Опишете задачата
Към всички skills

understand-figma

Egonex-AI · Дизайн

Analyze a Figma file via the Figma REST API and generate an interactive design knowledge graph (pages, screens, components, component sets, instances, design tokens) with a kind:"design" dashboard.

Оригинален текст · няма потвърден превод на български
Платформи: Не са посочениНиво: СредноВ индекса: 19.09.2026 г.Обновен в GitHub: 12.09.2026 г.

Теми: antigravity-skills · business-knowledge · claude-code · claude-skills · codebase-analysis · codex · codex-skills · developer-tools-ai-agent · gemini-cli-skills · karpathy-llm-wiki · knowledge-base · knowledge-graph · memory · opencode-skills · pi-agent

Първо прочетете инструкцията.

Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.

Оригинален SKILL.md
GitHub хранилище
Звезди на репото
83 826
Лиценз
MIT
Последна проверка на записа
19.09.2026 г.

Добавете в своя инструмент.

Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.

npx skills add Egonex-AI/Understand-Anything

Страницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.

Откъс от SKILL.md

Началото на файла на автора, без превод.

/understand-figma

Analyzes a Figma file and produces an interactive design knowledge graph in the existing dashboard.

Prerequisites

  • FIGMA_TOKEN environment variable — a Figma personal access token (create one at https://www.figma.com/settings). If it is missing, STOP and tell the user:

    Set a Figma token first: create one at figma.com/settings, then export FIGMA_TOKEN=<token>.

  • Node ≥ 22, pnpm ≥ 10.

Security: the token is read only from the environment and travels only in the X-Figma-Token request header. Never write it to the graph, meta.json, logs, or intermediate files. This skill makes outbound calls to api.figma.com — unlike /understand, it is not fully offline. Tell the user this once.

Phase 0 — Pre-flight

  1. Parse $ARGUMENTS for a Figma URL or bare file key (the non-flag token) and an optional --language <lang>.
  2. Resolve PROJECT_ROOT to the current working directory. Resolve the data directory $UA_DIR once and reuse it for every read and write below: UA_DIR="$PROJECT_ROOT/$([ -d "$PROJECT_ROOT/.understand-anything" ] && echo .understand-anything || echo .ua)" — the legacy .understand-anything/ when it already exists, otherwise the new .ua/. Because each phase may run in a fresh shell, carry $UA_DIR forward like $PROJECT_ROOT, re-resolving it with the same line if a later command block needs it.
  3. Resolve PLUGIN_ROOT and ensure core is built (same logic as /understand Phase 0.1.5). If packages/core/dist/figma/index.js is missing, run: 
    cd "$PLUGIN_ROOT" && (pnpm install --frozen-lockfile 2>/dev/null || pnpm install) && pnpm --filter @understand-anything/core build
  4. mkdir -p $UA_DIR/intermediate.

Phase 1 — FETCH & PARSE (deterministic)

Run the bundled scan script (<SKILL_DIR> is this skill's directory):

FIGMA_TOKEN="$FIGMA_TOKEN" node <SKILL_DIR>/figma-scan.mjs "$PROJECT_ROOT" "<url-or-key>"

It writes $UA_DIR/intermediate/scan-manifest.json and prints the node counts. Relay the counts to the user. If it exits non-zero, relay stderr and STOP.

If the scan prints UP_TO_DATE, report "Design graph is already up to date for this Figma file version" and STOP. To force a full rebuild, re-run with UNDERSTAND_FIGMA_FORCE=1 set in the environment.

Phase 2 — ANALYZE (LLM enrichment)

Целият SKILL.md в GitHub