Decision Log logo

Decision Log

Community
davekilleen
decision-log

Capture an important decision with its context, options, rationale, and review date, then find it again when it matters.

Overview

Publisherdavekilleen
RepositoryDex
Skill namedecision-log
Stars
481
Forks
130
Bundled files
Instructions only
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 davekilleen on GitHub. Read the source before you install it.

Installation

Install the Decision Log 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.
  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/davekilleen/Dex.git /tmp/Dex
mkdir -p .claude/skills
cp -r /tmp/Dex/packages/dex-agent-plugin/skills/decision-log .claude/skills/decision-log
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Decision Log 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 Decision Log 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 Decision Log 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.

Execution mode

Run inline in the current conversation by default, so this work can see what the user has already discussed, decided, or settled this session. Do not fork merely because this skill was selected. Only run in the background when the user explicitly asks for a background run or the host has already obtained a specific background-work approval for this run.

Purpose

Keep important decisions from disappearing into meetings, messages, or memory. Record what was decided, why it made sense at the time, and when it should be looked at again.

Use this for decisions that would be costly, confusing, or time-consuming to reconstruct later. Do not turn every small preference into a formal entry.

When to Use

  • The user says "we decided", "I chose", or "the call is"
  • A meeting ends with a meaningful choice
  • Several options were considered and the reasoning may matter later
  • A past decision is shaping today's work
  • The user asks why something was done

Step 1: Look for Relevant Past Decisions

Before recording a new decision, search for the topic in:

  1. The active project's files under 04-Projects/
  2. 06-Resources/Decisions/Decision_Log.md
  3. Recent meeting notes under 00-Inbox/Meetings/
  4. Related person or company pages when the decision concerns them

If semantic search is available, use it to find decisions expressed in different words. Otherwise use a careful text search.

Surface a past decision only when it is genuinely relevant. Say what was decided, when, and whether the new choice confirms, changes, or replaces it.

Step 2: Confirm the Decision

Gather the minimum information needed for a useful record:

  • Decision: the choice in one clear sentence
  • Context: what made the choice necessary
  • Options considered: the real alternatives, including keeping things as they are when relevant
  • Rationale: why this option won
  • Review date: a date or a clear statement that no review is needed
  • Related work: project, goal, people, company, or meeting

If anything important is missing, ask one question at a time. Do not invent options or reasoning the user did not give.

Step 3: Choose the Right Home

Use the narrowest useful location:

  • A decision that belongs to one active project → append to that project's Decisions.md
  • A decision that applies across projects or to the user's wider work → append to 06-Resources/Decisions/Decision_Log.md
  • If the best project is unclear → ask before filing it

Create the parent folder or file when it does not exist. Append to an existing file; never replace earlier decisions.

Step 4: Write the Entry

Use this structure:

markdown
## YYYY-MM-DD — Decision title

**Decision:** One sentence stating the choice.

**Context:** The situation, constraint, or question that prompted it.

**Options considered:**
- Option A — the main benefit or trade-off
- Option B — the main benefit or trade-off

**Rationale:** Why this choice made the most sense with the information available.

**Review:** YYYY-MM-DD — what would justify revisiting it

**Related:** [[Project, goal, meeting, person, or company]]

If no review is needed, write **Review:** No planned review rather than leaving the field blank.

Keep the entry factual and compact. Preserve uncertainty: if the choice was a trial, say so.

Step 5: Close the Loop

After saving, confirm:

  • The decision in one sentence
  • Where it was saved
  • The review date, if any
  • Any earlier decision it replaces

If the decision creates follow-up work, offer to add the next action through the normal task flow. Do not create a task without the user's confirmation.

Connection to /week-review

Entries with a review date, a changed assumption, or an unresolved follow-up are designed to be surfaced during /week-review. When this skill records one of those, mention that /week-review can bring it back at the right time. This is a connection between the two skills; do not edit the week-review files.

Rules

  • Record the user's decision, not your preferred answer
  • Separate facts from assumptions
  • Never rewrite an older entry to make history look cleaner
  • When a decision changes, add a new entry and link the earlier one
  • Use absolute dates
  • Keep sensitive personal details out unless the user explicitly wants them recorded

Frequently asked questions

What does the Decision Log AI skill do?

Capture an important decision with its context, options, rationale, and review date, then find it again when it matters.

Why use Decision Log on TypingMind?

Because you install it once and use it with any model. Decision Log 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 Decision Log in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davekilleen/Dex/tree/main/packages/dex-agent-plugin/skills/decision-log. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Decision Log?

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 Decision Log?

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

Is the Decision Log AI skill free?

It is published on GitHub by davekilleen. Check the repository for licensing terms. 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 👇