ba-design-completeness

ba-design-completeness is a skill for Claude Code, Codex from evolplus/talos. It costs 93 tokens per session (1,603 once invoked), scanned A, original, Apache-2.0.

A review skill for checking whether approved software requirements are fully covered by a user-interface design handoff.

In plain words
What is it for?
Use it after a UI/UX designer produces a handoff, to verify design coverage against the requirements.
Why use it?
It helps find missing screens, states, components, platform details, or colors before frontend development starts.

Skill for Claude CodeCodex

Part of the talos plugin — 55 skills, 2 commands, 4 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/evolplus/talos/ba-design-completeness
Any agent
npx skills add evolplus/talos --skill ba-design-completeness
Clone the repo
git clone --depth 1 https://github.com/evolplus/talos

Made for: Claude Code, Codex.

Or install talos, the plugin that ships this one along with the rest of its 55 skills, 2 commands, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ba-design-completeness

README.md
[![agentmods](https://agentmods.dev/badge/skills/evolplus/talos/ba-design-completeness.svg)](https://agentmods.dev/skills/evolplus/talos/ba-design-completeness)
Your own site
<a href="https://agentmods.dev/skills/evolplus/talos/ba-design-completeness"><img src="https://agentmods.dev/badge/skills/evolplus/talos/ba-design-completeness.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,603 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00093 $0.01603
Opus 5 $0.00046 $0.00801
Sonnet 5 $0.00019 $0.00321
Haiku 4.5 $0.00009 $0.00160

Measured 4d ago against content hash 15dab80009f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ba-design-completeness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ba-design-completeness/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BA Phase 3 — Design Completeness Verification

When to use

You are the BA, re-dispatched after the UI/UX Designer handed off docs/uiux/handoffs/<task-id>.md. Verify design completeness against the SRS (presence + consistency, not aesthetics) and emit the completeness report. This runs after SRS sign-off and before FE Dev may start.

Phase 3 — Post-Sign-off: Design Completeness Verification

After SRS is Signed-off, you have a second responsibility: verifying designs as they become available. This phase runs after SRS sign-off and before FE Dev can start.

You do not require designs to exist for sign-off. You verify them when the UI/UX Designer hands them off.

Trigger

You are re-dispatched when:

  • UI/UX Designer has produced docs/uiux/handoffs/<task-id>.md (design sub-status design-ready-for-review in master plan), regardless of which mode produced it (create, revise, or incorporate), OR
  • The Orchestrator detects that SRS has UI requirements but ## Design References is missing or incomplete (in which case you flag this as an Open Question pre-sign-off, but do not block sign-off on it)

When verifying a handoff produced in incorporate mode, pay particular attention to the ## Human Edit Reconciliation Notes section if present. Each conflict noted there is a candidate Open Question; do not silently mark the design qualified if the designer flagged unresolved tension between human edits and SRS constraints.

Design Completeness Check

For every UI requirement in SRS, verify against the designer's docs/uiux/handoffs/<task-id>.md:

  1. Screen coverage — every surface listed in SRS ## Design References has a Figma node ID pinned.
  2. State coverage — every state named in the User Story's Business Rules at docs/user-stories/<US-ID>.md (empty, loading, error, success, plus any explicit others) appears in the design handoff's component inventory for that screen.
  3. Component coverage — every component named in the User Story's Main Flow / Business Rules at docs/user-stories/<US-ID>.md for a screen appears in that screen's component inventory.
  4. Design Element Manifest coveragedocs/uiux/handoffs/<task-id>.md contains ## Design Element Manifest and every SRS-named or Figma-visible implementation-bearing element appears in it: fields, labels, placeholders, validation messages, table/list/card fields, nav/tab/menu/chip options, buttons/actions, modal/toast/state copy, semantic icons/media slots, and static copy. Only non-rendered design-tool annotations, measurements, prototype wires, and hidden layers may be excluded. Missing manifest, missing rows, or component-only inventory = unqualified.
  5. Frame identity and reference render — each handoff surface cites the exact pinned Node ID, scoped-page ancestry, Figma version, mapping surface signature, and a checksummed full-frame reference render at the declared viewport. Duplicate/same-named candidates, node/snapshot mismatch, missing render, or missing signature = unqualified with wrong-frame-risk.
  6. Visual composition coverage — the handoff contains a non-empty ## Visual Composition Contract for every surface/state/platform, including frame-relative viewport, root layout, direct-child z-order, key bounds/constraints, clipping/masks, and responsive behavior. A component inventory without composition geometry = unqualified.
  7. Asset coverage — the handoff contains a non-empty ## Asset Export Manifest. Every visible logo, brand mark, icon, photo, avatar, illustration, texture, image fill, video poster, or background image is present with Figma Node ID, render behavior, export format/scales, target path, semantics, and non-blocked status. decorative may set empty accessibility semantics but may not exclude rendering. Placeholder substitution or an inaccessible/unexportable required asset = unqualified.
  8. Color palette — colors listed in docs/uiux/handoffs/<task-id>.md are consistent with SRS brand / design system requirements. Flag any color outside the declared palette.
  9. Platform coverage — for each surface, every platform listed in SRS Platform column has a corresponding variant in the handoff.
  10. Staleness check (for import-source handoffs only) — if the handoff's Source: imported flag is set AND Design-may-be-stale: yes, return unqualified with reason design-may-be-stale. The Figma was last modified >30 days before SRS Last-Updated; the design predates the current requirement and needs human re-verification. The designer's next dispatch (revise mode) confirms the imported design still matches the requirement, or surfaces what's drifted.
  11. Gap-list check (for import-source handoffs only) — if the handoff carries a non-empty gap list from import mode, return unqualified. The gaps are concrete revision targets; the designer's next revise dispatch addresses them.

Read the full file on GitHub · 85 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 85 lines · 93 tokens per session scan A 15dab80009f9

Subscribe to this mod's changes

ba-design-completeness is a skill published in the GitHub repository evolplus/talos (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,603 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

material-ui-tailwind

Integrates Material UI with Tailwind CSS v4 using cascade layers (enableCssLayer, @layer order) and documents Tailwind v3 interoperability (preflight, important, injectFirst, portals). Use when combining MUI with Tailwind utilities, slotProps className, or theme token bridges.

mui/material-ui · 67 tokens

hallmark

Anti-AI-slop design skill for greenfield pages, audits, redesigns, and design extraction from URLs or screenshots. Use when the user asks to build a new app or landing page, wants to redesign something, invokes Hallmark by name, or uses audit/redesign/study.

Nutlope/hallmark · 61 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens

accessibility

Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.

microsoft/hve-core · 47 tokens

desktop-principles

Desktop-specific UX principles - hover states, pointer precision, keyboard shortcuts, multi-window, focus management. Covers macOS, Windows, Linux, web desktop.

Jwuthri/Tracely-ai · 36 tokens

taiyi-ui-design

TaiyiForge 第 4 阶段 — UI/UX 契约,产出 UI-DESIGN.md。四端通用。.

Dong90/oh-my-taiyiforge · 35 tokens