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
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.
About
Use cases: security
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 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
- 0.624score
adr-workflow
ramboz
Scaffold, accept, index, and link Architectural Decision Records (ADRs).
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
analyze
ramboz
Cross-artifact consistency report for jig specs — a non-destructive six-category audit at CRITICAL/HIGH/MEDIUM/LOW severity, covering duplication, ambiguity…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
arch-review
ramboz
Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions.
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
bug-fix
ramboz
Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through REPORTED → DIAGNOSING → ROOT_CAUSED →…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
code-health
ramboz
Run a static-analysis pass on a project — detect the ecosystem (Python or Node), drive its linter (ruff / eslint, plus advisory pyright/complexity/ prettier…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
contracts
ramboz
Team baseline for external-interface contract artifacts: OpenAPI, JSON Schema, AsyncAPI, .proto, and GraphQL SDL, with spectral, ajv, buf, and…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
explain
ramboz
Explain jig vocabulary and artifacts in plain language.
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
pr-review
ramboz
Team baseline for PR and code review — produces scope, blockers, nits, and strengths.
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
reframe
ramboz
Re-baseline a jig corpus onto a moved load-bearing reference by drafting a keystone ADR and an affected-artifact disposition manifest.
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
security-review
ramboz
Team baseline for security review — a best-effort heuristic security pass over a diff or change-set.
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
slice-land
ramboz
Verify a finished slice is actually ready to land (tests green, DoD ticked, deviation log present, STATUS=DONE) and emit a deterministic landing checklist for…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
tdd-loop
ramboz
Drive the red-green-refactor loop for any non-trivial code change.
SkillAFreshness: A★ 7Claude Code +9
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
- Repository
- github.com/ramboz/jig
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ramboz
- 0.624score
analyze
ramboz
Cross-artifact consistency report for jig specs — a non-destructive six-category audit at CRITICAL/HIGH/MEDIUM/LOW severity, covering duplication, ambiguity…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
arch-review
ramboz
Team baseline for architecture, design-doc, and RFC review — produces summary, strengths, concerns, and open questions.
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
bug-fix
ramboz
Drive the teeth-gated lifecycle for reported defects: diagnose root cause, prove it, and prevent regression through REPORTED → DIAGNOSING → ROOT_CAUSED →…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
code-health
ramboz
Run a static-analysis pass on a project — detect the ecosystem (Python or Node), drive its linter (ruff / eslint, plus advisory pyright/complexity/ prettier…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
contracts
ramboz
Team baseline for external-interface contract artifacts: OpenAPI, JSON Schema, AsyncAPI, .proto, and GraphQL SDL, with spectral, ajv, buf, and…
SkillAFreshness: A★ 7Claude Code +9 - 0.624score
adr-workflow
ramboz
Scaffold, accept, index, and link Architectural Decision Records (ADRs).
SkillAFreshness: A★ 7Claude Code +9
Cite this page
clarify skill. Agent Mart. https://agentmart.dev/skills/ramboz-clarify (last updated 2026-10-24)