Run the craft feature-delivery workflow on a backlog id, a spec/PRD file, or a free-text feature description. Triggers - "apply the workflow", "use my default workflow", "craft this".
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add scolladon/craft --skill craft-run --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Craft Run?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/scolladon-craft-run-6b3119e6)More formats (shields.io, HTML) on the badges page.
---
name: craft-run
description: Run the craft feature-delivery workflow on a backlog id, a spec/PRD file, or a free-text feature description. Triggers - "apply the workflow", "use my default workflow", "craft this".
---
Input: $ARGUMENTS
Resolve the pipeline manifest first: run
`node "${CRAFT_ROOT}/engine/bin/pipeline-resolve.js" "${CRAFT_ROOT}/pipeline/default.yml"`
as a shell step before following the procedure below.
Follow `skills/run/SKILL.md` in this repository verbatim as the run procedure — its
preamble and numbered steps are the single source for flag parsing, manifest and
pipeline resolution, phase walking, and contract assembly; do not restate, summarize,
or re-derive them here. Thread $ARGUMENTS through exactly as that skill's own
`$ARGUMENTS` input.
Delegation: spawn each phase worker as its craft role subagent (the `craft-<role>`
definitions installed under `.cursor/agents/`) rather than working sequentially, and
pass each spawn its resolved model with `--model`. The per-role tier rides that launch
arg — the subagent frontmatter carries no model field. Batch spawns conservatively; do
not assume the spawn tool queues gracefully past its concurrent cap.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
