Skip to content
Agentmart
Submit a tool

new-spec

Scaffold a spec triplet (spec.md / plan.md / context.md) under specs/YYYYMMDD-<name>/ before starting a non-trivial piece of work.

Skill by jhlee0409

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying new-spec?

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/jhlee0409-new-spec

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 spec triplet (spec.md / plan.md / context.md) under specs/YYYYMMDD-<name>/ before starting a non-trivial piece of work. Use when a task spans multiple modules / several commits / a new ADR, or when the user says "new spec", "스펙 만들어", "plan this out", "spec this", "기획부터".

Use cases: productivity

Reviews

Write a review

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
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/new-spec

Tools it pre-approves 3

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Bash,
  • Read,
  • Edit

What's inside

Skill name
new-spec
Description
Scaffold a spec triplet (spec.md / plan.md / context.md) under specs/YYYYMMDD-<name>/ before starting a non-trivial piece of work. Use when a task spans multiple modules / several commits / a new ADR, or when the user says "new spec", "스펙 만들어", "plan this out", "spec this", "기획부터".
License
MIT
Allowed tools
Bash,, Read,, Edit
Instructions
21 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts
  • Pre-approves some shell commands

Files (2)

  • SKILL.md
  • new-spec.sh

SKILL.md (first lines)

# new-spec

Structure non-trivial work before coding — the spec is what keeps the work
grounded on the original ask (this is where reliability comes from, not from a
measurement system).

1. **Decide if a spec is warranted.** Yes if the task touches ≥2 modules / areas,
   needs ≥3 commits, introduces a new ADR, or is forward-only. **Skip it** for
   small work (single file, doc-only, a follow-up) — spec ceremony on tiny tasks
   is net-negative.
2. **Scaffold:** run
   `bash "${CLAUDE_PLUGIN_ROOT}/skills/new-spec/new-spec.sh" "<name>"` from the
   repo root. It creates `specs/<date>-<slug>/{spec,plan,context}.md` and prints
   the directory.
3. **Fill, in order:** `spec.md` (the original ask verbatim + acceptance),
   `plan.md` (dependency-ordered tasks), then load the tasks and surface **N/M**
   as you work. A "done" tone before all plan tasks are consumed is not allowed.
4. **`context.md` `## 0. Resume here`** — write it with `/harness-kit:handoff` at
   a stopping point; a fresh session resumes from it with `/harness-kit:pickup`.

From jhlee0409/omni-harness-kit, MIT.

More from jhlee0409/omni-harness-kit

Signals

Stars
2
Forks
1
Open issues
0
Last commit (this folder)
Jul 21, 2026 (3 months ago)
Last release
Jul 22, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/jhlee0409/omni-harness-kit
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from jhlee0409

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 new-spec 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 new-spec?

CallGet help
Cite this page

new-spec skill. Agent Mart. https://agentmart.dev/skills/jhlee0409-new-spec (last updated 2026-10-24)