Go Ai Native Sweep logo

Go Ai Native Sweep

Organization
vibevm
go-ai-native-sweep

Run the recurring AI-Native discipline sweep on this Go project — the seven-step floor first, then the health collector's ratchet items, weekly drift and judgment tiers. Use daily or several times a day on an active tree; any single item is a safe stop.

Overview

Publishervibevm
Repositoryvibevm
Skill namego-ai-native-sweep
Stars
285
Forks
83
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by vibevm on GitHub. Read the source before you install it.

Installation

Install the Go Ai Native Sweep AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.ai-native/go-ai-native-lang/v1.0.0/vibevm/vibespecs/skills/go-ai-native-sweep
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vibevm/vibevm.git /tmp/vibevm
mkdir -p .claude/skills
cp -r /tmp/vibevm/vibevm/vibepacks/org.vibevm.ai-native/go-ai-native-lang/v1.0.0/vibevm/vibespecs/skills/go-ai-native-sweep .claude/skills/go-ai-native-sweep
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Go Ai Native Sweep in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Go Ai Native Sweep on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Go Ai Native Sweep is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

The discipline sweep (Go stack) {#root}

@fact:RUNNING-THE-STANDING-SWEEP You are running the standing sweep from the Discipline's Sweep Playbook (spec://org.vibevm.ai-native/core-ai-native/04-SWEEP-PLAYBOOK — the shipped copy is at vibedeps/flow-core-ai-native/<version>/spec/04-SWEEP-PLAYBOOK.md; read it once per session if you have not). @status:impl/done

@fact:two-truths-lead The two truths: @status:impl/done

  • @fact:TRUTH-GATES-ARE-THE-FLOOR the gates are the floor, the sweep is the ceiling, @status:impl/done
  • @fact:TRUTH-GATE-IS-TRUTH and the gate is truth, the collector is a guide. @status:impl/done

@fact:NEVER-SWEEP-ON-A-RED-TREE Never sweep on a red tree. @status:impl/done

@fact:ACT-ON-COLLECTOR-FACTS Act on collector facts, never on memory. @status:impl/done

@fact:ALL-COMMANDS-ARE-THE-SHIPPED-TOOLCHAIN All commands below are the shipped toolchain. @status:impl/done

@fact:IF-NOT-ON-PATH-INSTALL-OR-RUN-IN-PLACE If go-ai-native is not on PATH, either install it once — cargo install --path vibedeps/<stack-slot>/crates/go-ai-native-cli — or run it in place: cargo run --manifest-path vibedeps/<stack-slot>/Cargo.toml -p go-ai-native-cli --bin go-ai-native -- <args>. @status:impl/done

Tier 0 — the hard floor (ALWAYS first) {#tier-zero}

sh
go-ai-native floor

@fact:FLOOR-HAS-SEVEN-STEPS Seven steps: gofmt → go vet → go test → staticcheck+exhaustive → conform → specmap → test-gate. @status:impl/done

@fact:RED-FLOOR-ADMITS-ONLY-GREENING-WORK Red? The only legal work is making it green — fix, do not proceed. @status:impl/done

@fact:CHECK-THE-PRINTED-POLICY-LINES Check the printed policy lines: a NO conform.toml — topology default in force line means the project is not bootstrapped (go-ai-native init) and any green under it is vacuous, and every DISABLED by policy line is a standing decision to re-question weekly — a floor that shrank quietly is the failure mode this line exists to catch. @status:impl/done

Tier 1 — the ratchet (every run) {#tier-one}

sh
go-ai-native health

@fact:READ-THE-HEALTH-SUMMARY Read the summary (the JSON at discipline/health/latest-go.json is the work-list; its git diff is the trend). @status:impl/done

@fact:take-cheapest-wins-lead Take one or two cheapest wins: @status:impl/done

  1. @fact:RATCHET-DANGER-BAND-FILES danger-band files — split any file at the top of the [540,600) band before an edit trips the 600 budget. Go packages are natively multi-file: move a cohesive slice into a sibling file of the SAME package (GUIDE §15 — the cheapest split of the three stacks); item-level //spec: tags move with their items. @status:impl/done
  2. @fact:RATCHET-SUPPRESSION-CENSUS suppression census — every reasonless //lint:ignore / //exhaustive:ignore is unrecorded testimony: add the reason or fix the underlying finding. A t.Skip on a known-failing test moves to discipline/registry/tests-baseline.json the day it is found (GUIDE §10 — Go has no in-source xfail twin; the registry carries full weight). @status:impl/done
  3. @fact:RATCHET-EXAMPLE-COVERAGE example coverage — exported seam items without an Example are retrieval gaps; document the highest-traffic seam first (the four Example idioms, GUIDE §15). @status:impl/done
  4. @fact:RATCHET-ORPHAN-BACKLOG orphan backlog — untagged exported identifiers the ratchet will block on: tag the item (//spec:implements …), //spec:scope its package (doc.go), or unexport it. @status:impl/done
  5. @fact:RATCHET-CENSUS-REGRESSIONS census regressions — go-ai-native health's printed ban census {N} reasoned / {M} unreasoned (and ban_census in the snapshot): every go_unsafe fact without a //spec:deviates reason counts unreasoned. The kinds behind the count are init_decl, blank_import, ambient_call, naked_go, error_string_match and seam_error_missing_req; the collector reports one project-wide total, not a per-kind or per-package split, so compare the figure against the previous run rather than expecting a breakdown. Drain immediately; restructure beats testify. Outside the gate they are the adoption backlog: flip a package into [go] gated only after it drains to zero. @status:impl/done

Tier 2 — drift (weekly) {#tier-two}

  • @fact:DRIFT-TRIPWIRE go-ai-native tripwire --base origin/main — re-disposition every touched-and-open debt entry; file new deficiencies into discipline/registry/debt.json, never leave them as prose. @status:impl/done
  • @fact:DRIFT-DOC-CODE Doc/code drift: WAL freshness (if the project keeps one — see 06-WAL-CONVENTION), architecture docs vs the real package layout, roadmap staleness. File stale-doc debt. @status:impl/done
  • @fact:DRIFT-MARKER-CENSUS Marker census: rg -n 'TODO|FIXME|REVIEW|XXX|HACK' over the source roots — graduate load-bearing markers into the registries, delete trivial ones. @status:impl/done
  • @fact:DRIFT-GOLDEN-TRANSCRIPTS Golden transcripts (discipline/golden/, testdata/ goldens): must fail loudly, re-captured deliberately, never auto-updated — the -update flag never runs in CI. @status:impl/done

Tier 3 — deep judgment (weekly) {#tier-three}

@fact:WALK-THE-WISH-RULES Walk the WISH rules over the week's diff (typed seams, cell isolation and oracles, goroutine ownership, uniformity, contract-first ordering, lying godoc, closed-vocabulary naming — GUIDE §2–§9). @status:impl/done

@fact:CAMPAIGN-SIZED-BACKLOG-BECOMES-A-RAID If a Tier-1 backlog has grown campaign-sized, plan a raid instead: 03-RAID-PLAYBOOK + 05-CAMPAIGN-FORM. @status:impl/done

Closing a sweep {#closing-a-sweep}

@fact:TOPIC-GROUPED-COMMITS Topic-grouped commits, one logical unit each, citing the sweep item. @status:impl/done

@fact:COMMIT-THE-REFRESHED-HEALTH-JSON Commit the refreshed discipline/health/latest-go.json in the same run. @status:impl/done

@fact:RESUME-POINTER Resume pointer: with a WAL — bump its standing line at any milestone move; without — the closing commit message carries the summary (floor state, items taken, next candidate). @status:impl/done

@fact:NEVER-LEAVE-STATE-ONLY-IN-THE-CONVERSATION Never leave the sweep's state only in this conversation. @status:impl/done

The generation-time assistant (before you edit, not instead of the floor) {#generation-time-assistant}

@fact:STACK-SHIPS-AN-AGENTIC-TYPE-ORACLE The stack ships an agentic type oracle. @status:impl/done

@fact:check-the-hypothetical-content-lead Before writing a nontrivial .go edit, check the HYPOTHETICAL content instead of paying a red floor iteration: @status:impl/done

sh
vibe bin exec go-ai-native-tcg -- validate internal/cells/<cell>/<file>.go \
    --content-from - --root .   # the edit on stdin; exit 1 = would fail

@fact:MCP-ALTERNATIVE or, when the vibevm MCP server is mounted, call tcg_validate with language: "go" and the content argument (plus tcg_scope / tcg_complete / tcg_type for in-scope symbols, type-valid completions, and quick info). @status:impl/done

@fact:RESPONSES-CARRY-THE-SAME-CONFORM-FINDINGS Responses carry the SAME conform findings as the gate, flagged baselined or new, with guide-citing advice — a new finding in the answer means the floor WILL go red if you write that edit. @status:impl/done

@fact:ORACLE-PREREQUISITES Prerequisites: go ≥ 1.24 + gopls (go install golang.org/x/tools/gopls@latest — a stack obligation). @status:impl/done

@fact:ORACLE-HONESTY Honesty: gopls stands on go/types, the reference implementation of the spec — tighter than rust-analyzer↔rustc, still not the compiler; the floor stays the truth (TCG-ORACLE-GO §5). @status:impl/done

Frequently asked questions

What does the Go Ai Native Sweep AI skill do?

Run the recurring AI-Native discipline sweep on this Go project — the seven-step floor first, then the health collector's ratchet items, weekly drift and judgment tiers. Use daily or several times a day on an active tree; any single item is a safe stop.

Why use Go Ai Native Sweep on TypingMind?

Because you install it once and use it with any model. Go Ai Native Sweep is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Go Ai Native Sweep in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vibevm/vibevm/tree/main/vibevm/vibepacks/org.vibevm.ai-native/go-ai-native-lang/v1.0.0/vibevm/vibespecs/skills/go-ai-native-sweep. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Go Ai Native Sweep?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Go Ai Native Sweep?

As many as you like. As long as a model supports skills, you can use Go Ai Native Sweep with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Go Ai Native Sweep AI skill free?

It is published on GitHub by vibevm. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇