference sidecar: .matstudylab/skills-pref.json (mode: auto | local-only, last_synced_at). Absence ⇒ treat as auto. Never auto-install Node.

Helper — write preference mode

Preserve last_synced_at unless the bootstrap script just stamped it. From repo root:

python3 - <<'PY'
from pathlib import Path
import sys
sys.path.insert(0, "scripts/lib")
from skills_bootstrap import load_pref, write_pref
path = Path(".matstudylab/skills-pref.json")
data = load_pref(path)
data["mode"] = "auto"  # or "local-only"
write_pref(path, data)
PY

Branch A — local-only (bootstrap: SKIPPED_LOCAL_ONLY)

Show Scenario A. Do not probe Node or sync.

ChoiceAction
Continue with /buildProceed to Step 2
Re-enable sync (switch to auto mode)Write mode: auto, re-run Step 0 bootstrap, then re-enter Step 1 on the new outcome

Branch B — Node/npx missing (bootstrap: NODE_MISSING)

Show Scenario B (three options).

ChoiceAction
Continue with vendored skills (this session only)Proceed to Step 2 (no pref write)
Continue and remember: do not sync (local-only)Write mode: local-only, then Step 2
Open setup — how to install Node and sync skillsDetect OS; print only the matching block from docs/agents/skills-node-os-checklist.md. Never auto-install. When the user has Node/npx, re-run Step 0; on SETUP_OK / UPDATE_OK go to Branch E

Branch C — Sync failed (bootstrap: SYNC_FAILED_CONTINUE)

Show Scenario C (include a short stderr / exit detail). Same three-option table as Branch B, except option 3 is Retry setup/update (re-run Step 0 when Node is present).

Branch D — Incomplete setup (no successful sync yet)

Trigger when preference is auto/absent and setup is still incomplete after Step 0: empty/missing skills map in skills-lock.json, or last_synced_at is null, and you did not just get SETUP_OK / UPDATE_OK / SKIPPED_FRESH. Prefer Branch B or C when those markers also apply.

Show Scenario D. Same three options; option 3 is Open setup — sync now (OS checklist if no Node; else re-run Step 0).

Branch E — Quiet success

OutcomeMessage
SETUP_OK / UPDATE_OKScenario G. Ensure mode: auto (script stamps last_synced_at). Continue to Step 2 — no menu.
SKIPPED_FRESHScenario E one-liner. Continue to Step 2 — no menu.

Completion criterion: HITL branch resolved — user choice applied (pref written when required), quiet success acknowledged, or setup path waiting on Node install / re-bootstrap; then proceed to Step 2 only when continuing /build this turn.

Step 2 — LORE onboarding (first run)

If LORE.md is missing or lacks companion .md language / git workflow, ask the user and write answers to LORE.md from docs/templates/LORE.md.

Completion criterion: companion language and git workflow are recorded (or user declined onboarding).

Step 3 — Scan import/

./scripts/build-import.sh scan

Recursively list bundle proposals grouped by folder under import/.

Completion criterion: the user sees proposed bundles and optical magnitude (<type>/) for each.

Step 4 — Grill-me (mandatory before any write)

Run .agents/skills/grill-me/SKILL.md (→ /grilling) on the catalog plan: types, bundle names, 1:1 vs N:1, files to move, and what stays in import/ for later sessions.

Do not write files until grill-me passes.

Completion criterion: user confirmed the catalog plan.

Step 5 — Homonym check

For each bundle:

./scripts/build-import.sh homonym <type> <bundle>
ResultAction
homonymAsk: skip, rename bundle, or route to /modify
availableProceed to catalog

Completion criterion: every bundle has a resolved homonym decision.

Step 6 — Catalog confirmed bundles

Move only user-confirmed bundles (directly to codes/, not via new/):

./scripts/build-import.sh catalog <type> <bundle> import/<path/to/folder>

Drafts a base companion .md from docs/templates/script-companion.md when missing.

New codes/<type>/ folders require user confirmation; append folder map + decision log rows to LORE.md.

Completion criterion: each confirmed bundle exists under codes/; only cataloged files were removed from import/.

Step 7 — Post-build handoff

  • Recommend /explain for priority scripts.
  • If LORE git workflow is own-repo, propose a commit after user OK (catalog: <type>/<bundle>).

Completion criterion: user knows recommended next commands.

Safety (non-negotiable)

  • Never modify codes/ without explicit user confirmation per bundle.
  • Never delete from import/ except files cataloged in this session.
  • Never delete or overwrite measurement data outside the confirmed bundle folder move.
  • Never auto-install Node or run package managers for the user; OS checklists are display-only.

Reference

  • Wayfinder spec: .scratch/matstudylab/issues/11-grilling-comando-build.md
  • Companion template: docs/templates/script-companion.md
  • Homonym + incremental rules: docs/spec.md (/build, US32–33)
  • HITL decisions: .scratch/skills-auto-provisioning-v2/issues/02-grilling-build-hitl-dialogue.md
  • Canonical English HITL copy: .scratch/skills-auto-provisioning-v2/assets/prototype-node-gate-messages.md
  • OS install checklists: docs/agents/skills-node-os-checklist.md
  • Manual HITL verification: docs/agents/build-skills-hitl-checklist.md

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.