Skip to content
Agentmart
Submit a tool

create-work-item

Scaffold a new developer-scoped project directory under work/ that follows the work-directory conventions (README + launcher next-session.md + ledger…

Skill by kashman001

IndexedMIT
Write a review

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/kashman001-create-work-item

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

Scaffold a new developer-scoped project directory under work/ that follows the work-directory conventions (README + launcher next-session.md + ledger handoff.md). Use when starting a new piece of multi-session work, when the user says "create a work item / work directory / project", or before beginning work that will span more than one session and needs a launcher + ledger. For single-file or one-shot tasks, do not create a work directory.

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

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/create-work-item

What's inside

Skill name
create-work-item
Description
Scaffold a new developer-scoped project directory under work/ that follows the work-directory conventions (README + launcher next-session.md + ledger handoff.md). Use when starting a new piece of multi-session work, when the user says "create a work item / work directory / project", or before beginning work that will span more than one session and needs a launcher + ledger. For single-file or one-shot tasks, do not create a work directory.
License
MIT
Instructions
170 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

## Purpose

Create a `work/<project-name>/` directory pre-wired with the standard backbone
files (README, launcher, ledger) so multi-session work starts consistent and
stays context-cheap. This skill owns the scaffolding procedure; the durable
definition of each file's role lives in `docs/work-directory-conventions.md`.

Do **not** use this for trivial single-step tasks — those need no work
directory. Use it when work will span multiple sessions or needs persistent,
agent-neutral state on disk.

## Required Reads

**Always read first:**

1. `docs/work-directory-conventions.md` — the file roles and write discipline.

**Read on demand:**

1. `skills/session-rollover/SKILL.md` — how the launcher and ledger are
   maintained (and rolled over) across sessions.
2. `skills/decision-log/SKILL.md` — only if the project will keep a
   `decisions.md` / ADRs.

## Procedure

1. **Confirm scope and name.** Pick a hyphenated directory name
   (`work/<project-name>/`). Ask the user for the governing skill(s) if any
   workflow skill applies; use `—` if none.

   **Ask whether the effort needs a spec.** Rule of thumb: a spec is required
   when success criteria can't fit the README's one-line goal — multi-feature
   work, user-facing behaviour, anything where "done" is genuinely debatable.
   Ops-flavoured efforts skip it. An external tracker ticket (JIRA, GitHub
   issue) with real acceptance criteria can *be* the spec of record. Skeleton
   and full rules: `docs/agents/issue-tracker.md` → "Spec conventions".
   **If no spec: the README's `## Success criteria` section is required.**

2. **Create the directory and the three backbone files** below. Substitute
   `<project>`, a one-line description, the governing skill(s), and the first
   objective. Use the canonical names `next-session.md` (launcher) and
   `handoff.md` (ledger).

3. **README.md** (project identity — durable, changes rarely):

   ```markdown
   # <Project> — <one-line what-it-is>

   Governing skill(s): `<skill>` (or none).

   **Start here:** `next-session.md` (catch-up launcher) → `handoff.md`
   (session ledger, top block).

   ## What this is

   <2–4 sentences: goal, scope, why it exists.>

   ## Success criteria

   <!-- Required when the effort has no spec.md; delete if spec.md exists. -->

   <How we'll know this effort is done — verifiable, not "make it work".>

   ## Files

   - `next-session.md` — forward launcher (what to do next). REPLACED each rollover.
   - `handoff.md` — session ledger (what happened). APPEND newest-on-top; archive
     to `handoff-archive.md` when it exceeds the two most recent sessions.
   - <other project files, added as they appear.>
   ```

4. **next-session.md** (launcher — starts nearly empty, forward-only):

   ```markdown
   # Catchup prompt — <Project> (paste into a new agent session)

   We're resuming <project>. Works in any runtime (Claude Code, Codex, Gemini,
   OpenCode) — all read `CONTEXT.md` via their entrypoint.

   > **This file is the LAUNCHER (catch-up prompt).** Forward-only, and REPLACED
   > at each rollover: it holds what to do next, still-binding constraints, and
   > pointers — never session history. Past-tense provenance lives in
   > `handoff.md` (the append-only ledger). Convention:
   > docs/work-directory-conventions.md.

   ## >>> START HERE <<<

   <The current objective and the concrete next actions (a short numbered todo).>

   ## Constraints already decided (do not re-litigate)

   <One-liners + pointers, added as decisions are made.>

   ## Read these first, in order

   1. `work/<project>/README.md`
   2. `work/<project>/handoff.md` (top block)
   ```

   **Plan markers — only when asked** (`--plan` among the arguments, or the
   user says the effort will run a plan per `docs/plans.md`); the default
   scaffold carries none, plans stay opt-in. Append to `next-session.md`:

   ```markdown
   ## Position

   <!-- plan:begin position -->
   <!-- plan:end position -->
   ```

   `scripts/plan.sh sync` renders the plan's position and frontier between
   the markers and refuses a launcher without them.

5. **handoff.md** (ledger — purpose header + first block):

   ```markdown
   <!--
   PURPOSE: This is the LEDGER (provenance log). Append-only, newest block on
   TOP. Each "# Session Handoff" block records what happened in one session.

From kashman001/ai-workspace-template, MIT.

More from kashman001/ai-workspace-template

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 12, 2026 (17 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from kashman001

Cite this page

create-work-item skill. Agent Mart. https://agentmart.dev/skills/kashman001-create-work-item (last updated 2026-10-24)