Speq Record logo

Speq Record

Community
marconae
speq-record

Merges implemented spec deltas into the permanent specs and archives the plan. Use after /speq-implement, or to record, merge, or archive a finished plan. Arg: plan-name.

Overview

Publishermarconae
Repositoryspeq-skill
Skill namespeq-record
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 Record 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-record
  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-record .claude/skills/speq-record
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Speq Record 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 Record 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 Record 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.

Spec Recorder (Orchestrator)

Thin orchestrator. It verifies preconditions and delegates the merge work to the recorder-agent sub-agent.

Required Skills (for the orchestrator)

Invoke before starting:

  • /speq-cli — Spec validation

The recorder-agent sub-agent invokes its own required skills.

Workflow

Phase 0: Load Project Hook (orchestrator)

Check for .speq/record-hook.md in the repo root.

  • Present: read it. Announce "Loaded project hook: .speq/record-hook.md". Its content is authoritative: it can add to, change, or override any part of this workflow. If the hook conflicts with this workflow, the hook wins.
  • Absent: continue normally, no mention.

Note it (not its full content) as a Project Hook: line in the recorder-agent brief below.

Phase 1: Resolve Plan Name (orchestrator)

Get the plan name from the user prompt. If none is given, ask the user to choose from the plans under specs/_plans/.

Phase 2: Verify Preconditions (orchestrator)

Check: specs/_plans/<plan-name>/verification-report.md exists?
├─ Yes → Proceed
└─ No  → STOP: "Run /speq-implement <plan-name> first."

Phase 3: Delegate to recorder-agent

Spawn the recorder sub-agent with the plan name:

Delegate to recorder-agent — Record <plan-name> into permanent specs

## Plan Name
<plan-name>

## Context
- Verification report confirmed at: specs/_plans/<plan-name>/verification-report.md
- Plan file: specs/_plans/<plan-name>/plan.md
- Delta specs: specs/_plans/<plan-name>/**/spec.md
- Architecture delta (optional): specs/_plans/<plan-name>/architecture.md

## Your Task
Merge all delta specs, and the architecture delta if present, into permanent specs per the `recorder-agent` workflow. Validate between merges. Archive the plan on success. If any library threshold is exceeded (scenarios > 10, domain features > 8), STOP before archiving and return a question for the user.

Project Hook: <if active, ".speq/record-hook.md — read it and apply it"; otherwise omit this line>

Return a summary of merged features and the archive path.

Phase 4: Handle Threshold Escalations (orchestrator)

If the sub-agent returns threshold signals:

  1. Ask the user for their organizational decision
  2. Respawn recorder-agent with the decision, OR apply a trivial edit (for example, a file rename) directly
  3. Archive only after all decisions are resolved

If the sub-agent returns Recording failed: architecture delta: ..., do not respawn it and do not fix the delta yourself. The plan stays unarchived. Report the message to the user and stop. The fix is a plan change: correct architecture.md in the plan, or refresh its BASE after a stale-base error.

Phase 5: Confirm Completion (orchestrator)

Report to user:

✓ Verification report confirmed
✓ All deltas merged
✓ Spec library validated
✓ Plan archived: specs/_recorded/NNN-<plan-name>
✓ Architecture merged: <sections>   (omit when no delta)
✓ ADRs accepted: N — <slugs>   (omit when none)

Work Split (reference)

StepPerformed byWhy
Precondition checks, user questionsThis skill (pins Sonnet)Lightweight orchestration
Delta merge, validation, archiverecorder-agent sub-agentFixed steps: apply markers, validate, archive

The split preserves rotation discipline: the orchestrator can respawn the sub-agent with a fresh context and keep its own state.

Anti-Patterns

PatternWhy Wrong
Record without verification reportImplementation not proven
Archive after an architecture delta failureThe delta was not merged, so the plan must stay open

Frequently asked questions

What does the Speq Record AI skill do?

Merges implemented spec deltas into the permanent specs and archives the plan. Use after /speq-implement, or to record, merge, or archive a finished plan. Arg: plan-name.

Why use Speq Record on TypingMind?

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

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

Which AI models can use Speq Record?

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 Record?

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

Is the Speq Record 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 👇