Ds Govern

Community

BIAsia

ds-govern

c2d2c governance pipeline — the standard workflow for converging and freezing a component/style system. Use when the user wants to unify, converge, standardize, or govern a visual dimension (radius, shadows, color, spacing, motion, a component API), asks to add a lint/CI gate for a style rule, wants hardcoded values migrated onto tokens, or complains the same style is hand-written differently across the codebase. Covers census → spec → convergence → full migration → gate → dead-code removal → write-back.

Overview

Publisher	BIAsia
Repository	`c2d2c`
Skill name	`ds-govern`
Stars	58
Forks	2
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

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 BIAsia on GitHub. Read the source before you install it.

Installation

Install the Ds Govern AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/BIAsia/c2d2c/tree/main/skills/ds-govern
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.

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/BIAsia/c2d2c.git /tmp/c2d2c
mkdir -p .claude/skills
cp -r /tmp/c2d2c/skills/ds-govern .claude/skills/ds-govern

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ds Govern 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 Ds Govern 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 Ds Govern 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.

c2d2c:ds-govern — converge + freeze

Project parameters

Resolve parameters from C2D2C.md at the repo root (fallback: .claude/c2d2c.md); if absent, offer to bootstrap one from the template at ../../templates/C2D2C.template.md (plugin root; standalone installs without that file fetch https://raw.githubusercontent.com/BIAsia/c2d2c/main/templates/C2D2C.template.md). This skill uses TOKEN_HOME, SPEC_HOME, GATE_HOME, LAW_HOME, DS_ROUTE, TOKEN_EXPORT, GATES.

Core mental model: governance = convergence + freezing. Convergence without freezing drifts back within months; freezing without cleanup leaves two systems that mislead everyone who comes later. One governance pass must complete all five moves: single source, full migration, gate, dead-code removal, written rule.

0. Decide to govern

Trigger signals: the third hand-written variant of the same style; reviews correcting the same class of mistake repeatedly; a restore job discovering "this value exists five ways in the codebase". Scope first: which dimension (radius/shadow/color/spacing/a component API), which directories, which areas are exempt (demos/marketing pages/vendored code, usually).

1. Full-repo census

rg every current spelling of the dimension into a list: each form × occurrence count × representative file.
Derive the "rungs actually in use" from the list. The ladder grows out of usage, not out of thin air.
Separate the exceptions: legitimate special cases (future exemption areas) vs. drift (to migrate).

2. Write the spec (STOP: user review)

Write the system doc in SPEC_HOME, covering:

The ladder/recipe: fixed token table (e.g. a px-value radius ladder, a three-tier shadow recipe) and when each rung applies.
Single source: where values live (tokens) and where logic lives (single-source modules like field-shell.ts, tone.ts).
The ban list: which spellings become illegal (raw literals, raw palette classes, inline beziers…).
Exemptions: directory-level exemptions plus allowlist semantics (the allowlist is a frozen baseline, not a door: existing debt may sit in it; new code may not enter).

Get the user's sign-off before touching code.

3. Converge the implementation

Tokens go into TOKEN_HOME (one value often registers in several places: CSS variable + theme alias + class ladder + design-side export; put the "adding a rung = N edits" list in the spec).
Absorb component APIs: geometry/color become component-owned (driven by size/variant; matching classes stripped from caller className), ending caller overrides.
For heavy coupling use restyle-in-place: when the behavior layer can't move (blocked by a lynchpin component), swap only the visual shell, leave behavior in place, and record the blocker.

4. Migrate every caller

Migrate all call sites in one pass; no dual-track period. If volume forces batching, each batch must be internally complete (that batch's components, callers, and tests move together).
Anything the new API can't express flows back into step 2 as a spec fix, never as a caller-side loophole.

5. Freeze with a gate

Write check:<system> into GATE_HOME: scan for banned spellings, skip exempt areas, match the allowlist exactly (file + pattern), fail everything else with a fix hint in the error message ("use X instead").
Wire it into the CI aggregate so local GATES runs it too.
The allowlist holds existing debt only: baseline what can't migrate today, then only ever shrink it.

6. Remove the dead code

Delete old tokens, old classes, old components, barrel exports, types, i18n keys, unreferenced styles. Delete completely; keep nothing "just in case".
Run GATES to confirm nothing dangles.

7. Write it back

Add/update a rule in LAW_HOME: one-sentence rule + pointer to the spec + gate name, so future agents get it right without reading the spec.
Create/update the DS_ROUTE preview page for the new ladder (token visualization + component state matrix).
Run TOKEN_EXPORT to sync the token changes to the design side (the token flow described in c2d2c:c2d).

Reporting rhythm

Steps 1-2 merge into one message: census findings + spec draft (STOP).
After steps 3-7, close out: migration volume, gate list, deletion list, rules diff, MR link.

Frequently asked questions

What does the Ds Govern AI skill do?

Why use Ds Govern on TypingMind?

Because you install it once and use it with any model. Ds Govern 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 Ds Govern in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/BIAsia/c2d2c/tree/main/skills/ds-govern. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ds Govern?

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 Ds Govern?

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

Is the Ds Govern AI skill free?

Yes. It is published on GitHub by BIAsia 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.

View all

Api Design

affaan-m

CommunityPopular

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

Accessibility

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

Archify

Validated interactive HTML diagrams, upstream-maintained.

Auteur

Design and build cinematic, award-level web pages.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

c2d2c:ds-govern — converge + freeze

Project parameters

0. Decide to govern

1. Full-repo census

2. Write the spec (STOP: user review)

3. Converge the implementation

4. Migrate every caller

5. Freeze with a gate

6. Remove the dead code

7. Write it back

Reporting rhythm

Frequently asked questions

Related AI Skills

Set up your own AI workspace now