TypingMindTypingMindThe best frontend for AI
Mstar Roles logo

Mstar Roles

Community
btspoony
mstar-roles

Role prompt hub and single load-selection authority: identity-first `references/<role>.md`, PM-activated skill presets, the none/named-preset/resume decision. Always load for any Morning Star role.

Overview

Publisherbtspoony
Repositorymstar-harness
Skill namemstar-roles
Stars
67
Forks
4
Bundled files
23
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.

  • 23 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 Roles 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-roles
  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-roles .claude/skills/mstar-roles
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Mstar Roles 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 Roles 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 Roles 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

This hub is the single load-selection authority for Morning Star roles (Spec A2): mstar-harness-core stays the lifecycle/authorization semantic authority and the global entry whenever it is loaded, but this hub owns the selection decision — core does not maintain a second mandatory-role table. When a Morning Star role starts work in a session:

  1. Read this mstar-roles skill; resolve role mapping and parameter tables below. This hub bootstrap does not require mstar-harness-core first.
  2. Read the corresponding references/<role>.md file — identity-first: mission, scope, and NEVER rules come before any skill list. Non-PM roles also read the linked minimal leaf boundary (references/_shared/leaf-executor-core.md — role-owned, always loads with the reference).
  3. Apply the Assignment Skill presets: decision — explicit none ⇒ no optional topic preset (identity + assignment + role-owned methods only); omitted on a substantive implementation / QC / QA round ⇒ the role's standard preset; explicit named preset ⇒ that role's supported members; omitted on a trivial route ⇒ identity only. Role-owned QC/QA methods and assigned evidence obligations load regardless of preset. none never grants delegation and never waives gates. Unknown preset or missing required identity ⇒ return Needs Context / Blocked — never infer project-manager.
  4. Whenever mstar-harness-core is loaded by that decision (PM required reads, standard routes, direct lifecycle-topic invocation) it remains the global entry (state machine, gates, routing); if any conflict appears, mstar-harness-core remains the authoritative source for lifecycle, gates, routing, and invariants.
  5. Resume: retain loaded identity/contract only when the source hashes are unchanged; read changed / phase-required material; never reinterpret none as permission.
  6. Expand placeholders from role parameters before execution.

The table below summarizes each role's preset menu; when a role file's preset section differs, follow the role file for that session.

Exception: project-manager is the core orchestrator and keeps required reading (not a preset, never preset-gated) — see references/project-manager.md.

Role Reference Mapping

Agent idReference fileParameterized slots
project-managerreferences/project-manager.md—
product-managerreferences/product-manager.md—
architectreferences/architect.md—
code-reviewerreferences/code-reviewer.md—
fullstack-devreferences/fullstack-dev-shared.mdrole_id, track
fullstack-dev-2references/fullstack-dev-shared.mdrole_id, track
frontend-devreferences/frontend-dev.md—
qa-engineerreferences/qa-engineer.md—
qc-specialistreferences/qc-specialist-shared.mdrole_id, reviewer_index, focus, report_suffix
qc-specialist-2references/qc-specialist-shared.mdrole_id, reviewer_index, focus, report_suffix
qc-specialist-3references/qc-specialist-shared.mdrole_id, reviewer_index, focus, report_suffix
ops-engineerreferences/ops-engineer.md—
writing-specialistreferences/writing-specialist.md—
prompt-engineerreferences/prompt-engineer.md—

Role → skill presets (PM-activated)

PM-owned activation; the omission / none / named-preset / resume / unknown-preset rule is defined once in § Load Order above — this table only summarizes each role's preset menu (role refs own their named member lists). Role-owned files (e.g. references/qc-specialist/, references/qa-engineer/acceptance-gate.md) are excluded from presets; they always load with the reference.

RolePreset menu
project-managermstar-dispatch-gates, mstar-phase-gates, mstar-conventions, mstar-roles ref; + references/project-manager/qa-trigger-matrix.md for QA gate tiers; + mstar-review-qc before QC; + mstar-branch-worktree / mstar-artifacts as the round requires; + mstar-skill-authoring for skill work; + mstar-iteration for iteration lifecycle (start/drive/close); + mstar-pr-loop for the explicitly requested PR quality-gate loop, or when iteration Phase 1 records pr_merge_policy: reviewed-auto as that iteration's Phase 5 review path; + mstar-strategy for strategic alignment; + mstar-use-cli when the round runs or interprets CLI commands; + mstar-compound / mstar-compound-refresh pre-loaded by mstar-iteration § iteration-close
fullstack-dev*, frontend-devmstar-coding-behavior, mstar-dispatch-gates, mstar-branch-worktree (if repo writes); plan path symbols from mstar-conventions (minimal); mstar-design-md when implementing styled UI; mstar-design-system when the round converges an existing implementation onto a baseline; mstar-use-cli when the round runs or interprets CLI commands
qc-specialist*Presets: mstar-branch-worktree, mstar-artifacts (review bundle paths); mstar-design-md when reviewing UI; mstar-design-system when judging implementation-vs-baseline differences; mstar-use-cli when the round runs or interprets CLI commands. Role-owned (never gated): references/qc-specialist/ workflow/checklist/template (+ lenses on demand)
qa-engineerPresets: mstar-branch-worktree, mstar-artifacts (closing R#); mstar-design-md when verifying visual output; mstar-design-system when the round compares the build against a baseline; mstar-use-cli when the round runs or interprets CLI commands. Role-owned (never gated): references/qa-engineer/acceptance-gate.md
architectmstar-phase-gates (Prepare), mstar-artifacts (knowledge/specs); mstar-design-md (creator + design intent); mstar-strategy (STRATEGY.md creation/maintenance); mstar-use-cli when the round runs or interprets CLI commands
product-managermstar-phase-gates (Prepare), mstar-artifacts (knowledge/specs); mstar-design-md (creator + design intent); mstar-strategy (STRATEGY.md creation/maintenance)
code-reviewermstar-sdd (per-task review mode); mstar-audit (audit mode: full workflow); mstar-conventions (paths); mstar-use-cli when the round runs or interprets CLI commands
ops-engineermstar-coding-behavior, mstar-branch-worktree; mstar-use-cli when the round runs or interprets CLI commands
prompt-engineerAll topic skills when editing harness text; mstar-use-cli when the round runs or interprets CLI commands

Use skill names (not absolute filesystem paths) in role references.

Role references/*.md files include explicit NEVER sections (anti-recursion, tool misuse, Git discipline). Treat those bullets as hard gates alongside mstar-harness-core; do not treat them as optional style tips.

Parameter Table (SSOT)

Dev track (fullstack-dev family)

role_idtrackMeaning
fullstack-devprimaryBackend-led primary implementation track
fullstack-dev-2parallel_secondarySecond implementation track for parallel independent modules

QC reviewer (qc-specialist* family)

Job: Independent code review on the plan branch diff (logic, security, contracts, maintainability, reliability). Not test execution — suites/builds belong to implementer (L1) and qa-engineer (L4). See mstar-review-qc/references/review-responsibility-boundaries.md.

Default (SDD): plan QC tri-review — qc-specialist / qc-specialist-2 / qc-specialist-3 → {SDD_DIR}/review/qc1.md…qc3.md + qc-consolidated.md when Execution mode: sdd.

Exception (inline / hotfix): single-seat → {SDD_DIR}/review/qc.md (QC mode: single).

role_idreviewer_indexfocusreport_suffix
qc-specialist1Architecture coherence and maintainability riskqc1 → {SDD_DIR}/review/qc1.md
qc-specialist-22Security and correctness riskqc2 → {SDD_DIR}/review/qc2.md
qc-specialist-33Performance and reliability riskqc3 → {SDD_DIR}/review/qc3.md

PM consolidated (tri mode): {SDD_DIR}/review/qc-consolidated.md (same folder; no <plan-id> basename prefix) + durable main-plan summary. Naming SSOT: mstar-artifacts/references/plan-files-and-reports.md.

Engine check (when available): run mstar roles validate (or import validateRoleMapping / lintLoadOrder from @mstar-harness/engine in a host hook) to validate the mapping and parameter tables above against the on-disk references/*.md layout (shared families included) and lint load-order declarations: mstar-* topics declare core-first with only exact-identity exemptions; this hub's bootstrap declares the § Load Order decision matrix. On fail -> do not proceed; fix and re-run. Skill text below remains authoritative when the runtime is absent.

Maintenance Rules

  • Edit behavior in references/*.md.
  • Edit role family parameters in this file.
  • Keep shared-family roles (fullstack-dev*, qc-specialist*) on one shared reference file.
  • Role references stay identity-first: mission / responsibilities / NEVER rules before any skill list; topic-skill loads live only in the Skill Preset (PM-Activated) section.
  • Add new roles by updating mapping, parameters (if needed), and adding corresponding agents/*.md shell.

Workflow

加载顺序：Read 本 skill（角色映射 + 参数表；本 skill 即加载选择权威）→ 解析对应 references/<role>.md（身份优先：mission / NEVER / responsibilities 在前）+ 非 PM 角色读取其链接的 leaf 边界 → 按 § Load Order 的 Skill presets: 决策加载专题 skill（解释权只在 § Load Order；角色 ref 只列成员名单）。映射 / 参数表与磁盘 references/*.md 布局不符时先修再继续。

Evidence

Correct structural evidence = mstar roles validate reports zero mapping and load-order violations: lifecycle topics declare core-first, and the hub declares identity-first / none / standard / role-owned methods / unknown-preset decisions. Reference files match the mapping; shared families use one reference. This validation does not establish model compliance or waive lifecycle authority.

References

  • 角色正文 → references/<role>.md（本 skill 内；leaf QC / QA 等子目录见 references/qc-specialist/、references/qa-engineer/）

  • 全局角色 → mstar-harness-core 加载矩阵与专题 skill 索引

  • Explicit independent E2E/browser/device requests → mstar-e2e (PM orchestrates; ops-engineer executes; routine QA does not trigger it).

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 Roles AI skill do?

Role prompt hub and single load-selection authority: identity-first `references/<role>.md`, PM-activated skill presets, the none/named-preset/resume decision. Always load for any Morning Star role.

Why use Mstar Roles on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/btspoony/mstar-harness/tree/main/skills/mstar-roles. 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 Roles?

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 Roles?

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

Is the Mstar Roles 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
NousResearch logo

Auteur

NousResearch
OrganizationPopular

Design and build cinematic, award-level web pages.

53.5K
250.4K
25 files
View
NousResearch logo

Excalidraw

NousResearch
OrganizationPopular

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

53.5K
250.4K
4 files
View
NousResearch logo

Simple English

NousResearch
OrganizationPopular

Rewrite text to ASD-STE100 Simplified Technical English.

53.5K
250.4K
2 files
View
NousResearch logo

Watchers

NousResearch
OrganizationPopular

Poll RSS, JSON APIs, and GitHub with watermark dedup.

53.5K
250.4K
4 files
View

Set up your own AI workspace now

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