Skip to main content
NeVibeCode · repository · 59 items

mycelium: a set by haabe

The haabe/mycelium repository on GitHub: 59 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

About the repository

GitHub
haabe/mycelium
Stars
★ 54
License
MIT
Source updated
2026-10-24
In the catalog since
2026-10-27
dora-check skill dora-check assesses delivery health with metrics matched to the product type. Software checks use DORA and APEX; other products follow their own assessment paths. CX Codex +1 ★ 54repo stars diamond-render skill diamond-render turns .claude/diamonds/active.yml into a picture of the decisions recorded so far, in order, plus the ones still ahead. Useful at the end of an assessment. CX Codex +1 ★ 54repo stars diamond-progress skill diamond-progress is a Claude Code skill that records a diamond's decisions: target, experiment, build, release, and close, running theory gates and a Definition of Done checklist. CX Codex +1 ★ 54repo stars diamond-assess skill diamond-assess reviews a diamond’s current state, checks theory gates, and suggests the next move. It is built for the Mycelium framework. CX Codex +1 ★ 54repo stars devils-advocate skill devils-advocate puts a pending decision through pre-mortem, reversed assumptions and a blind adversarial pass, so a weak premise shows up before it ships. CX Codex +1 ★ 54repo stars delivery-bootstrap skill delivery-bootstrap detects the tech stack in an unfamiliar repository, verifies builds and tests, and offers matching development and security tooling. CX Codex +1 ★ 54repo stars definition-of-done skill A skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that walks the agent through a Definition of Done checklist before a task is closed. Runs on demand when a feature is ready for sign-off. CX Codex +1 ★ 54repo stars define-done skill define-done sets a measurable Definition of Done for a diamond: a change in behaviour that creates value, not a build list. Useful when work gets signed off on shipping alone. CX Codex +1 ★ 54repo stars cynefin-classify skill cynefin-classify — a skill for Claude Code and five other agent environments. It places a new problem into a Cynefin domain and picks the working method: checklists, expert analysis, or safe-to-fail probes. CX Codex +1 ★ 54repo stars cycle-render skill cycle-render — a skill for Claude Code, Codex, Cursor and other platforms that renders project cycle history from .claude/canvas/cycle-history.yml as a Gantt timeline and outcome distribution chart. CX Codex +1 ★ 54repo stars count skill count reads your repository and prints one line: when the first source file landed, how many decisions came before it, how many sessions there were. Sends nothing anywhere. CX Codex +1 ★ 54repo stars corrections-audit skill corrections-audit — a skill for Claude Code, Codex, Cursor and other platforms examines correction logs, uncovers recurring mistakes, and surfaces graduation paths to guardrails and anti-patterns. CX Codex +1 ★ 54repo stars canvas-update skill The canvas-update skill updates canvas files from new evidence, checks related sections, and logs the changes. It is designed for projects using Mycelium. CX Codex +1 ★ 54repo stars canvas-sync skill canvas-sync — a skill that synchronizes canvas state between team sessions through git. Keeps all team members aligned on product knowledge and decision history. CX Codex +1 ★ 54repo stars canvas-health skill canvas-health lints canvas knowledge base files for stale validation dates, missing fields, and evidence mismatches. Keeps model context consistent. CX Codex +1 ★ 54repo stars bvssh-check skill bvssh-check — a skill for Claude Code, Cursor and other editors that checks whether your current work aligns with Better Value Sooner Safer Happier principles. Run at diamond completion and periodically throughout development. CX Codex +1 ★ 54repo stars bias-check skill bias-check — a Claude Code skill that reviews cognitive biases before research or any significant decision. It runs before interviews, data analysis, and go-to-market choices. CX Codex +1 ★ 54repo stars assumption-test skill assumption-test is a Claude Code skill that designs the smallest test for a solution's riskiest assumption. It uses the AFTER model to choose the lightest meaningful test. CX Codex +1 ★ 54repo stars adopt skill adopt — a Claude Code skill that runs discovery on a project where code already exists. It reads the repo, fills in what the code can establish, and lists the questions the code cannot answer. CX Codex +1 ★ 54repo stars

41–59 of 59

More in NeVibeCode

Project sponsors

Companies that keep this analytics open