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
user-needs-map skill Maps user needs with Rich Allen's User Needs Mapping method. It separates needs from solutions and flags underserved ones for an Opportunity Solution Tree.
CX Codex +1
★ 54repo stars
user-interview skill user-interview guides story-based interviews about what people have actually done, then helps capture findings through a JTBD lens. Use it to explore past experiences instead of testing opinions about hypothetical features.
CX Codex +1
★ 54repo stars
usability-check skill usability-check runs a screen-level usability review against Nielsen's 10 heuristics and returns a pass/partial/fail table, useful before calling UI work done.
CX Codex +1
★ 54repo stars
threat-model skill Runs STRIDE threat modeling for features and system architectures. Evaluates data flows, trust boundaries, and AI vulnerabilities before code ships.
CX Codex +1
★ 54repo stars
theory-fidelity skill The theory-fidelity skill checks whether a project’s claimed theories are reflected in its mechanisms and whether those mechanisms match the theories. Run it after adding a theory or changing its implementation.
CX Codex +1
★ 54repo stars
team-shape skill team-shape — a Claude Code skill that checks team structure against Team Topologies by Skelton and Pais. Looks at cognitive load, interaction modes, and Conway's Law.
CX Codex +1
★ 54repo stars
start skill start combines Mycelium project initialization and a ten-minute discovery interview into a single entry flow.
CX Codex +1
★ 54repo stars
setup skill setup — a Claude Code skill that prepares a project for the Mycelium plugin: state directories and starter files. Runs once after installing the plugin, before any other skill.
CX Codex +1
★ 54repo stars
service-check skill service-check scores a service or feature against Lou Downe's 15 principles of good services and returns a Pass / Partial / Fail table with the fixes that matter most.
CX Codex +1
★ 54repo stars
security-review skill security-review runs OWASP Secure by Design assessments tailored to your product code and architecture.
CX Codex +1
★ 54repo stars
scaffold-cost-check skill scaffold-cost-check — a Claude Code skill that measures the token cost of Mycelium's scaffold. Runs as a one-shot audit and reports how much context CLAUDE.md, the engine, harness, canvas and memory consume.
CX Codex +1
★ 54repo stars
retrospective skill Runs a structured retrospective after every completed delivery cycle. It records the cycle in cycle-history.yml, captures prediction calibration, and feeds the learning loop.
CX Codex +1
★ 54repo stars
render skill Dispatcher for the Mycelium visualization fleet. It routes rendering requests to specialist skills or lists all available project canvases.
CX Codex +1
★ 54repo stars
regulatory-review skill regulatory-review — a Claude Code skill that decides whether a product falls under AI regulation. It runs EU AI Act risk classification and Article 50 transparency checks.
CX Codex +1
★ 54repo stars
reflexion skill Runs the reflexion loop: implement, validate, self-critique, then decide. Each pass ends with a verdict — done, fix, or escalate after three rounds.
CX Codex +1
★ 54repo stars
receipt-render skill receipt-render generates a shareable, privacy-checked one-page work receipt from a completed Mycelium diamond.
CX Codex +1
★ 54repo stars
purpose-properties skill purpose-properties — a Claude Code skill that runs on six platforms. It reads purpose.yml and pulls out checkable properties no solution may contradict.
CX Codex +1
★ 54repo stars
prompt-optimizer skill prompt-optimizer — a Claude Code skill that A/B tests CLAUDE.md edits against eval benchmarks. Run it when agent instructions stop producing stable output and you need to measure which wording works.
CX Codex +1
★ 54repo stars
privacy-check skill privacy-check — a skill for Claude Code and five other platforms that assesses a feature or system against the seven Privacy by Design principles and GDPR. It walks through data collection, storage, access and breach readiness.
CX Codex +1
★ 54repo stars
preflight skill preflight is a Claude Code skill that checks scope, constraints, project readiness, and success criteria before a delivery task.
CX Codex +1
★ 54repo stars
ping skill ping is a Claude Code skill that returns a marker line to check that the Mycelium plugin is installed and invoked by namespace. It is not for everyday use.
CX Codex +1
★ 54repo stars
ost-render skill ost-render renders .claude/canvas/opportunities.yml trees into Mermaid mindmaps or structured lists with built-in attribution and privacy controls.
CX Codex +1
★ 54repo stars
ost-builder skill ost-builder — a Claude Code skill for turning research into an Opportunity Solution Tree. It also runs in Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode — never from brainstorming.
CX Codex +1
★ 54repo stars
mocked-persona-interview skill mocked-persona-interview is a Claude Code skill for simulated persona interviews when real users are out of reach. It sets rules for varied perspectives and marking speculation.
CX Codex +1
★ 54repo stars
migrate-from-legacy skill migrate-from-legacy is a Claude Code skill that moves a Mycelium project from legacy installation to plugin form while preserving project state.
CX Codex +1
★ 54repo stars
metrics-pull skill metrics-pull — a skill for Claude Code and five other agentic coding platforms. Pulls snapshots from every configured metric source, computes deltas against the previous run, flags unexplained signals and drafts canvas evidence entries.
CX Codex +1
★ 54repo stars
metrics-detect skill metrics-detect — a skill for Claude Code, Codex, Cursor and other agents that scans a project and identifies which external metric sources apply — GitHub, Plausible, Stripe and more.
CX Codex +1
★ 54repo stars
log-evidence skill log-evidence records offline findings from interviews and user research back into Mycelium canvas files.
CX Codex +1
★ 54repo stars
launch-tier skill The launch-tier skill for Claude Code builds a release scale from past launches and aligns product and go-to-market expectations, with an adapted exercise for solo work.
CX Codex +1
★ 54repo stars
jtbd-map skill jtbd-map splits customer work into functional, emotional and social jobs, then saves the map to a canvas file.
CX Codex +1
★ 54repo stars
interview skill interview is a Claude Code skill that runs a structured discovery conversation when kicking off a repository, clarifying product purpose, vision, and scope.
CX Codex +1
★ 54repo stars
ice-score skill ice-score — a skill for Claude Code, Codex, Cursor, Copilot and Gemini CLI that scores solutions or opportunities with Itamar Gilad's ICE method: Impact × Confidence × Ease, each 0–10, where Confidence comes from his Confidence Meter.
CX Codex +1
★ 54repo stars
harms-check skill harms-check — a skill that scans a user-facing product for deceptive patterns and foreseeable misuse before release, the harms that security and privacy gates don't look for.
CX Codex +1
★ 54repo stars
handoff skill handoff creates structured briefs and mobile-friendly capture templates for offline human tasks like user interviews, observations, and outreach.
CX Codex +1
★ 54repo stars
gist-plan skill gist-plan is a skill for Claude Code, Codex, Cursor and other IDEs that turns goals into ideas, steps and tasks using Gilad's Evidence-Guided framework. It structures experiment-based planning.
CX Codex +1
★ 54repo stars
friction-log skill friction-log drafts an honest write-up of where working with Mycelium felt confusing or slow. You edit it and decide whether it goes anywhere.
CX Codex +1
★ 54repo stars
framework-health skill framework-health — a skill for the Mycelium framework that tracks cycle velocity, discard patterns, confidence calibration, gate hit rates, and regressions. Runs quarterly or after every 20 completed cycles.
CX Codex +1
★ 54repo stars
feedback-review skill feedback-review — a Claude Code skill that aggregates feedback signals from all active Mycelium loops. It reports health, trajectory, overdue checks, regression warnings, and Goodhart's Law violations.
CX Codex +1
★ 54repo stars
fan-out skill fan-out — a skill for Claude Code, Codex, Cursor and other platforms that spawns workers in parallel to explore multiple solutions, then collects their scorecards and picks a winner by evidence.
CX Codex +1
★ 54repo stars
eval-runner skill eval-runner — a skill for Claude Code, Codex, Cursor and other agents that runs YAML eval scenarios through a reflexion loop and writes results to JSON.
CX Codex +1
★ 54repo stars
1–40 of 59