Ospec Change logo

Ospec Change

Community
henrydiaosi
ospec-change

Create or advance an active change inside an OSpec project, from requirement intake through verification and finalize.

Overview

Publisherhenrydiaosi
Repositorydorado
Skill nameospec-change
Stars
79
Forks
13
Bundled files
Instructions only
LicenseMIT
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 henrydiaosi on GitHub. Read the source before you install it.

Installation

Install the Ospec Change 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/henrydiaosi/dorado/tree/main/assets/global-skills/claude/ospec-change
  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/henrydiaosi/dorado.git /tmp/dorado
mkdir -p .claude/skills
cp -r /tmp/dorado/assets/global-skills/claude/ospec-change .claude/skills/ospec-change
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ospec Change 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 Ospec Change 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 Ospec Change 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.

OSpec Change

Use this skill when the user says things like "use ospec change to do a requirement".

Scope

This skill is the single entry for the full change lifecycle inside an initialized OSpec project:

  • requirement intake
  • change naming or matching
  • explicit queue planning when the user asks for queue behavior
  • proposal and task refinement
  • implementation guidance
  • progress tracking
  • verification
  • archive readiness check
  • finalize closeout

Read Order

  1. .skillrc
  2. SKILL.index.json
  3. for-ai/ai-guide.md
  4. for-ai/execution-protocol.md
  5. If Stitch installation, provider switching, doctor remediation, MCP setup, or auth setup is involved, read the repo-local Stitch plugin spec first. When docs/stitch-plugin-spec.zh-CN.md exists, treat it as the source of truth for the config shape.
  6. If the user explicitly asks for queue behavior, inspect changes/queued/ before creating new queue items.
  7. changes/active/<change>/proposal.md
  8. changes/active/<change>/tasks.md
  9. changes/active/<change>/state.json
  10. changes/active/<change>/verification.md
  11. changes/active/<change>/review.md

Language

  • Follow the project-adopted document language from for-ai/ and existing change docs.
  • Keep Chinese projects in Chinese unless the repo explicitly adopts English.

Plugin Gates

After reading .skillrc, inspect enabled plugins before advancing the change.

Stitch

When .skillrc.plugins.stitch.enabled = true and .skillrc.plugins.stitch.capabilities.page_design_review.enabled = true:

  • determine whether the current change activates stitch_design_review from proposal flags and tasks.md / verification.md optional_steps
  • if activated, read changes/active/<change>/artifacts/stitch/approval.json
  • if approval.json.preview_url or submitted_at is empty, run ospec plugins run stitch <change-path> before asking the user to review the design
  • if .skillrc.plugins.stitch.project.project_id is already configured, reuse that exact Stitch project instead of creating a new project
  • if .skillrc.plugins.stitch.project.project_id is empty, treat the first successful Stitch run as the canonical project and keep using it for later changes
  • treat missing approval or status != approved as a blocking gate
  • do not claim the change can continue implementation closeout or archive readiness until Stitch approval is complete
  • treat the built-in stitch plugin with the configured provider adapter as the default path unless .skillrc.plugins.stitch.runner is explicitly overridden
  • if a custom runner is configured and token_env is set but missing, stop and request configuration first
  • if runner readiness, provider CLI, stitch MCP, or auth readiness is unclear, use ospec plugins doctor stitch <project-path> before ospec plugins run stitch <change-path>
  • if Stitch installation, provider switching, doctor remediation, MCP setup, or auth setup is involved, read the repo-local Stitch plugin spec first; when docs/stitch-plugin-spec.zh-CN.md exists, use its documented Gemini / Codex config snippets instead of inventing command / args / env or stdio-proxy settings
  • if the repo-local Stitch spec is missing, use these built-in baselines instead of guessing:
    • gemini: %USERPROFILE%/.gemini/settings.json -> mcpServers.stitch.httpUrl = "https://stitch.googleapis.com/mcp" and headers.X-Goog-Api-Key
    • codex: %USERPROFILE%/.codex/config.toml -> [mcp_servers.stitch], type = "http", url = "https://stitch.googleapis.com/mcp", and X-Goog-Api-Key in headers or [mcp_servers.stitch.http_headers]
  • use ospec plugins approve stitch <change-path> or ospec plugins reject stitch <change-path> to record the review result

Required Logic

  1. Inspect repository state first when posture is unclear.
  2. If the repo is not initialized, stop at initialization guidance instead of forcing a change.
  3. If the request is a new requirement, derive a concise kebab-case change name and create it.
  4. If the matching active change already exists, continue it instead of duplicating it.
  5. Default to one active change unless the user explicitly asks to split work into multiple changes, create a queue, or execute a queue.
  6. When queue behavior is explicitly requested, derive an ordered list of concise kebab-case change names. Each name should represent one execution unit, not a mixed bundle.
  7. For explicit queue planning, present the queue as an ordered list first. Use ospec queue add ... to create queued changes and ospec run ... only when the user explicitly asks to run the queue.
  8. Treat changes/active/<change>/ as the execution container.
  9. Keep proposal.md, tasks.md, state.json, verification.md, and review.md aligned with actual execution and with the project's established document language.
  10. Use OSpec closeout commands instead of inventing a parallel process.
  11. Apply plugin gates from .skillrc before advancing a change.
  12. If stitch_design_review is activated, inspect the Stitch approval artifact before continuing execution.
  13. If the Stitch preview has not been submitted yet, run ospec plugins run stitch <change-path> before asking for design review.
  14. If Stitch approval is missing or not approved, stop at the review gate instead of treating the change as ready.

Commands

bash
ospec status [path]
ospec new <change-name> [path]
ospec changes status [path]
ospec queue status [path]
ospec queue add <change-name> [path]
ospec queue activate <change-name> [path]
ospec queue next [path]
ospec run start [path] --profile manual-safe
ospec run step [path]
ospec run status [path]
ospec plugins status [path]
ospec plugins doctor stitch [path]
ospec plugins run stitch [changes/active/<change>]
ospec plugins approve stitch [changes/active/<change>]
ospec plugins reject stitch [changes/active/<change>]
ospec progress [changes/active/<change>]
ospec verify [changes/active/<change>]
ospec archive [changes/active/<change>] --check
ospec finalize [changes/active/<change>]

Guardrails

  • Do not assume dashboard workflows exist.
  • Do not refer to basic or full structure levels.
  • Do not confuse repository initialization with change execution.
  • Do not enter queue mode unless the user explicitly asks for queue behavior.
  • Do not turn an ordinary single requirement into multiple queued changes unless the user explicitly asks to split it.
  • Do not continue past an active Stitch review gate when approval is missing or not approved.
  • Do not claim completion until implementation, verification notes, and closeout status are aligned.
  • If real project tests exist, run or recommend them separately from ospec verify.

Frequently asked questions

What does the Ospec Change AI skill do?

Create or advance an active change inside an OSpec project, from requirement intake through verification and finalize.

Why use Ospec Change on TypingMind?

Because you install it once and use it with any model. Ospec Change 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 Ospec Change in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/henrydiaosi/dorado/tree/main/assets/global-skills/claude/ospec-change. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ospec Change?

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 Ospec Change?

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

Is the Ospec Change AI skill free?

Yes. It is published on GitHub by henrydiaosi 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

Set up your own AI workspace now

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