Skip to content
Agentmart
Submit a tool

clarify

Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized questions and appends them to the…

Skill by ramboz

IndexedMIT★ 7
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/ramboz-clarify

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

Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized questions and appends them to the spec's `## Clarifications` section. Auto-triggers when you say clarify this spec, audit this spec for ambiguities, is this spec ready for review, find unknowns in this scope, surface what's still unclear or unspecified, scan for unanswered questions, or what's missing from this spec. Do not use for: spec-compliance review of a finished slice (use `/jig:independent-review` instead); cross-artifact consistency analysis or drift detection (use `/jig:analyze` instead); project-vision or architecture elicitation (use `/jig:vision-elicitation` instead).

Use cases: security

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 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/clarify

What's inside

Skill name
clarify
Description
Lightweight spec clarification scan for jig projects — a six-category ambiguity audit that asks up to five prioritized questions and appends them to the spec's `## Clarifications` section. Auto-triggers when you say clarify this spec, audit this spec for ambiguities, is this spec ready for review, find unknowns in this scope, surface what's still unclear or unspecified, scan for unanswered questions, or what's missing from this spec. Do not use for: spec-compliance review of a finished slice (use `/jig:independent-review` instead); cross-artifact consistency analysis or drift detection (use `/jig:analyze` instead); project-vision or architecture elicitation (use `/jig:vision-elicitation` instead).
License
MIT
Instructions
388 lines in SKILL.md · view on GitHub

Files (3)

  • SKILL.md
  • worked-example-jig.md
  • worked-example-saas.md

SKILL.md (first lines)

> Spec 023 introduces this skill as jig's **pre-spec ambiguity scan**. It
> is the sixth non-stub active jig skill that ships without a `.py`
> helper — clarify is fundamentally a judgment skill, and the
> determinism it needs (locate the target doc, find an existing
> `## Clarifications` section if any, append new entries) Claude can
> run inline via Read + Edit. The skill slots between
> `workflow.py new <slug>` (stub reservation) and the
> `READY_FOR_REVIEW` transition (spec body ready for first review).
>
> Per user direction on 2026-05-18, jig's clarify ships as a
> **standalone baseline**, not a deferral surface. Power users who
> want spec-kit's `/speckit.clarify` install spec-kit and invoke it
> explicitly under `/speckit.*`. There is no category-based deferral
> hint in this skill's description.

## What this skill does

Runs a structured ambiguity scan against a DRAFT-state spec document
across **six categories** aligned with jig's slice template (Scope &
Boundaries / Acceptance Criteria Testability / Dependencies & Blockers /
Non-functional Requirements / Edge Cases & Failure Modes / Terminology
Consistency). The skill rates each category Clear / Partial / Missing,
selects up to **five prioritized questions** (Partial/Missing weighted
above Clear), asks them one at a time recording the user's verbatim
answer, and appends a `## Clarifications` section to the target document
with the Q/A entries plus a coverage summary table.

The skill is **breadth over depth**: catch the obvious unanswered
questions across the six taxonomy categories in a few minutes, leave
deep domain-specific clarification (legal review, regulatory edges,
multi-stakeholder facilitation) to the dev's judgment or to a richer
team process. The five-question budget exists to keep the scan
lightweight enough to actually run before each `READY_FOR_REVIEW`
transition — not so heavy it becomes a chore the team skips.

## When to use vs. when to defer

There are four sibling skills people often confuse with this one. Pick
the right one:

- **`/jig:spec-workflow`** — sibling skill for **state transitions**
  (`workflow.py new`, `workflow.py transition`, status board regen).
  Spec-workflow moves a slice between DRAFT / READY_FOR_REVIEW /
  IN_PROGRESS / REVIEWED / RECONCILED / DONE; it does not elicit
  clarifications. Reach for `/jig:spec-workflow` when you want to
  reserve a new spec number or push a slice to the next state.
  Reach for this skill when the spec body has gaps you want surfaced
  *before* the next transition.
- **`/jig:analyze`** — sibling jig skill (spec 024, sequenced after
  this one) for **cross-artifact consistency analysis**. Analyze
  reads multiple specs + ADRs + docs and surfaces drift between
  them. This skill scans **one document** for internal ambiguities.
  Reach for `/jig:analyze` when you suspect a spec disagrees with
  another spec or with an ADR. Reach for this skill when one spec's
  body has unanswered questions in isolation.
- **`/jig:vision-elicitation`** — sibling skill that fills slots in
  `docs/product-vision.md` and `docs/architecture.md`. That's
  **project-scope elicitation**: who are the users, what's the
  problem, what's the architecture? This skill is **spec-scope
  elicitation**: what does this *one slice* mean, what are its
  ACs, what are its dependencies? Reach for vision-elicitation
  immediately after `scaffold-init`; reach for this skill when
  authoring or reviewing a single spec.
- **`/jig:independent-review`** — sibling skill that reviews a
  finished slice against its spec.md. Independent-review **assumes
  the spec is clear** — it checks the implementation against the
  ACs. This skill helps make the spec clear in the first place,
  so independent-review has something specific to review against.
  Reach for `/jig:independent-review` after the slice is
  implemented; reach for this skill before the slice has
  transitioned to `READY_FOR_REVIEW`.

Rule of thumb: **draft a spec → this skill. Transition a spec →
`/jig:spec-workflow`. Audit across specs → `/jig:analyze`. Review the
implementation → `/jig:independent-review`. Set up the project →
`/jig:vision-elicitation`.**

## Inputs

Two input modes, both supported by the MVP:

1. **Single `spec.md` (overview-level scan).** The user names a spec
   directory (`docs/specs/023-clarify/`) or its `spec.md` file
   directly. The scan covers the spec body's Overview / Why now /
   Goals / Non-goals / Decomposition / Open questions sections. The
   `## Clarifications` section gets appended to that `spec.md`.
2. **One `slice-NN-*.md` (slice-level scan).** The user names a
   specific slice file (`docs/specs/023-clarify/slice-01-clarify-skill-md.md`).
   The scan covers the slice's Goal / DoR / Acceptance Criteria /
   DoD / Anti-horizontal-phasing check. The `## Clarifications`
   section gets appended to that slice file (not to the parent
   spec.md).

**Mixed-mode ("scan the spec AND every slice") is explicitly NOT
supported by the MVP.** That requires per-doc bookkeeping and a
re-entry/resume protocol that's out of scope for this slice. If
the same friction surfaces three times across real usage, a future
slice 023-02 can ship a `.py` helper that orchestrates the loop.
Until then, the user re-runs the skill per document.

## Six-category taxonomy

For each category, the skill rates the target document Clear / Partial /
Missing. The scan is internal to the model — the rating is not shown
to the user unless an answer is sought. The categories below are aligned
with jig's slice template; spec-kit's nine-category taxonomy was slimmed
to six by dropping "Domain & Data Model" and "Interaction & UX Flow"
(which assume slots jig's slice template doesn't have) and folding
their substance into "Scope & Boundaries" where it applies.

### Scope & Boundaries

What is in-scope, what is out-of-scope, what is the boundary with
adjacent specs? Watch for unstated assumptions about which layer or
module the change touches.

What to check:

- Is the in-scope deliverable named in concrete terms (file paths,

From ramboz/jig, MIT.

More from ramboz/jig

Signals

Stars
7
Forks
1
Open issues
10
Last commit (this folder)
Oct 6, 2026 (22 days ago)
Last release
Oct 5, 2026 (24 days ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from ramboz

Cite this page

clarify skill. Agent Mart. https://agentmart.dev/skills/ramboz-clarify (last updated 2026-10-24)