Skip to content
Agentmart
Submit a tool

plumbline-spec-engine

Internal Plumbline engine.

Skill by nickyfactz

IndexedMIT★ 28
Write a review

Chalk Labs

Need help deploying plumbline-spec-engine?

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/nickyfactz-plumbline-spec-engine

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

Internal Plumbline engine. Use only after the Plumbline router or a Plumbline phase wrapper selects specification work.

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 and code. Checked Oct 26, 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/plumbline-spec-engine

What's inside

Skill name
plumbline-spec-engine
Description
Internal Plumbline engine. Use only after the Plumbline router or a Plumbline phase wrapper selects specification work.
License
MIT
Instructions
56 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • files: referenced but missing: references/specification-template.md, references/artifact-lifecycle.md, references/product-autonomy.md

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Specification engine

## Outcome and completion

Create or adopt one controlling product specification for the current task. A
specification is complete when it states the product outcome, users/workflows,
scope, non-goals, required behavior, constraints, acceptance/proof direction,
and remaining assumptions or residual questions clearly enough for planning.

## Adopt the strongest source

Assess sufficiency, not Plumbline conformance. Accept a user-supplied internal
or external design, handoff, attachment, or prior plan when it settles outcome,
users/workflows, scope, non-goals, behavior, constraints, and acceptance/proof.
Adopt it at the latest safe phase without replaying settled shaping.

When an artifact is sufficient for execution but lacks a separate specification
file, preserve the artifact. Do not require a separate file when the supplied
artifact is sufficient. Recommend a companion only when it materially
improves product clarity or recovery. Keep one controlling source for the task;
name competing candidates and ask the user to select one rather than silently
merging them.

Read `references/specification-template.md`,
`references/artifact-lifecycle.md`, and `references/product-autonomy.md` when
creating, adopting, or expanding a specification. Use the repository's
existing canonical/transient locations. For a blank repository, use
`docs/specs/<feature-slug>.md`.

## Adopt a shaping handoff

When an approved shaping handoff exists, promote it in place as the active
specification. Expand its compact headings into the existing specification
template instead of creating a competing file. Preserve decisions, research
findings and source links, open product questions, fog items, rejected
alternatives, and non-goals. Carry non-blocking fog into assumptions or
residual questions; leave it visible without blocking planning.

Materialize chat-only or attachment-only requirements before long-running work
when a durable record is needed. Preserve source and provenance, avoid
rewriting large or binary inputs wholesale, hash large inputs when appropriate,
and use a safe Markdown extraction when committing the original is unsafe.

## Resolve product questions only

Ask only blocking product questions, one at a time, with a recommendation. Technical
choices belong to the agent and should come from repository evidence, research,
conventions, and safe defaults. Record product amendments explicitly and keep
the approved source's intent intact.

When the controlling artifact is sufficient for the next phase, report the
adoption or companion recommendation once and direct the user to
`plumbline-plan` or `plumbline-execute`. Specification creates or adopts the
contract; it does not implement code.

From nickyfactz/plumbline, MIT.

More from nickyfactz/plumbline

Signals

Stars
28
Forks
0
Open issues
0
Last commit (this folder)
Aug 8, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from nickyfactz

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 plumbline-spec-engine 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 plumbline-spec-engine?

CallGet help
Cite this page

plumbline-spec-engine skill. Agent Mart. https://agentmart.dev/skills/nickyfactz-plumbline-spec-engine (last updated 2026-10-24)