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
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- lilly-builds/senior-engineer-modetheir own version, first seen Nov 8, 2026
- endqwerty/endstacktheir own version, first seen Nov 8, 2026
- DnsQueen/orcinus-skillstheir own version, first seen Nov 8, 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 versions156 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 156
- 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
146 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.
In this repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- acceptSkill
- ask-mattSkill
- claude-handoffSkill
- codebase-designSkill
- code-reviewSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- explainSkill
- git-guardrails-claude-codeSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- loop-meSkill
- matlab-performance-optimizerSkill
- matlabSkill
- matstudylab-bootstrapSkill
- migrate-to-shoehornSkill
- modifySkill
- newSkill
- prototypeSkill
- researchSkill
- resolving-merge-conflictsSkill
- scaffold-exercisesSkill
- setup-matt-pocock-skillsSkill
- setup-pre-commitSkill
- setup-ts-deep-modulesSkill
- tddSkill
- teachSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wait-whatSkill
- wayfinderSkill
- wizardSkill
- writing-beatsSkill
- writing-for-agentsSkill
- writing-fragmentsSkill
- writing-great-skillsSkill
- writing-shapeSkill
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
- Very specific: line 9
Read LORE.md, AGENTS.md, docs/spec.md, and CONTEXT.md before acting.
- Very specific: line 15
Read and execute .agents/skills/matstudylab-bootstrap/SKILL.md before any other step.
- Distinctive: line 16
Do not proceed until bootstrap completes (skip, setup/update, or warn-and-continue).
- Very specific: line 22
After Step 0, branch on the bootstrap outcome.
- Very specific: line 83
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.
- Very specific: line 99
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 …
- Distinctive: line 118
Completion criterion: every bundle has a resolved homonym decision.
- Very specific: line 137
If LORE git workflow is own-repo, propose a commit after user OK (catalog: <type>/<bundle>).
- Very specific: line 143
Never modify codes/ without explicit user confirmation per bundle.
- Very specific: line 144
Never delete from import/ except files cataloged in this session.
- Distinctive: line 145
Never delete or overwrite measurement data outside the confirmed bundle folder move.
- Distinctive: line 146
Never auto-install Node or run package managers for the user.
“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.
Files
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)
PYBranch A — local-only (bootstrap: SKIPPED_LOCAL_ONLY)
Show Scenario A. Do not probe Node or sync.
| Choice | Action |
| Continue with /build | Proceed 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).
| Choice | Action |
| 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 skills | Detect 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
| Outcome | Message |
SETUP_OK / UPDATE_OK | Scenario G. Ensure mode: auto (script stamps last_synced_at). Continue to Step 2 — no menu. |
SKIPPED_FRESH | Scenario 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 scanRecursively 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>| Result | Action |
homonym | Ask: skip, rename bundle, or route to /modify |
available | Proceed 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
/explainfor 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
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.

