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
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.
About
Use cases: productivity
Reviews
Write a reviewNo 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
- 0.507score
accessibility-checks
jhlee0409
Use when verifying accessibility (WCAG 2.2 AA) of a rendered UI in a real browser before reporting done — the omp-native replacement for the chrome-devtools…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
chrome-verify-checks
jhlee0409
Use when verifying a chrome-extension/ change before reporting done.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
db-verify-checks
jhlee0409
Use when verifying data-shape claims against a real store — MongoDB or a SQL store (SQLAlchemy / SQLite / Postgres) — before reporting any data-touching…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
llm-eng-checks
jhlee0409
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
perf-checks
jhlee0409
Use when investigating or optimizing performance in a real browser/build/DB before reporting a fix — the omp-native replacement for the chrome-devtools…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
ui-verify-checks
jhlee0409
Use when verifying a frontend UI change in a real browser before reporting done.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
blast-radius
jhlee0409
Enumerate the full impact set of a symbol before or during a change — every reference, caller, implementation/subtype, and reverse import — plus an explicit…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
diagnose
jhlee0409
Disciplined diagnosis loop for a hard bug or performance regression — reproduce → minimize → hypothesize → instrument → fix the cause → regression-test.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
handoff
jhlee0409
Write the live working-set state into a resume block so a FRESH session can continue this work without re-narration.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
localize
jhlee0409
Resolve a change request into an EXACT edit target before touching code, then gate the edit on tests — the localize → edit → validate loop.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
tdd
jhlee0409
Drive a single behavior change with Kent Beck's red → green → refactor loop — write the failing test FIRST, confirm it fails for the right reason, implement…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
assess
jhlee0409
Read-only maintainability audit of a whole codebase — ranks the files most likely to cause maintenance pain (size × churn hotspots, test gaps, lint debt) and…
SkillCFreshness: C★ 2Claude Code +9
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
- 0.507score
chrome-verify-checks
jhlee0409
Use when verifying a chrome-extension/ change before reporting done.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
db-verify-checks
jhlee0409
Use when verifying data-shape claims against a real store — MongoDB or a SQL store (SQLAlchemy / SQLite / Postgres) — before reporting any data-touching…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
llm-eng-checks
jhlee0409
Use when building or hardening an LLM feature — prompt design, RAG, eval harness, model/provider selection, guardrails, and token/cost budgeting — with…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
perf-checks
jhlee0409
Use when investigating or optimizing performance in a real browser/build/DB before reporting a fix — the omp-native replacement for the chrome-devtools…
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
ui-verify-checks
jhlee0409
Use when verifying a frontend UI change in a real browser before reporting done.
SkillCFreshness: C★ 2Claude Code +9 - 0.507score
accessibility-checks
jhlee0409
Use when verifying accessibility (WCAG 2.2 AA) of a rendered UI in a real browser before reporting done — the omp-native replacement for the chrome-devtools…
SkillCFreshness: C★ 2Claude Code +9
Cite this page
new-spec skill. Agent Mart. https://agentmart.dev/skills/jhlee0409-new-spec (last updated 2026-10-24)