Figma Design System Builder
warpdotdev/warp
Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.
Draws a click-flow overlay on a section of laid-out Figma screens for static handoff: a dot on each clickable element, an elbow line with rounded corners and an open arrow at the destination screen.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figma-click-flow --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow .claude/skills/figma-click-flow && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "figma-click-flow" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow into .claude/skills/figma-click-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-click-flow", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flowType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figma-click-flow --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow .agents/skills/figma-click-flow && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "figma-click-flow" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow into .agents/skills/figma-click-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-click-flow", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figma-click-flow --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow .cursor/skills/figma-click-flow && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "figma-click-flow" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow into .cursor/skills/figma-click-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-click-flow", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/hashgraph-online/awesome-codex-plugins.git --path plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figma-click-flow --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow .gemini/skills/figma-click-flow && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "figma-click-flow" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow into .gemini/skills/figma-click-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-click-flow", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install hashgraph-online/awesome-codex-plugins figma-click-flowInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow .github/skills/figma-click-flow && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "figma-click-flow" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow into .github/skills/figma-click-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-click-flow", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins figma-click-flow --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow .opencode/skills/figma-click-flow && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "figma-click-flow" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow into .opencode/skills/figma-click-flow/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "figma-click-flow", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
figma-click-flowDraws a click-flow overlay on a section of laid-out Figma screens for static handoff: a dot on each clickable element, an elbow line with rounded corners and an open arrow at the destination screen.
Figma Click Flow is an agent skill from hashgraph-online/awesome-codex-plugins. Draws a click-flow overlay on a section of laid-out Figma screens for static handoff: a dot on each clickable element, an elbow line with rounded corners and an open arrow at the destination screen. figma.createConnector is not a function in Figma Design files, so each connector is emulated with one SVG import (hardened recipe in references/draw-overlay.js). Use when the user asks for a "click flow", "flow arrows", "wire screens", "turn this into a flow", or in Portuguese "vira em fluxo", "setas do fluxo".
Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/draw-overlay.js`). Compatibility notes: Writes to a Figma Design file through figma-console-mcp (figmaexecute, Desktop Bridge plugin in Figma Desktop) or through the official Figma MCP server…
It sits in Frontend & Design. It works with Figma. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 9e7b281. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships script files (JavaScript), which the agent can run.
Shell commands in SKILL.md call:
nodeFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Writes to a Figma Design file through figma-console-mcp (figma_execute, Desktop Bridge plugin in Figma Desktop) or through the official Figma MCP server (use_figma, Full seat, not validated by this repo; the recipe guards figma.loadAllPagesAsync, which Figma lists as not implemented there). Requires the figma-canon and figma-preflight skills.
From compatibility in the SKILL.md frontmatter.
Figma Click Flow loads about 3.9k tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 132 tokens; SKILL.md has 1,720 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from hashgraph-online/awesome-codex-plugins at commit 9e7b281, republished under its MIT licence (© hashgraph-online). 1,720 words, ~3,850 tokens.
.claude/skills/figma-click-flow/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Draws a printed user-flow overlay on a section of laid-out screens. Each connection: a red dot at the click target on screen A, an elbow line with rounded corners ending in an open arrow at screen B's nearest edge. Reference look: a flow section of one production file.
REQUIRED PREREQUISITE: load figma-canon + pass figma-preflight before any figma_execute write (the write path is the figma-console MCP server through its Desktop Bridge plugin). With only the official Figma MCP server connected, the write goes through use_figma on path B of figma-preflight Check 0 (not validated by this repo: keep writes small, read back every change), and Phase 4 validates with get_screenshot within the budget in figma-canon/references/rate-limit-recovery.md.
figma.createConnector throws not a function in Figma Design files (verified via figma_execute, field note 2026-05). CONNECTOR nodes that already exist in design files were created via the UI (Shift+L shortcut) and cannot be cloned: node.clone() errors with Cloning CONNECTOR nodes is not supported in the current editor. This skill therefore emulates the connector look by importing one SVG per connection through figma.createNodeFromSvg.
reactions on nodes) and wants the same connections visible in static handoff.(from-element-id -> to-screen-id) pairs.figma.createConnector directly.figma_execute after figma-preflight.Verified against a reference node in one production file. refConn in the right column is the reference connector.
| Property | Value | Source of truth |
|---|---|---|
| Stroke color | #E5484D | Neutral default, configurable. The reference used one dominant red in 20+ instances; that value was project-specific |
| Stroke weight | 4 px | refConn.strokeWeight === 4 |
| Path | Elbow with rounded corners, R = 12 px | connectorLineType: 'ELBOWED' + visual radius pixel-picked |
| Origin marker | Filled circle, r = 5 px (10 px diameter) | connectorStartStrokeCap: 'CIRCLE_FILLED' |
| End cap | Open arrow, two strokes back from tip at ±28°, length 12 px | connectorEndStrokeCap: 'ARROW_LINES' |
| Layer name | flow-overlay · click-connectors (kebab-case with a middle-dot separator, from one project's own layer canon; keep this exact name, because the rerun and the cleanup snippet find the overlay by it) | figma-canon/references/naming-canon.md |
The stroke color #E5484D is a neutral default and is configurable: override it through the strokeColor input (STROKE_COLOR in the recipe) when the file has a brand-specific accent.
sectionId: "123:456" # required
mode: from-prototype # default; OR "explicit" OR "auto-layout"
pairs: # used when mode === "explicit"
- from: "123:789" # element that gets tapped
to: "123:790" # destination screen
triggerFilter: ["ON_CLICK", "ON_PRESS"] # default; ignores hover/drag
includeOverlayActions: true # default; sheets count as navigation
strokeColor: "#E5484D" # default; see Visual canon
cornerRadius: 12 # default
strokeWeight: 4 # default
originAnchor: "auto" # default; "center" | "edge-toward-dest" | "auto"Each input is a constant in the CONFIG block of references/draw-overlay.js: sectionId is SECTION_ID, mode is MODE, pairs is EXPLICIT_PAIRS, triggerFilter is TRIGGER_FILTER, includeOverlayActions is INCLUDE_OVERLAY_ACTIONS, strokeColor is STROKE_COLOR, cornerRadius is CORNER_RADIUS, strokeWeight is STROKE_WEIGHT, originAnchor is ORIGIN_ANCHOR. The recipe also has DOT_RADIUS, ARROW_LEN, AUTO_LAYOUT_MIN_AR and AUTO_LAYOUT_ROW_GAP, which have no input above.
mode reference:
from-prototype (default): walks reactions[] on every descendant. Best when designer wired the prototype.explicit: uses pairs. Best when the caller has a known list (from a PRD, a spec that lists screen transitions, or a hand-curated list).auto-layout: groups top-level FRAMEs in the section into rows by Y, sorts each row by X, builds intra-row left-to-right pairs. Best when prototype isn't wired and screens are sequentially laid out (like a numbered catalog). Heuristic: verify visually before trusting; rows mixing scenarios may produce wrong connectors.AUTO_LAYOUT_MIN_AR). This filters out labels and dividers. For desktop or landscape screens, lower that constant, or the run returns drawn: 0.AUTO_LAYOUT_ROW_GAP) below the previous one starts a new row.originAnchor reference:
auto (default): bbox center for small nodes (<200×200 = buttons, list rows), edge-toward-dest for screen-sized nodes (any node at least 200 px in both dimensions). Right behavior for both prototype-driven mode and screen-level adjacency.center: always bbox center. Use when prototype reactions are wired on small interactive elements and you want the dot ON the button.edge-toward-dest: nearest-edge midpoint. Use for screen-to-screen adjacency where center would put the dot deep inside the screen body.If user just says "wire it up" with no detail, default to mode: from-prototype.
Walk up to the page ancestor (sections may be nested inside sections), call figma.loadAllPagesAsync(), then await figma.setCurrentPageAsync(pageNode). Use figma.getNodeByIdAsync exclusively: sync getNodeById errors under documentAccess: dynamic-page.
Server note for use_figma (official Figma MCP server): Figma's figma-use skill lists figma.loadAllPagesAsync() as not implemented in that runtime, and says a read of a member the node type does not have throws TypeError: node.X: no such property 'X' on Y node, optional chaining included (figma/mcp-server-guide, read 2026-10). So the recipe calls figma.loadAllPagesAsync() inside try/catch and carries on without it (setCurrentPageAsync loads the page anyway), and it checks "reactions" in n before reading reactions, because SECTION, SLICE and COMPONENT_SET nodes do not declare it. In figma_execute both guards change nothing. This repo has not run the recipe on use_figma.
Walk descendants of the section. For each node, inspect reactions[], and in each reaction read actions[] (the recipe falls back to the singular action field when actions is absent). Collect a pair when:
action.type === 'NODE' (navigate to frame), ORaction.type === 'OVERLAY' (open sheet/modal, counts as flow), ANDreaction.trigger.type is in the triggerFilter (default: ON_CLICK, ON_PRESS, ON_TAP).The recipe keeps a reaction that has no trigger.
Drop pairs where from or to cannot be resolved or lies outside the section's bounding box (likely external/cross-page links). Dropped pairs come back in the dropped array of the return value with a reason (node not found or outside section): report them instead of losing them silently.
If 0 pairs found, return early with a warning so the caller can switch to mode: explicit and supply pairs manually.
For each pair compute (all in absolute page space):
origin = anchor on from node's absoluteBoundingBox, picked by originAnchor: bbox center for small interactive nodes, nearest-edge-toward-dest for screen-sized FRAMEs (auto default), or as overridden.dest = nearest-edge midpoint of to frame's absoluteBoundingBox (left / right / top / bottom).(midX, origin.y) then (midX, dest.y) where midX = (origin.x + dest.x) / 2. Same right-angle topology as connectorLineType: 'ELBOWED'.cornerRadius (default 12), inserted as Q-curves.If |origin.y - dest.y| < 2 * cornerRadius, drop the elbow and draw a straight line (avoids degenerate corners).
Per pair, build an SVG string with:
<circle> at origin (origin marker).<path> with the elbow + Q-corners (the trunk).<polyline> arrowhead at dest.Import via figma.createNodeFromSvg(svgString), which returns a FRAME with vector children. Position the imported frame at (minX, minY) (the SVG's top-left in page space).
Coord-space rule (verified): SECTION children use section-local coords. After section.appendChild(overlay), set overlay.x = 0; overlay.y = 0 so overlay aligns with section's top-left. Then position each imported SVG frame as a child of overlay using overlay-local coords (subtract section absolute origin).
vectorPaths.windingRule: 'NONE' is accepted by the API (verified). Auto-fit moves a vector to its path's leftmost coord after vectorPaths is set; trust this rather than fighting it.
See references/draw-overlay.js for the complete hardened snippet. The same snippet is written to run in use_figma of the official Figma MCP server too, with the guards described in Phase 0 (not validated on that server by this repo); the timeout figures below are for figma_execute only.
figma_execute has a default timeout of 5000 ms and accepts up to 30000 ms. After a timeout or an error, do not rerun at once: this recipe removes the prior overlay and then draws a new one, so first read figma-canon/references/figma-execute-atomicity.md and the section "figma_execute timeout on bulk clone and font loads" in figma-canon/references/plugin-api-anomalies.md.
Use figma_capture_screenshot (plugin export). REST-backed screenshots return HTTP 429 (rate limited) after a handful of calls in a batch; see figma-canon/references/rate-limit-recovery.md. Do not use figma_take_screenshot for large sections.
As of figma-console-mcp v1.40.8, figma_take_screenshot uses the Desktop Bridge plugin when connected and falls back to the REST API, while figma_capture_screenshot always uses the plugin runtime and needs the bridge. The rule above still holds: figma_capture_screenshot is the call that always stays on the plugin runtime.
Check:
Idempotent rerun: skill auto-removes any prior flow-overlay · click-connectors frame inside the section before drawing. To remove without redrawing (here section is the section node, from await figma.getNodeByIdAsync(sectionId)):
const overlay = section.findOne(n => n.name === 'flow-overlay · click-connectors');
if (overlay) overlay.remove();| Mistake | Fix |
|---|---|
figma.createConnector(...) | Not a function in design files; emulate via SVG import |
node.clone() on existing CONNECTOR | Throws "Cloning CONNECTOR nodes is not supported" |
figma.getNodeById | Use getNodeByIdAsync; sync version errors under dynamic-page |
Set overlay.x = section.x before append | Section children use LOCAL coords, produces double offset; set x=0; y=0 AFTER append |
| Validate with a REST-backed screenshot | figma_take_screenshot returned 429 on the large sections of one production file; use figma_capture_screenshot |
Filter only action.type === 'NODE' | Misses OVERLAY (sheet open), common in mobile flows; include both |
Ignore reaction.trigger.type | Hover/drag triggers pollute the overlay; filter to ON_CLICK/ON_PRESS/ON_TAP |
| Draw nothing when prototype unwired | Detect 0 pairs and return early with a warning, not a silent empty overlay |
| Sharp 90° corners | Use Q-curves with R=12 to match reference rounded look |
Passing section.parent to figma.setCurrentPageAsync | Walk up parent chain until type === 'PAGE'; nested sections break naive section.parent |
| Need | Call |
|---|---|
| Discover prototype reactions | node.reactions[].action.{type:'NODE'|'OVERLAY', destinationId} (the recipe reads actions[] and falls back to action) |
| Filter by trigger | ['ON_CLICK','ON_PRESS','ON_TAP'].includes(reaction.trigger?.type) |
| Build connector SVG | <circle> + <path> (elbow w/ Q-corners) + <polyline> arrow |
| Import SVG | figma.createNodeFromSvg(svgString) returns a FRAME with VECTOR children |
| Default red | #E5484D (rgb 0.898, 0.282, 0.302) |
| Cleanup | section.findOne(n => n.name === 'flow-overlay · click-connectors')?.remove() |
figma-canon + figma-preflight: required before any figma_execute write.figma-orient: only run if file is unfamiliar this session; skip otherwise.references/draw-overlay.js: full hardened snippet, copy + parameterize for use. It is a figma_execute body (top-level await and return), not a standalone Node script.figma-canon/references/figma-execute-atomicity.md: what to do after a figma_execute timeout or error before retrying.© hashgraph-online, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 9e7b281
Figma Click Flow next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Figma Click Flow this skillhashgraph-online/awesome-codex-plugins | 1.3k | — | ~3.9k | Automated safety check: Pass | MIT | |
| Figma Design System Builderwarpdotdev/warp | 65k | 2 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Figma use_figma Plugin API Ruleswarpdotdev/warp | 65k | 4 repos | ~4.4k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Design to Codewarpdotdev/warp | 65k | 4 repos | ~2.9k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Design System Rules Generatorwarpdotdev/warp | 65k | 3 repos | ~4.6k | Automated safety check: Pass | AGPL-3.0 | |
| Figma Code Connect Componentswarpdotdev/warp | 65k | 2 repos | ~4.2k | Automated safety check: Pass | AGPL-3.0 |
warpdotdev/warp
Builds or updates a design system in Figma from a codebase in ordered phases: discovery, variables and tokens, components, theming and documentation, with checkpoints.
warpdotdev/warp
Required groundwork before any use_figma call: the rules and reference files for running JavaScript in a Figma file through the Plugin API without common failures.
warpdotdev/warp
Turns a Figma frame or component into production code that matches the design, using the Figma MCP server and the project's own design system.
warpdotdev/warp
Creates project-specific design system rules from your codebase so coding agents implement Figma designs with your components, naming and tokens.
warpdotdev/warp
Maps published Figma components to their code implementations with Code Connect, using the Figma MCP suggestion and mapping tools.
ZeroZ-lab/cc-design
High-fidelity HTML design and prototype creation. An agent skill from ZeroZ-lab/cc-design.
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
hashgraph-online/awesome-codex-plugins
Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
Works with
Categories
Draws a click-flow overlay on a section of laid-out Figma screens for static handoff: a dot on each clickable element, an elbow line with rounded corners and an open arrow at the destination screen. Figma Click Flow is an agent skill from hashgraph-online/awesome-codex-plugins. Draws a click-flow overlay on a section of laid-out Figma screens for static handoff: a dot on each clickable element, an elbow line with rounded corners and an open arrow at the destination screen.
Figma Click Flow fits situations like: the user asks for a click flow; turn this into a flow; in Portuguese vira em fluxo.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a claude-code`. Or copy the skill folder (plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow in hashgraph-online/awesome-codex-plugins) into .claude/skills/figma-click-flow in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a codex`. Or copy the skill folder (plugins/thiagoxikota/figma-maxxing/skills/figma-click-flow in hashgraph-online/awesome-codex-plugins) into .agents/skills/figma-click-flow in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill figma-click-flow -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/figma-click-flow, .gemini/skills/figma-click-flow, .github/skills/figma-click-flow and .opencode/skills/figma-click-flow in your project.
Going by SKILL.md and its folder, Figma Click Flow needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: Node.js. Compatibility (from SKILL.md): Writes to a Figma Design file through figma-console-mcp (figma_execute, Desktop Bridge plugin in Figma Desktop) or through the official Figma MCP server (use_figma, Full seat, not validated by this repo; the recipe guards figma.loadAllPagesAsync, which Figma lists as not implemented there). Requires the figma-canon and figma-preflight skills..
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Figma Click Flow is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.9k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.9k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Figma Click Flow: Figma Design System Builder (warpdotdev/warp, 65k stars), Figma use_figma Plugin API Rules (warpdotdev/warp, 65k stars), Figma Design to Code (warpdotdev/warp, 65k stars) and Figma Design System Rules Generator (warpdotdev/warp, 65k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,255 GitHub stars. The repository holds 714 skills in this directory. The repository was last updated on October 9, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.