Speq Adr Rules logo

Speq Adr Rules

Community
marconae
speq-adr-rules

When a decision becomes an ADR: the default is no, only durable decisions qualify, search first, one decision per ADR. Use inside a /speq-plan, /speq-record, or /speq-audit run.

Overview

Publishermarconae
Repositoryspeq-skill
Skill namespeq-adr-rules
Stars
54
Forks
10
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 marconae on GitHub. Read the source before you install it.

Installation

Install the Speq Adr Rules 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/marconae/speq-skill/tree/main/.claude/skills/speq-adr-rules
  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/marconae/speq-skill.git /tmp/speq-skill
mkdir -p .claude/skills
cp -r /tmp/speq-skill/.claude/skills/speq-adr-rules .claude/skills/speq-adr-rules
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Speq Adr Rules 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 Speq Adr Rules 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 Speq Adr Rules 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.

ADR Rules

An ADR is a rare record of a durable decision. Most plans produce none. This skill is the single owner of the rules. Other skills and agents cite it and do not restate it.

1. Default No

  • The expected number of Promotes to ADR: yes entries per plan is zero.
  • Set yes only when a criterion in rule 2 applies and you can name it.
  • Two or more yes entries in one plan get re-judged. Re-read each one against rule 2 and rule 3 before you keep it.
  • A plan with many Design Decisions entries or many resolved review findings does not owe an ADR for each. Most decisions are local and stay no.

2. Criteria for Yes

A decision qualifies only when at least one of these holds:

  • It affects multiple components.
  • It sets a long-lived constraint that binds future work.
  • It is a major technology, API, persistence, security, or deployment choice.
  • It rejects a plausible alternative, and the reason will matter to a later reader.

The entry's Rationale names the criterion that applies and states the result of the search in rule 5.

3. Never an ADR

  • Naming, file placement, and folder layout.
  • A one-off bug fix.
  • A scope trim or a task ordering choice.
  • Implementation detail: function signatures, file paths, flags, data layout inside one module.
  • A workaround specific to one plan's own mechanics, such as a spec-merge gap or a review-loop correction.
  • A corollary of another decision. Record it as a bullet in the parent entry's Consequences line.
  • A statement that already lives in a feature spec scenario.

4. Where It Goes Instead

ContentDestination
Conventions that bind contributors or agentsCLAUDE.md, AGENTS.md, a .speq/*-hook.md file, or specs/mission.md Constraints
WHAT the system is: components and boundariesspecs/architecture.md, changed through an architecture delta
HOW this plan builds itA phrase in the plan.md task line. Only a choice with a rejected alternative gets a decision-log.md ## Design Decisions entry with Promotes to ADR: no
Execution stepsplan.md ## Implementation Tasks

An ADR records why. specs/architecture.md records what is.

To change an existing ADR, write a new ADR with Supersedes: <slug>. Do not edit the old fragment.

5. Search First

Before you set yes, read the ADR digest (/speq-cli) and any fragment that matches the decision. If an ADR already covers the decision, do not promote a duplicate. Either set no, or supersede that ADR when the decision has changed. State the search result in Rationale.

Every plan reads the accepted ADRs before it records design decisions. A plan whose decision, spec delta, or architecture delta contradicts an accepted ADR either conforms to it or supersedes it through a decision-log entry with Supersedes: <slug> and Promotes to ADR: yes. A silent contradiction is a defect.

6. One Decision, No Detail

  • One ADR records one decision.
  • Decision states the choice in plain words. It holds no function signatures, file paths, or flags.
  • An ADR names a library but never pins its version. A version number lives in the manifest or lockfile. The Decision states the policy instead, for example "use the registry release, not a git tag".
  • If the Decision needs a list of paths, signatures, or version numbers to make sense, the content is implementation detail. Move it to the plan.md task line, or to a decision-log.md ## Design Decisions entry with Promotes to ADR: no if it has a rejected alternative.

7. Shape

An ADR has four short sections: Context, Decision, Options Considered, Consequences.

  • Options Considered appears only when a real alternative was rejected.
  • Consequences appears only when the entry carries a Consequences line.
  • Each section is a few sentences. A section that needs a page is more than one decision or holds implementation detail.

7a. Minimum Text, No History

An ADR holds the least text that states the decision. Follow /speq-writing-guardrails.

  • State the current fact in the present tense. Do not narrate how the decision was reached: no earlier attempts, review rounds, plan names, dates, or "was changed from".
  • Context is one or two sentences: the situation that forces the decision.
  • Decision is one to three sentences.
  • An Options Considered row is one line: the option and the reason it lost.
  • Consequences are short bullets that name what becomes easier or harder.
  • Do not copy a decision-log entry's Rationale or Alternatives prose into the ADR. Keep only what a later reader needs to understand why.
  • Remove a sentence that a reader could drop without losing the decision or its reason.

8. Status Lifecycle

  • An ADR is proposed at plan time. A Promotes to ADR: yes entry that passes rules 1 to 5 is the proposal. The plan skill prints it as an ADR candidate.
  • Recording the plan is the acceptance. recorder-agent writes Status: Accepted when /speq-record runs.
  • To reject a proposal, change the entry to Promotes to ADR: no and run the plan skill again before you record. In a PR run, comment on the draft PR and run /speq-plan-pr again with the PR number.
  • Deprecated and Superseded by <slug> follow the existing rules.

9. Vocabulary

TermMeaning
ADRA permanent record in specs/_decision/ of one durable decision
Plan contextThe ## Context part of plan.md: a bullet list of the problem and the forces behind one plan's change. It holds no decisions and is not an ADR
Decision-log entryA note in a plan's decision-log.md. Only an entry marked Promotes to ADR: yes can become an ADR
ADR candidateA decision-log entry marked Promotes to ADR: yes. It is the proposal, shown when the plan is ready
AcceptedAn ADR written by /speq-record. Recording the plan is the acceptance

Frequently asked questions

What does the Speq Adr Rules AI skill do?

When a decision becomes an ADR: the default is no, only durable decisions qualify, search first, one decision per ADR. Use inside a /speq-plan, /speq-record, or /speq-audit run.

Why use Speq Adr Rules on TypingMind?

Because you install it once and use it with any model. Speq Adr Rules 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 Speq Adr Rules in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/marconae/speq-skill/tree/main/.claude/skills/speq-adr-rules. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Speq Adr Rules?

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 Speq Adr Rules?

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

Is the Speq Adr Rules AI skill free?

Yes. It is published on GitHub by marconae 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 👇