All authors
Claude Skills by haabe
github.com/haabe84 skills1 installs129 views
- A11y CheckAccessibility audit, scoped to the surfaces a product actually has. Detects web / rendered_markdown / terminal / native_app / video_audio / document / headless, then applies only the criteria that bind. WCAG 2.1 AA in full for web; not at all for headless.Votes: 0GitHub stars: 46
- Assumption TestDesign 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).Votes: 0GitHub stars: 46
- Bias CheckUse before any research activity or significant decision. Reviews cognitive biases relevant to the current stage.Votes: 0GitHub stars: 46
- Bvssh CheckUse to evaluate whether current work aligns with Better Value Sooner Safer Happier. Run at diamond completion and periodically.Votes: 0GitHub stars: 46
- Canvas HealthLint canvas files for staleness, missing fields, inconsistent evidence types, and orphaned references. Run periodically or before major transitions.Votes: 0GitHub stars: 46
- Canvas SyncSynchronize canvas state across team sessions via git. Ensures all team members see the same product knowledge.Votes: 0GitHub stars: 46
- Canvas UpdateUpdate canvas sections with new evidence. Ensures canvas stays current as the single source of truth.Votes: 0GitHub stars: 46
- Corrections AuditUse to analyze correction trends, surface recurring patterns, and graduate repeat corrections to guardrails or anti-patterns.Votes: 0GitHub stars: 46
- Cynefin ClassifyUse when facing a new problem to classify its domain (Clear, Complicated, Complex, Chaotic, Confused) and select appropriate methods.Votes: 0GitHub stars: 46
- Definition Of DoneUse to verify a feature/story meets all Definition of Done criteria before marking complete.Votes: 0GitHub stars: 46
- Delivery BootstrapUse when starting implementation on a new or unfamiliar codebase. Auto-detects tech stack and sets up development context.Votes: 0GitHub stars: 46
- Devils AdvocateSystematically challenge current assumptions before major decisions. Counters confirmation bias, groupthink, and overconfidence.Votes: 0GitHub stars: 46
- Diamond AssessUse to evaluate the current state of a diamond. Checks theory gates, confidence levels, and recommends next action.Votes: 0GitHub stars: 46
- Diamond ProgressRecord a diamond's next decision (set_target; start_experiment and commit_to_build; release; close; an L0's state_purpose or review). Runs the theory gates each decision needs, validates evidence, and at close runs the executable Definition of Done checklist.Votes: 0GitHub stars: 46
- Dora CheckAssess delivery health metrics. For software: DORA + APEX. For content/AI/service products: product-type-appropriate metrics.Votes: 0GitHub stars: 46
- Eval RunnerRun eval scenarios to benchmark Mycelium effectiveness. Execute tasks using reflexion loop, validate against success criteria, record metrics.Votes: 0GitHub stars: 46
- Fan OutParallel agent orchestration for OST exploration. Fan-out multiple solution explorations, fan-in results to compare and select winners.Votes: 0GitHub stars: 46
- Feedback ReviewAggregate feedback signals across all active loops. Reports health, trajectory, overdue checks, regression warnings, and Goodhart's Law violations.Votes: 0GitHub stars: 46
- Framework HealthEvaluate Mycelium's own process effectiveness. Measures cycle velocity, discard trends, confidence calibration, gate effectiveness, regression rate. Run quarterly or every 20 cycles.Votes: 0GitHub stars: 46
- Gist PlanGIST planning workflow. Structure goals into ideas, steps, and tasks using Gilad's evidence-guided framework.Votes: 0GitHub stars: 46
- HandoffGenerate structured handoff materials for offline human tasks (interviews, observations, outreach). Creates actionable briefs with phone-friendly capture templates.Votes: 0GitHub stars: 46
- Ice ScoreUse to prioritize solutions or opportunities using ICE scoring with evidence-backed confidence.Votes: 0GitHub stars: 46
- InterviewUse when onboarding a new product/project. Progressive interview to understand purpose, vision, north star, and competitive landscape.Votes: 0GitHub stars: 46
- Jtbd MapMap the Jobs to be Done (functional, emotional, and social) that people are trying to get done. Based on Christensen's JTBD theory — applies to any object, not only software.Votes: 0GitHub stars: 46
- Launch TierClassify releases into launch tiers and plan go-to-market. Based on Lauchengco's Loved framework.Votes: 0GitHub stars: 46
- Log EvidenceRecord findings from completed offline human tasks (interviews, observations, outreach) back into the canvas. The re-entry point after /mycelium:handoff.Votes: 0GitHub stars: 46
- Metrics DetectDetect 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.Votes: 0GitHub stars: 46
- Metrics PullPull 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.Votes: 0GitHub stars: 46
- Migrate From LegacyMigrate 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.Votes: 0GitHub stars: 46
- Mocked Persona InterviewUse 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.Votes: 0GitHub stars: 46
- Ost BuilderUse to build or update an Opportunity Solution Tree from research data. Never from brainstorming.Votes: 0GitHub stars: 46
- PingSmoke-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.Votes: 0GitHub stars: 46
- PreflightUse before starting delivery work. Pre-implementation validation checklist to ensure readiness.Votes: 0GitHub stars: 46
- Privacy CheckUse to assess Privacy by Design compliance and GDPR/data protection alignment for a feature or system.Votes: 0GitHub stars: 46
- Prompt OptimizerA/B test CLAUDE.md instruction changes against eval benchmarks. Capture baselines, test variants, compare results.Votes: 0GitHub stars: 46
- ReflexionUse for self-correcting implementation. Implements the reflexion loop: implement, validate, self-critique, retry (max 3 iterations).Votes: 0GitHub stars: 46
- Regulatory ReviewUse to assess regulatory applicability for products that may fall under AI regulation (EU AI Act, Article 50 transparency).Votes: 0GitHub stars: 46
- RetrospectiveStructured retrospective after completing a delivery increment or diamond. Captures learning for continuous improvement.Votes: 0GitHub stars: 46
- Security ReviewOWASP secure design review for code and architecture. Checks input validation, authentication, authorization, data protection.Votes: 0GitHub stars: 46
- Service CheckUse to evaluate a service or feature against Downe's 15 principles of good services.Votes: 0GitHub stars: 46
- SetupFirst-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. Optionally provisions opencode runtime support (a starter scaffold) when opencode is detected or requested. Idempotent — re-running on an initialized project is a no-op. Run this once after installing the Mycelium plugin and before invoking other skills.Votes: 0GitHub stars: 46
- StartOne command from "plugin installed" to "running brief on your idea." Combines /mycelium:setup (project-state initialization) and /mycelium:interview (10-minute discovery brief) into a single flow. Run this immediately after installing the Mycelium plugin — it's the recommended entry point for first-time users.Votes: 0GitHub stars: 46
- Team ShapeAssess team structure against Skelton's Team Topologies. Evaluate cognitive load, interaction modes, and Conway's Law alignment.Votes: 0GitHub stars: 46
- Threat ModelUse to conduct STRIDE threat modeling for a system or feature design.Votes: 0GitHub stars: 46
- Usability CheckEvaluate user-facing interfaces against Nielsen's 10 Usability Heuristics. Complements /mycelium:service-check (Downe = service-level quality, Nielsen = interface-level quality).Votes: 0GitHub stars: 46
- User InterviewGuide for conducting Torres-style story-based interviews with the people whose experience you're researching, with bias mitigation and a JTBD lens.Votes: 0GitHub stars: 46
- User Needs MapMap the needs of the people you're building or exploring for, independently of solutions, using Allen's User Needs Mapping methodology. Identifies underserved needs that feed into the Opportunity Solution Tree.Votes: 0GitHub stars: 46
- Wardley MapCreate or update a Wardley Map of how any domain delivers value. Maps the needs it serves, the capabilities involved, how each is evolving (genesis to commodity), and strategic plays. Applies to any domain, not only software.Votes: 0GitHub stars: 46
- Xai CheckExplainability (XAI) audit for products containing AI components. Five-stage tier-scaled check: risk classification, stakeholder×question matrix, fidelity audit, system card, recourse path. Honest about what was validated functionally vs what needs user testing.Votes: 0GitHub stars: 46
- New User IntakeHeuristic-candidate fixture: outside curated list but strong user-content signal.Votes: 0GitHub stars: 46