haabe

Run eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.

Aggregate feedback signals across all active loops. Reports health, trajectory, overdue checks, regression warnings, and Goodhart's Law violations.

Generate structured handoff materials for offline human tasks (interviews, observations, outreach). Creates actionable briefs with phone-friendly capture templates.

Use to prioritize solutions or opportunities using ICE scoring with evidence-backed confidence.

Smoke-test skill that confirms the Mycelium plugin loaded correctly. Returns a deterministic marker string for plugin-shape validation. Not for end-user invocation in normal use.

Use to assess regulatory applicability for products that may fall under AI regulation (EU AI Act, Article 50 transparency).

Use to evaluate a service or feature against Downe's 15 principles of good services.

Assess team structure against Skelton's Team Topologies. Evaluate cognitive load, interaction modes, and Conway's Law alignment.

Evaluate user-facing interfaces against Nielsen's 10 Usability Heuristics. Complements /mycelium:service-check (Downe = service-level quality, Nielsen = interface-level quality).

Map user needs independently of solutions using Allen's User Needs Mapping methodology. Identifies underserved needs that feed into the Opportunity Solution Tree.

GIST planning workflow. Structure goals into ideas, steps, and tasks using Gilad's evidence-guided framework.

Use when onboarding a new product/project. Progressive interview to understand purpose, vision, north star, and competitive landscape.

Accessibility audit against WCAG 2.1 AA. Checks semantic HTML, ARIA, keyboard navigation, color contrast, screen reader compatibility.

Use to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.

Synchronize canvas state across team sessions via git. Ensures all team members see the same product knowledge.

Update canvas sections with new evidence. Ensures canvas stays current as the single source of truth.

Use when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate methods.

Use when starting implementation on a new or unfamiliar codebase. Auto-detects tech stack and sets up development context.

Use to evaluate the current state of a diamond. Checks theory gates, confidence levels, and recommends next action.

Assess delivery health metrics. For software: DORA + APEX. For content/AI/service products: product-type-appropriate metrics.

Design the smallest viable test to validate or invalidate a critical assumption. Based on Torres's assumption testing framework, organized by Gilad's AFTER model (Assessment → Fact-Finding → Tests → Experiments → Release Results).

Use before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.

Lint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.

Use to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns.

Use to verify a feature/story meets all Definition of Done criteria before marking complete.

Systematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overconfidence.

Progress a diamond from one phase to the next. Runs all required theory gate checks, validates evidence, and at Deliver->Complete runs the executable Definition of Done checklist.

Classify releases into launch tiers and plan go-to-market. Based on Lauchengco's Loved framework.

Parallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and select winners.

Evaluate Mycelium's own process effectiveness. Measures cycle velocity, discard trends, confidence calibration, gate effectiveness, regression rate. Run quarterly or every 20 cycles.

Map user Jobs to be Done across functional, emotional, and social dimensions. Based on Christensen's JTBD theory.

Record findings from completed offline human tasks (interviews, observations, outreach) back into the canvas. The re-entry point after /mycelium:handoff.

Pull snapshots from all configured metric sources, compute deltas against prior snapshots, flag unexplained signals, and draft evidence entries for canvas files. One entry point for all external product/market metrics.

Use to build or update an Opportunity Solution Tree from research data. Never from brainstorming.

Use before starting delivery work. Pre-implementation validation checklist to ensure readiness.

Valid frontmatter.

Detect which external metric sources apply to this product (GitHub, Plausible, Stripe, etc.) and configure adapters. Retrofit entry point for projects that started before v0.14; also runnable to refresh source list when the product grows.

Migrate a Mycelium project from legacy install (npx-degit, framework files in .claude/) to plugin install (framework lives in plugin cache, .claude/ holds project state only). Detects current install form, walks the user through plugin installation, runs the migration script, and verifies project state survived. Idempotent — safe to invoke on already-migrated projects.

Use when real user interviews aren't possible (solo/hobby/dogfood projects) but persona work is still needed. Enforces epistemic discipline: adversarial spectrum, pre-committed stop conditions, speculation tagging. NOT a substitute for /mycelium:user-interview when real users are available.

Use to assess Privacy by Design compliance and GDPR/data protection alignment for a feature or system.

Structured retrospective after completing a delivery increment or diamond. Captures learning for continuous improvement.

First-run setup for the Mycelium plugin. Creates project-state directories (.claude/canvas, .claude/diamonds, .claude/memory, .claude/harness) and minimal starter files in the user's project. Idempotent — re-running on an initialized project is a no-op. Run this once after installing the Mycelium plugin and before invoking other skills.

Product discovery to delivery for AI agents. 45+ skills, 12+ theory gates — the agent earns the right to code. Software, courses, AI tools, services.

Product discovery to delivery for AI agents. 45+ skills, 12+ theory gates — the agent earns the right to code. Software, courses, AI tools, services.

Has description but no name field.

A/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.

Use for self-correcting implementation. Implements the reflexion loop: implement, validate, self-critique, retry (max 3 iterations).

OWASP secure design review for code and architecture. Checks input validation, authentication, authorization, data protection.