Design
- When to use it
- On-brand visual work: capture a brand once as a brand.json the Word and PowerPoint converters apply, and plan a deck slide by slide for its audience.
- Covers
- Create on brand collateral (2), Explain it to decision makers (1)
- Where you decide
- No gated loop of its own; the skills run one at a time.
- Size
- 7 skills · 0 loops
npx skilldrop-cli install --pack design
Installs 7 skills, including core.
Other ways to install
The pack's loops too, each as an invokable skill:
npx skilldrop-cli install --loop --pack design
In Claude Code, as a plugin (after /plugin marketplace add sananthanarayan/skilldrop):
/plugin install design@skilldrop
Into Cursor, Kiro or another IDE:
npx skilldrop-cli install --pack design --ide cursor
Start here: Capture your brand once, then outline a deck for it
Paste this into your agent:
Set up our brand kit from this logo (./brand/logo.png) and these colours: #0E5A46, #F2A541. Then outline a five-slide deck from ./notes/q3-update.md for Thursday's team meeting.
- Before you start
- Your logo as a PNG file, and your brand colours if you know them
- How to tell it worked
- brand-kit writes brand.json and a one-page BRAND.md with contrast checked, and slide-outliner returns a slide-by-slide outline with takeaway titles and speaker notes, sized to the time.
- If nothing happens
- If brand-kit does not activate, ask for it by name ("use brand-kit"). To turn the outline into a .pptx in your brand, the converters pack's md-to-pptx takes the same brand.json with --brand.
A typical session
When: You need a deck or document in your own branding and do not want to answer the brand questions every time.
You bring:
- your logo as a PNG, and a white version if you have one
- brand colours, fonts or a PowerPoint template, if you know them
- the content: the doc or points for the deck
- the audience and how long you have to present
-
- You
- Hand over your logo, colours and any brand guidelines or template.
- You get
- A brand.json and a one-page BRAND.md, with text contrast checked and each value traced to where it came from.
-
- You
- Give it the content, the audience and the time slot.
- You get
- A slide-by-slide outline with takeaway titles, key points, speaker notes, backup slides for likely questions, and a slide-count check against the time.
-
- You
- Run it on the outline against the deck rubric.
- You get
- A verdict and severity-tagged findings with a fix for each.
- You decide
- Build the deck from the outline, apply the changes, or rework it.
You end with: A reusable brand kit and a reviewed outline, ready to become an on-brand .pptx with md-to-pptx from the converters pack.
Compare Design with another pack
Skills in this pack (2)
- brand-kit Capture a brand once as a reusable brand.json — logo files (and an on-dark version), colour roles as hex codes, heading and body fonts, voice, imagery rules, a PowerPoint template, contact details and the legal footer — plus a one-page BRAND.md, with text contrast checked and every value traced to where it came from. Use when the user wants decks, flyers or documents in their branding, says "use our brand", "here's our logo and colours", "set up our brand kit", or hands over brand guidelines. standard
- slide-outliner Outline an architecture review or technical pitch deck — slide titles, key points per slide, and speaker notes. Does NOT generate PowerPoint/Keynote files; produces a structured outline the user can paste into any deck tool. Use when the user is preparing for an architecture review, design review, sales pitch, partner meeting, or steering-committee presentation. standard
Included from core (5)
- brief-intake Turn raw mess — a Slack thread, meeting transcript, Jira ticket, half-written Notion page, email chain, or paragraph of free-form context — into a structured brief that the downstream skill (adr-generator, design-doc, runbook-generator, exec-summary, slide-outliner) can consume without further intake. Use whenever the user has unstructured source material and is about to invoke another skilldrop skill, or when a draft is missing the load-bearing context the next step will need. standard
- context-graph Map the decisions behind a codebase from its ADRs, RFCs and design records — each record's status and date, what supersedes or amends what, which records cite which, the files and folders each decision governs, and with git the commits that implemented it and the commits that changed each decision's code since it was made, and who made them — then answer "why is it like this?" from the record and check the record is still true. Finds supersessions only one side records, current decisions pointing at code that is gone, code that has drifted from its decision, two current decisions governing the same path, and references to records that don't exist. Use when the user asks "why do we use X", "which decisions govern this file or service", "is this ADR still current", "has the code drifted since we decided this", "are our ADRs out of date", "what was decided before I change this", wants a map of the architecture decisions, or is onboarding onto a codebase's history. standard
- council-review Convene a council of distinct senior-engineer personas (Architect, Security, Operator/SRE, Pragmatist, User-Advocate, plus optional bench seats) to deliberate a decision, design, or code change — each takes an independent stance, the genuine disagreements are surfaced as named cruxes, and a Chair issues a reconciled verdict that records dissents and states what would change the decision. The "Claude Council." Use when a choice has real tradeoffs and one reviewer's voice isn't enough: architecture decisions, risky changes before merge, RFC/design scrutiny, "should we adopt X?", rewrite-vs-refactor, or a pre-mortem. heavy
- doc-critique Review an existing document — ADR, design doc, runbook, exec summary, tech-comparison matrix, deck outline, decision log — and produce a structured critique against the same quality bars the skilldrop generators enforce. Categorizes findings by severity (blocker / major / minor / nit), points to the exact section/line, and suggests a concrete fix for each. Use when the user wants a second-pair-of-eyes review before sharing a doc, or has been handed someone else's artifact and wants to know what to push back on. heavy
- output-hygiene Review agent-written text before it ships and strip the machine artifacts it carries — invisible Unicode, non-breaking spaces, homoglyphs, harness-added provenance trailers, trailing chat closers — then flag the prose tells a script cannot catch, each quoted with a rewrite. Use when the user wants to clean up AI-generated output, asks to remove a Claude watermark, attribution footer, or "Generated with" line, wants a draft that does not read as machine-written, or needs a pre-ship hygiene pass on a document, commit message, or pasted chat answer. standard