claude

unic-spec-review

Adversarial review of web specifications across Confluence pages & comments, Figma designs, and the live system. Produces Confidence-scored, Six-Hats-tagged Findings with an interactive Approval Loop that posts selected comments back to Confluence.

1 on GitHubby Unic AGv0.1.11LGPL-3.0-or-laterupdated 11 days ago
/

Plugin unic-spec-review from marketplace unic-agent-plugins in unic/unic-agents-plugins. Commands read from the repo's manifest — 9 days ago.

What it installs

Slash commands (3)

  • /unic-spec-review:review-spec

    Adversarial review of web specifications. Classify pasted Confluence, Figma, and live URLs; gather designs via Figma Dev Mode MCP and live observations via Playwright MCP; parallel eleven-agent fan-out, ranked hat-grouped triage. Read-only by default; --post activates the Approval Loop.

  • /unic-spec-review:setup-confluence

    Interactive setup wizard - writes ~/.unic-confluence.json with Confluence credentials

  • /unic-spec-review:spec-doctor

    Verify unic-spec-review prerequisites (Confluence credentials, Figma Dev Mode MCP, and Playwright MCP).

Subagents (11)

  • ambiguity-agent

    Ambiguity/Clarity Agent. Flags unmeasurable language, vague requirements, and undefined terms in a Confluence spec page. Emits structured Findings with Confidence Scores.

  • feasibility-agent

    Feasibility/Constraints Agent. Identifies requirements that exceed the detected stack's capabilities or impose disproportionate implementation costs. Emits structured Findings with Confidence Scores.

  • gaps-agent

    Gaps/Completeness Agent. Inspects a Confluence spec page for missing states, undefined behaviour, and absent acceptance criteria. Emits structured Findings with Confidence Scores.

  • green-agent

    Green Hat Agent. Surfaces alternatives, unexplored approaches, and creative options that the spec has not considered. Emits structured Findings with Confidence Scores.

  • internal-consistency-agent

    Internal-Consistency Agent. Finds self-contradictions, unresolved conflicts, and cross-page inconsistencies within the Confluence spec. Emits structured Findings with Confidence Scores.

  • non-functional-agent

    Non-functional Requirements Agent. Checks the Confluence spec for missing or under-specified non-functional concerns (accessibility, i18n, performance, SEO, responsive behaviour, error handling). Emits structured Findings with Confidence Scores.

  • red-agent

    Red Hat Agent. Surfaces likely points of user confusion, frustration, or emotional friction that the spec does not address. Emits structured Findings with Confidence Scores.

  • spec-versus-design-agent

    Spec-versus-Design Agent. Checks for inconsistencies between the Confluence spec page and any referenced Figma design artefacts or design intent. Emits structured Findings with Confidence Scores.

  • spec-versus-live-agent

    Spec-versus-Live Agent. Identifies mismatches between what the Confluence spec prescribes and how the live production system currently behaves. Emits structured Findings with Confidence Scores.

  • testability-agent

    Testability Agent. Assesses whether each requirement in the Confluence spec can be verified by the repo's actual test setup. Emits structured Findings with Confidence Scores.

  • yellow-agent

    Yellow Hat Agent. Challenges the stated value and justification of the spec - are the goals well-reasoned and worth the cost? Emits structured Findings with Confidence Scores.

View source on GitHub

More from unic/unic-agents-plugins

All 8 plugins →

AI-powered PR review with intent checking against Azure Boards and Jira work items, Confidence-scored Findings, and an interactive Approval Loop.

5 commands · 11 agents

1

[DEPRECATED — being replaced, see #677] A config-driven Harness for the SDLC — the AI development lifecycle — as an installable Claude Code plugin — main line /specs → /tickets → /build → /pr-review → /qa, plus /triage, /explore, /improve-architecture, and /cleanup. Four Archon workflows (build, qa, pr-review, explore) with human approval gates; the rest are commands/skills composing Matt Pocock's methods.

7 commands

1

pr-review

claude

[DEPRECATED — use unic-pr-review] Review Azure DevOps pull requests with multi-agent analysis and post threaded comments back to the PR.

1 command · 5 agents

1

Collects what a team learns about its repository from Claude Code sessions. A Stop hook says when learnings are due; a read-only subagent drafts .claude/rules/learned.md, and nothing is written without your yes.

1 skill · 1 agent · hooks

1

Keeps Claude concise. Ships the Terse Orwell output style, generic behaviour rules for every session and subagent, a per-turn language reminder, and /setup to write your Personal layer.

1 skill · hooks

1

Auto-format and lint files when Claude Code edits them. Runs Prettier + ESLint --fix after Write/Edit/MultiEdit/NotebookEdit.

hooks

1

Similar plugins

hyperframes

claudecodex

Recommended: all published HyperFrames skills in one versioned bundle. Create and render videos from HTML: the contract, film, captions, overlays, motion and look references, the CLI, the registry, media, Figma, slideshows and Remotion ports.

22 skills

heygen-com/hyperframes 83,516

figma

claude

Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and development workflows.

18 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

daisyUI Blueprint MCP server - (Needs paid license)

saadeghi/daisyui 42,821

Figma

claude

Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and development workflows.

18 skills · 1 MCP server

anthropics/knowledge-work-plugins 35,601

32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.

35 skills · hooks

alirezarezvani/claude-skills 29,725

Thirteen slash commands wrapping the designlang CLI: /extract (full design language → DTCG, Tailwind, Figma), /site (crawl a whole site → one canonical design system + consistency grade), /grade (shareable HTML report card + SVG badge), /battle (head-to-head graded comparison), /remix (restyle in 6 vocabularies — brutalist, swiss, art-deco, cyberpunk, soft-ui, editorial), /pack (one downloadable design-system bundle), /theme-swap (OKLCH-correct recolour around a new brand primary), /brand (full editorial brand-guidelines book — 13 chapters, hand-off-ready), /pair (fuse two designs across configurable axes — colours from one site, typography from another), /studio (live token-editor with component preview + export), /verify (rebuild from tokens and pixel-diff vs live for a fidelity score), /fidelity (score a clone vs the original — visual pixel-diff + motion fidelity — with a ranked correction plan), /gallery (build a shareable static gallery of measured clones).

2 skills · 14 commands

Manavarya09/design-extract 5,068

Maintain unic-spec-review?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins8 plugins