Skip to content
Agentmart
Submit a tool

decision-sync

Use when a decision captured by the aim/cross-check/own discernment skills should be filed into the Obsidian vault as a durable decision record, or when the…

Skill by courtneyr-dev

IndexedMIT
Write a review

Chalk Labs

Need help deploying decision-sync?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/courtneyr-dev-decision-sync

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when a decision captured by the aim/cross-check/own discernment skills should be filed into the Obsidian vault as a durable decision record, or when the user says "log this decision", "file the decision", "sync the decision", or "add this to the decision log". Reads a discernment-<slug>.md from the working directory, routes it to the right PARA folder, and writes it with vault frontmatter and backlinks.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/decision-sync

What's inside

Skill name
decision-sync
Description
Use when a decision captured by the aim/cross-check/own discernment skills should be filed into the Obsidian vault as a durable decision record, or when the user says "log this decision", "file the decision", "sync the decision", or "add this to the decision log". Reads a discernment-<slug>.md from the working directory, routes it to the right PARA folder, and writes it with vault frontmatter and backlinks.
License
MIT
Instructions
59 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (2)

  • SKILL.md
  • file_decision.py

SKILL.md (first lines)

# Decision sync

The `aim` → `cross-check` → `own` skills produce a `discernment-<slug>.md` in whatever directory
you were working in. That file is where the reasoning lives while the decision is open. This skill
moves the finished record into the vault, where it survives the repo it was made in.

Run it once a decision is actually made — after `own` has written its section. A decision still in
progress belongs in the working directory, not the vault.

## Where records go

| Situation | Destination |
|---|---|
| Decision is about a specific active project | `Projects/<project>/decisions/` |
| Everything else — tooling, workflow, standing policy | `Areas/Decisions/` |

Ask which project only when the working directory doesn't make it obvious. Never invent a project
folder; if no match exists, use `Areas/Decisions/`.

## Workflow

1. **Find the source.** Look for `discernment-*.md` in the working directory. If several exist, ask
   which one. If none exists, say so and stop — don't reconstruct a decision record from the chat.

2. **Check it's finished.** The file needs a populated `## Own` section. If `## Own` is missing or
   empty, tell the user the decision isn't captured yet and offer to run `own` first.

3. **Read it and write the vault note.** Preserve the reasoning verbatim — the Aim framing, the
   rubric result, the confidence calibration, the case against, and the final call. This record's
   value is that it shows the thinking, not just the outcome. Do not summarize away the
   disconfirming evidence.

4. **File it** with `file_decision.py` (below), which handles frontmatter, the ID, and the index.

5. **Link it.** Add `[[wikilinks]]` to related vault notes — the project note, any Permanent Note
   the reasoning draws on, the source material named in `## Aim`. Links to notes that don't exist
   yet are fine; they mark where the thinking should continue.

6. **Report** the vault path and what you linked. Leave the original `discernment-*.md` in place —
   the repo copy is the working artifact and deleting it loses the local trail.

## Helper

```bash
python3 ~/.claude/skills/decision-sync/file_decision.py <source.md> --title "<title>" [--project "<name>"] [--status decided|revisit] [--dry-run]
```

It writes the note, stamps `type: decision` frontmatter matching vault convention, assigns a
timestamp ID, and appends a row to `Areas/Decisions/Decision Log.md`. Use `--dry-run` to see the
destination and frontmatter without writing.

## Boundaries

- Never file a decision the user hasn't actually made. An open question is not a decision record.
- Never edit the reasoning to make the call look better-supported than the cross-check found it.
  A record that hides its own low-confidence claims is worse than no record.
- This skill writes to the vault only. It does not commit, publish, or share anything.

From courtneyr-dev/agent-skills, MIT.

More from courtneyr-dev/agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 5, 2026 (1 month ago)
Last release
Sep 5, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from courtneyr-dev

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get decision-sync running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying decision-sync?

CallGet help
Cite this page

decision-sync skill. Agent Mart. https://agentmart.dev/skills/courtneyr-dev-decision-sync (last updated 2026-10-24)