agentleFS
Sign inStart free
kwoekelkwoekel/woekel-works/skills/co-parent-reply/SKILL.md

co-parent-reply

Skill0 starsChanged 45 days agoMITView on GitHub

Draft a calm reply to a message from the co-parent (text, email, or co-parenting app), and offer to log the incoming message. Use when the user pastes a message from the other parent, says "help me respond", "what do I say back", or "draft a reply".

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Informative: only facts and logistics about the kids.

    line 20
  2. Distinctive:

    Offer a second, shorter version: if the first is more than 4 sentences.

    line 24
  3. Distinctive:

    Write in the user's voice, plain and neutral.

    line 49
  4. Distinctive:

    If the user's own draft is angry, don't lecture.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Co-Parent Reply Helper

Court folder: court/ below means whichever folder the user chose, recorded once as court-folder: in that folder's or the workspace's agent instructions. If unknown, ask once and record it. Never create a second one.

In a high-conflict case, every message may end up in front of a judge. This skill drafts replies that are short, calm, and protect the user, and it never sends them.

Organized draft for your attorney to review, not legal advice.

Steps

  1. Read the incoming message. Separate what actually needs an answer (dates, pickups, school, medical, money) from provocation, accusations, and bait.
  2. Check for red flags first. If the message mentions court, lawyers, a change to custody or the schedule, relocation, threats, or the children's safety, say so at the top: "This one may be worth showing your attorney before replying." Still offer a holding reply ("I received your message and will respond by [day].").
  3. Draft one reply using BIFF:
    • Brief: a few sentences. Long replies give more to argue with.
    • Informative: only facts and logistics about the kids.
    • Friendly: a neutral, polite opening or close. No sarcasm.
    • Firm: clear answer, clear next step, no opening for more debate.
  4. Don't: defend the user's character, answer every accusation, apologize for things the user didn't do, make admissions, discuss the case, or mention the other parent's behavior. If an accusation is false and must be addressed, one line: "I disagree with that description."
  5. Offer a second, shorter version if the first is more than 4 sentences.
  6. Save the incoming message and the draft to court/replies/YYYY-MM-DD-short-title.md.
  7. Offer to log it as a communication with the Incident Log skill (especially if it's tagged 🔴 or 🟡).

Output

> Organized draft for your attorney to review, not legal advice.

> Draft only. Not sent.

**What needs an answer:** [1–3 bullets]
**What to ignore:** [bait, in neutral words]
**Attorney flag:** none | [reason]

**Draft reply:**
> ...

**Shorter version:**
> ...

Rules

  • Never send. The user copies and sends it.
  • Write in the user's voice, plain and neutral. No legal jargon.
  • If the user's own draft is angry, don't lecture. Offer a calmer version side by side.
  • Privacy. Files stay in the user's own folder and their own private backup, and nothing is sent to anyone else. Reading a file sends its contents to the AI provider, so check the app's privacy settings and ask the attorney.
  • No unattended tidying. Automated tidy or lint jobs may report, but must not merge, move, rename, or rewrite anything in the court folder. State it in the folder's agent instructions, under court-folder:: automated-jobs: report only; never merge, move, rename, or rewrite anything here.

Source: BIFF response method (Brief, Informative, Friendly, Firm) from Bill Eddy, High Conflict Institute. Written for this kit; communication logging matches the Case Forge communication template (CaseForgeHq/family-court-strategist, MIT License).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free