TypingMindTypingMindThe best frontend for AI
Mstar Artifacts logo

Mstar Artifacts

Community
btspoony
mstar-artifacts

Plan artifacts: main plans, durable review summaries, QC/QA bundles, workflow state/config/progress/evidence, issue capture, residual severity. Read when authoring or mapping them.

Overview

Publisherbtspoony
Repositorymstar-harness
Skill namemstar-artifacts
Stars
67
Forks
4
Bundled files
6
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Mstar Artifacts 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/btspoony/mstar-harness/tree/main/skills/mstar-artifacts
  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/btspoony/mstar-harness.git /tmp/mstar-harness
mkdir -p .claude/skills
cp -r /tmp/mstar-harness/skills/mstar-artifacts .claude/skills/mstar-artifacts
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mstar Artifacts 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 Mstar Artifacts 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 Mstar Artifacts 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.

Load order

Before first Read of this skill: Read mstar-harness-core (SKILL.md), and mstar-conventions when path symbols matter. Git branch / worktree / QC checkout → mstar-branch-worktree. On conflict, mstar-harness-core wins.

Scope (plan directory artifacts)

TopicSee
Main plan, review bundle naming, durable summaries, QC waves, residual and plan index orderreferences/plan-files-and-reports.md
Plan template (Global Constraints, Interfaces)templates/plan.main.md
knowledge / iterations / specs boundaries and indexesreferences/knowledge-and-designs.md
ACTIVE execution rows, coordinator configuration/progress/completion and CAS, issue capture, residual severity/lifecyclereferences/status-and-residuals.md
Plan-level workflow lifecycle: delivery-kind declaration, stages, evidence contracts, engine seamsreferences/plan-workflow-lifecycle-contract.md (closing amendment File-route retirement is the live route)
Open-issue rollup (read-only)mstar status tech-debt (issue-store rollup; see references/status-and-residuals.md)

Out of scope: branch and QC/QA checkout alignment → mstar-branch-worktree; leaf QC checklist and verdict → mstar-roles/references/qc-specialist/; PM QC orchestration → mstar-review-qc; {HARNESS_DIR} discovery and init → mstar-conventions.

Execution authority, migration sources, and open residual (summary)

  • ACTIVE root register: {HARNESS_DIR}/store.db (execution_registry + execution_meta.root_updated_at), read through mstar status validate (no path; a path is refused). The PM-facing close caller is post-merge mstar status workflow-close --workflow <id> — one store transaction writes the terminal workflow state and unregisters the workflow (procedure → mstar-iteration/references/phase-6-post-merge-close.md §6.1–§6.2; route semantics → the lifecycle contract's File-route retirement amendment).
  • ACTIVE workflow / plan state: execution_workflows, execution_plans, workflow-wide execution_integration_leases, coordinator execution_sessions and registered execution_inputs in the store; read through mstar plan show / mstar status validate. Rows contain ordinary source metadata/configuration/progress/completion; per-row execution leases are removed. Main/control is Git-derived.
  • Migration sources / retained history: read-only root/snapshot/session inputs; mstar store upgrade preserves original execution-source bytes and standalone mstar migrate staging is retired. Historical shapes → mstar-engine-legacy references/migration-source-shapes.md (no execution route or live writer).
  • Persist surface: the user-facing persist family and engine ArtifactKind accept review and json only. No internal status/snapshot file writer or runtime file-state fallback remains.
  • Project registers: migration history only; shapes/provenance → mstar-engine-legacy references/migration-source-shapes.md. Open items are issues in {HARNESS_DIR}/store.db → mstar-project-governance「Issue capture」.
  • Canonical: capture confirmed findings as issues (plan-linked mstar plan issue-add, unscoped mstar issue add; recurrence appends an occurrence); the register is not a write target. Legacy execution imports use mstar store upgrade; project register import uses the separate reviewed mstar store migrate flow. Never dual-write.

Engine check (when available): run mstar status validate (ACTIVE authority and tokens; no path argument). On fail -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.

  • Fail-loud handoff: capture validates input at the domain boundary and refuses malformed submissions (nothing written) → references/status-and-residuals.md (“Fail-loud handoff contract”); historical document validation → mstar-engine-legacy references/migration-source-shapes.md.

  • Lifecycle: an issue is open until a §4 closure authority retires it (resolved / waived / duplicate / superseded); current machine severity and issue-disposition semantics → references/status-and-residuals.md; historical closure shapes → mstar-engine-legacy references/migration-source-shapes.md.

  • Findings cleanup: coordinator prepare records zero-residual | allow-residual, default allow-residual. Leaf Assignments mirror the effective mode for evidence duties, not admission sealing → references/status-and-residuals.md.

Engine check (when available): run mstar status findings-cleanup <plan-id> [--mode zero-residual|allow-residual] (or import findingsCleanupGate from @mstar-harness/engine in a host hook) to enforce the Findings cleanup mode above against the open issues linked to the plan in {HARNESS_DIR}/store.db. On fail -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.

  • {WORKFLOW_DIR}/<id>/notes.jsonl: plain append-only runtime notes, not accepted-operation authority; duplicate IDs/submissions append again. Historical plan-row arrays stay read-only. Append/read semantics → references/status-and-residuals.md; mstar status tech-debt reads open issues in the store.
  • Iteration safety: source metadata supplies checkout scope; atomic coordinator transactions/CAS protect state, while workflow-wide integration merge exclusion protects real serial merges (execution_integration_leases). Fields → references/status-and-residuals.md; procedure → mstar-iteration/references/phase-2-worktree-lease.md.

Engine check: mstar worktree check is the one engine-enforced checkout command (per-plan L1, workflow --entry, and L2), including integration merge-lease state. It is an engine-enforced subset, not a mutation substitute, a per-row admission ceremony, or clearance of the full pre-dispatch checklist.

Current field semantics, severity mapping, findings cleanup and issue closure → references/status-and-residuals.md; migration-source shapes → mstar-engine-legacy references/migration-source-shapes.md.

Templates (this skill): templates/plan.main.md only (templates/README.md). Bootstrap is mstar harness scaffold then mstar store init; there is no empty status template.

Workflow

Write the main plan under {PLAN_DIR} → primary coordinator advances its explicitly selected rows through ordinary domain operations → raw review bundle and durable summaries → capture confirmed findings as linked issues → direct complete with QC/QA and declared-route proof → the workflow's outer delivery/close obligations. ACTIVE identity/session/token defaults may be derived when unambiguous; explicit constraints still validate. Registration/unregistration stays workflow-owned on the ACTIVE store route (lifecycle contract, File-route retirement amendment).

Decision Rules

  • Residual severity is the machine-field SSOT (references/status-and-residuals.md); capture each new finding as an issue (plan-scoped mstar plan issue-add, otherwise mstar issue add; recurrence appends an occurrence). Historical files are read-only, never dual-write targets → mstar-engine-legacy references/migration-source-shapes.md.
  • Findings cleanup: allow-residual 默认（迭代 Phase 2）：open issue 先捕获（计划链接）再披露（清单 + severity + 跟踪位置；close 面另含 blocker-defer 标记）；unresolved critical 仍阻断 Approve；zero-residual 为显式 opt-in —— 细则 → references/status-and-residuals.md「Findings cleanup modes」。
  • 捕获前必须过 engine 域校验（fail-loud handoff）；迁移 register 文档过 validateResidual / validateProjectRegister；malformed → reject + rewrite。
  • Only domain writers mutate rows/issues: the ACTIVE coordinator contract is the only execution route. Validators never substitute for a write. Do not hand-write root status.json or workflow snapshots; those files are migration sources / retained history. The user-facing persist family is review / json only. Session references are lookups and tokens are CAS constraints, not bearer credentials; neither goes into a leaf Assignment.

Evidence

正确结果 = 可复核产物链：{SDD_DIR}/review/ 审查 bundle 落盘 + 主 plan 的 durable gate summary + store 执行行（mstar plan show）+ issue 生命周期（捕获 → §4 关闭权威关闭，mstar issue list 可复核）。拒绝「仅对话声称」。

References

  • references/plan-files-and-reports.md — 主 plan / review bundle 命名、QC 波次、durable summaries
  • references/status-and-residuals.md — ACTIVE execution fields, coordinator configuration/progress/completion, issue capture and current severity/lifecycle; migration-source shapes live in mstar-engine-legacy references/migration-source-shapes.md
  • references/knowledge-and-designs.md — knowledge / iterations / specs 边界与索引
  • references/plan-workflow-lifecycle-contract.md — plan-level workflow lifecycle contract: delivery-kind declaration, stages, evidence contracts, engine seams; closing amendment File-route retirement

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Mstar Artifacts AI skill do?

Plan artifacts: main plans, durable review summaries, QC/QA bundles, workflow state/config/progress/evidence, issue capture, residual severity. Read when authoring or mapping them.

Why use Mstar Artifacts on TypingMind?

Because you install it once and use it with any model. Mstar Artifacts 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 Mstar Artifacts in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/btspoony/mstar-harness/tree/main/skills/mstar-artifacts. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Mstar Artifacts?

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 Mstar Artifacts?

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

Is the Mstar Artifacts AI skill free?

Yes. It is published on GitHub by btspoony under the MIT license. 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.

Related AI Skills

View all
obra logo

Diagnosing Superpowers

obra
CommunityPopular

Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so…

26.3K
293.5K
19 files
View
obra logo

Brainstorming

obra
CommunityPopular

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

25.8K
288.1K
7 files
View
obra logo

Executing Plans

obra
CommunityPopular

Use when you have a written implementation plan to execute in a separate session with review checkpoints

25.8K
288.1K
Instructions
View
obra logo

Using Superpowers

obra
CommunityPopular

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

25.8K
288.1K
5 files
View

Set up your own AI workspace now

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