All authors
Claude Skills by Mozurok
github.com/Mozurok121 skills1 installs108 views
- A11y AuditSenior accessibility auditor mapping a UI surface (screen, flow, or component set) to WCAG 2.2 at a named conformance level. Produces ACCESSIBILITY_AUDIT.md, a per-criterion conformance ledger that splits machine-checkable rows from a manual-review queue, with severity and concrete remediation per finding. Activates when a screen-spec or an implemented surface has no conformance ledger, or when a delivery surface needs a conformance pass before sign-off. Do not use for a contrast-only request...Votes: 0GitHub stars: 7
- Ai Feature Eval HarnessDesign an evaluation plan for a product AI feature (LLM- or model-backed output): measurable success criteria, a held-out labeled eval dataset shape, per-criterion grading (code-based first, then LLM-based for nuanced judgment), and a pass threshold, then persist as AI_EVAL_PLAN.md. Use when the task ships or changes a feature whose output is model-generated or non-deterministic (assistant reply, classification, extraction, summarization, ranking, agent action) and needs a repeatable dataset-...Votes: 0GitHub stars: 7
- Api Contract ReviewReview an API contract (endpoints, request/response shapes, error codes, auth model) BEFORE implementation for naming consistency, versioning, pagination, idempotency, and alignment with existing endpoints. Distinct from review-hard (post-implementation risk) and repo-consistency-sweep (pattern matching on written code). Use when designing new endpoints or modifying existing API contracts. Do not use when the API is already implemented (use review-hard or repo-consistency-sweep instead).Votes: 0GitHub stars: 7
- Api Runtime VerifyVerify an implemented backend HTTP surface at runtime: per route, record the request actually made, the status, the content-type, and the observed body shape, assert each response against the slice's acceptance behavior, and decide a PASS/FAIL/BLOCKED gate. The probe's real output IS the evidence: a route whose output is not shown is unverified, never PASS. Capability-routed, and it routes fixes rather than applying them. Do not use to review a contract before implementation (use api-contract...Votes: 0GitHub stars: 7
- App Runtime VerifyVerify a built mobile or app runtime at runtime: run the app (device, emulator, or headless), read the captured output (native logcat, iOS device log, or the Metro/JS console), classify runtime errors against a per-stack taxonomy, and decide a PASS/FAIL gate for the slice's acceptance behavior. The run's real output IS the evidence; a claimed-but-not-shown run is unverified. React Native/Expo and Unity mobile are the documented adapters. Do not use to plan a screen (use implementation-plan), ...Votes: 0GitHub stars: 7
- Apply Sweep TriagePersist the user's triage decisions (apply, decline, discuss) from a SWEEP snapshot into REVIEW_PREFERENCES.md so future sweeps suppress declined findings and track applied fixes. Use after the user has edited the triage values in a SWEEP snapshot file produced by repo-consistency-sweep. Do not use when no sweep snapshot exists or when the user has not yet set triage values.Votes: 0GitHub stars: 7
- Approve PlanAtomically lock IMPLEMENTATION_PLAN.md as the approved execution baseline and stamp TASK_STATE.md with the approval signal. Symmetric counterpart to approve-proposed but for the plan itself, not for arbitrary PROPOSED artifacts. Use on every plan implementation-plan produces or self-critique-and-revise revises; it self-runs a blinded review, and only an ESCALATED exit reaches the user. Do not use when the plan is still draft, when implementation-plan returned NO_OP, when the plan contains [NE...Votes: 0GitHub stars: 7
- Approve ProposedAtomically persist every file marked PROPOSED in the most recent prior assistant turn's `### Artifact changes` block. Invoked on request only; it is not part of any default chain. The ADR-0001 mode gate it once serviced is gone, and what remains is the staged write: a command chose to stage a PROPOSED block inside a section it does not conventionally own (optional since ADR-0232 made ownership descriptive), and the user wants it promoted without waiting for the owner command. Use when the pri...Votes: 0GitHub stars: 7
- Atom Audit FleetAudit every atom in the design system in parallel against the documented component guidelines, dispatching one worker per small group of atoms and merging their rows into a single ATOM_AUDIT.md table. The orchestrator-workers variant of atom-audit. Use when the atom count is 6 or more, the cost-effectiveness threshold, and COMPONENT_GUIDELINES.md exists. Do not use below 6 atoms (use atom-audit single-agent), when COMPONENT_GUIDELINES.md is missing, or when only 1 or 2 atoms changed (use desi...Votes: 0GitHub stars: 7
- Atom AuditProduce ATOM_AUDIT.md table auditing every atom component against COMPONENT_GUIDELINES.md (memo, callbacks, inline styles, press anim, touch target, a11y, reduced motion). Output is the table; fixes flow through normal slice pipeline. Use when 2-4 weeks have passed since last audit, when 5+ new atoms shipped, or when COMPONENT_GUIDELINES has a new normative rule. Do not use when no atoms exist (run design-bootstrap first) or when only a single atom needs review (use design-spec-review instead...Votes: 0GitHub stars: 7
- Autonomous BoardRead-only board-of-record view for an autonomous-run task (ADR-0044 D7, wos/autonomous-track.md). Renders the run as the spec, the IMPLEMENTATION_PLAN waves and slices, and the TASK_STATE phases mapped to to-do / in-progress / escalated / proposed / done columns, sourced only from the Fhorja task artifacts. No external work tracker; no writes. Use when the maintainer wants a single-glance status of an autonomous run without opening every artifact. Do not use to change state (use sync-task-sta...Votes: 0GitHub stars: 7
- Autonomous ReadinessDecide whether an already-defined project is ready to boot an unattended overnight run, and refuse until it is. Reads the project's own definition artifacts through the shared definition-completeness reader, emits a per-criterion ledger with a BOOT or NOT-READY verdict naming every missing item, and returns NOT-READY when a declared runtime surface has no evidence adapter rather than booting blind. It reports and routes: it never answers a criterion on the operator's behalf, never records a d...Votes: 0GitHub stars: 7
- Autonomous RunRun one approved task through one supervised session with Fhorja's full-profile direct-use reference dispatcher. It delegates verifiable slices to existing commands, emits PROPOSED diffs only, and never creates commits or attestation refs. Use when a maintainer invokes Fhorja directly after approve-plan and a BOOT verdict from autonomous-readiness. Do not use from another execution loop, for an unapproved or NOT-READY plan, for a single slice (use implement-approved-slice), or when durable re...Votes: 0GitHub stars: 7
- Backend System DesignProduce a staff-grade backend system-design RFC for the active task: a 12-section design document (problem, requirements, architecture, data model and storage, API contract, caching, scaling and bottlenecks, reliability and SLOs, security, observability, rollout and migration, trade-offs) for a new service, endpoint, or backend feature, persisted as BACKEND_SYSTEM_DESIGN.md. Capability-routed, not stack-specific; composes with slo-define, performance-budget, api-contract-review, and release-p...Votes: 0GitHub stars: 7
- Branch CommitReturn a branch name and a concise commit message (at most 3 lines: a subject and an optional 2-line body) for the current task, grounded in the real `git diff` rather than a paraphrase of the task summary, and with `--apply` optionally create that commit after showing the staged diff in the same turn. Use when the user only needs quick branch and commit naming right before committing, full PR packaging is unnecessary, and there is a real inspectable diff (staged or unstaged changes, or a bra...Votes: 0GitHub stars: 7
- Capture ObservationAppend a single observation, question, hypothesis, or concern to TASK_STATE.md as task memory without disrupting in-progress work or requiring a full state sync. Lean append-only; never restructures other artifacts. Use when something surfaces mid-work that should be remembered for later (during planning, implementation, or review), when you noticed something not actionable now but should not be lost, when you want to log a hypothesis to validate before closure, or when a small concern does n...Votes: 0GitHub stars: 7
- Capture ReferencesPull external references (URLs or topics provided by the user) from the web, summarize each with a defined freshness format, and append them to projects/<client>__<project>/REFERENCES.md so all current and future tasks under that project can consume them as grounded external context. Deduplicates by URL. Use when the user wants to research and persist project-level references (stack docs, API contracts, regulations, competitor pages), supplies URLs to summarize with freshness metadata, surfac...Votes: 0GitHub stars: 7
- Code Context MapGenerate and re-sync an AI-readable code context map (a ranked, token-budgeted, layered Markdown map of files, imports, signatures, invoke edges, and typed external boundary calls: db/http/queue) for a target project (or, from a seed file, its import chain), written to a gitignored folder inside that project and regenerated on invoke. Extraction is ripgrep-based by default, with optional parser augmentation when a parser is already present; no embeddings. The map is a seed for grep, not a rep...Votes: 0GitHub stars: 7
- Code LocateGiven a behavior description, locate candidate code paths and line ranges in the active codebase that probably implement it. Outputs up to 10 candidates with HIGH/MEDIUM/LOW confidence, a one-line rationale each, and an explicit search trail, then proposes a SOURCE_OF_TRUTH.md update so the next step runs with concrete files instead of a vague codebase pointer. Use when the first real question is where the code lives and file paths are not yet known. Do not use when paths are already explicit...Votes: 0GitHub stars: 7
- Color Contrast ArchitectSenior design-system contrast architect enforcing WCAG 2.2 AA and AAA per design context (normal text, large text, UI components, focus indicators). Audits every documented foreground and background pair across the supplied themes BEFORE the visual choices lock, producing a pairwise contrast matrix with token-level remediation. Activates when design-bootstrap proposes tokens without contrast pairs, or when a screen-spec or component-spec mentions an unvalidated pair. Do not use for a single p...Votes: 0GitHub stars: 7
- Compact Task MemoryProduce a lossy compaction summary of TASK_STATE.md when task memory has grown beyond a useful working size, preserving canonical decisions and recommended next step while dropping stale facts. Distinct from sync-task-state (incremental, append-only, never lossy) and state-reconcile (drift repair, no shrinking). Use when task memory has accumulated across multiple slices (5+ completed) and feels heavy, the resume cost is growing as the file scales, the current known facts list is full of reso...Votes: 0GitHub stars: 7
- Component SpecGenerate a 15-section component specification from a Figma component using MCP tools (get_design_context, get_screenshot, get_variable_defs). Produces a spec doc matching the COMPONENT_SPEC.md template with anatomy, variants, sizes, states, accessibility, motion, haptics, platform, security, performance, and API sections pre-filled from Figma observations. Use when documenting a design system component. Do not use when the component has no Figma representation or when the spec already exists ...Votes: 0GitHub stars: 7
- Contract SignoffHarden the current decision set into a clean, normative source of truth with no residual ambiguity, then persist the result in DECISIONS.md and TASK_STATE.md as explicit reviewable edits (no silent intent drift). Use when key decisions are already resolved, the task has a stable contract or policy direction, and the remaining work is to harden wording and remove interpretation risk before planning or implementation. Do not use when major ambiguities remain unresolved, the task still needs dec...Votes: 0GitHub stars: 7
- Db Context PostgresValidate that a generic Postgres database (Cloud SQL, GKE Autopilot, RDS, self-hosted) is reachable via psql or pg_dump, introspect a user-scoped subset of the schema (extensions, tables, columns, indexes, foreign keys, optionally RLS policies and functions), and persist it as DB_CONTEXT.md with one cross-link in SOURCE_OF_TRUTH.md. Read-only introspection, never destructive SQL. Opt-in. Use when the task touches a non-Supabase Postgres and planning needs verified rather than assumed schema, ...Votes: 0GitHub stars: 7
- Db Context SupabaseValidate that a Supabase MCP server is reachable, introspect a user-scoped subset of the database (tables, columns, types, RLS policies, optionally functions and recent migrations), and persist it as DB_CONTEXT.md with one cross-link in SOURCE_OF_TRUTH.md. Read-only introspection, never destructive SQL. Falls back to the local Supabase CLI when no MCP server is reachable, and never records supabase status output into an artifact because it prints the service_role key. Opt-in. Use when the tas...Votes: 0GitHub stars: 7
- Decision InterviewAsk the minimum set of high-value decision questions needed before turning the task into canonical implementation rules. Decisions that would change runtime behavior, data integrity, rollout safety, or test strategy. Use when the missing information is decision-driven (not factual), different answers would change behavior or data integrity or rollout safety or test strategy, or the task cannot safely move into planning because policy or behavior is undecided. In an attended chain on a task br...Votes: 0GitHub stars: 7
- Delivery AssetGenerate an outward-facing delivery artifact (executive summary, slack or email update, demo script, release note, blog post draft) from the current task's work, scoped per audience and per format. Grounds every claim in the task artifacts and never invents metrics, customer impact, or marketing claims. Use when delivery needs audience-specific framing beyond a PR description or a team status note. Do not use when the audience is a code reviewer (use pr-package), for a quick team status updat...Votes: 0GitHub stars: 7
- Design BootstrapBootstrap a design system from a Figma file using MCP tools. Extracts token variables, identifies components, creates the directory structure, and generates scaffolded foundation docs and a component inventory. Use when starting a new project with a Figma design file. Do not use when the design system docs already exist or when there is no Figma file.Votes: 0GitHub stars: 7
- Design Spec ReviewReview a component or screen implementation against its spec doc for alignment on variants, states, accessibility, tokens, and visual fidelity. Distinct from review-hard (general risk) and repo-consistency-sweep (pattern matching). Activates when a slice's declared Scope touches a design-system button, icon, or component convention file (a shared atom/component under a design-system package) with no cited design-spec-review pass for that change. Use when a design system component or screen ha...Votes: 0GitHub stars: 7
- Direction AdjustCapture a small-to-medium course correction realized mid-task, not from external review: record it as a numbered D-N entry in DECISIONS.md, update TASK_STATE.md, and route back to the right command. Use when the realization came from your own work, is worth recording, does not invalidate the whole approach, and the current slice is recoverable with a small change of plan. Do not use when the trigger is external review or PR feedback (use pr-feedback-ingest or post-review-pivot), when it inval...Votes: 0GitHub stars: 7
- External Research FleetOrchestrator-workers variant of external-research for multi-modal sweep across distinct angles or source-groups of one research question. Promotes external-research's inline delegation to a first-class orchestrator with a worker contract and provenance. The orchestrator dispatches N mechanical-role workers (one angle each) in parallel; each produces a structured per-angle synthesis grounded in REFERENCES.md; orchestrator merges into a single EXTERNAL_RESEARCH.md with cross-angle reconciliatio...Votes: 0GitHub stars: 7
- External ResearchSynthesize multiple external sources into a task-scoped EXTERNAL_RESEARCH.md grounded in REFERENCES.md entries, with comparative analysis and a recommendation visually separated from the source-grounded findings. Never invents claims. Sources are captured first via capture-references. Use when the task depends on several external sources (vendor comparisons, regulatory evaluations, framework choices) and synthesis, not just capture, is what is missing. Do not use when a single source suffices...Votes: 0GitHub stars: 7
- Extract Foundations From ScreensExtract canonical foundations docs (`foundations/color.md`, `foundations/typography.md`, `foundations/spacing.md`, `foundations/radii.md`) from a batch of existing SCREEN_SPECs. Idempotent: re-runs only add new tokens, never overwrite existing role mappings, and route conflicts to a Review queue. Use when SCREEN_SPECs already document raw values and you need to converge them into role tokens. Do not use when foundations are already curated and screens already reference role tokens (run `found...Votes: 0GitHub stars: 7
- Feature Library Scout FleetOrchestrator-workers variant of feature-library-scout for deep per-feature-problem library research. One worker per problem ranks candidate libraries by adoption signal (registry downloads, dependents, last release, stars and trend, maintenance, platform fit) relative to the project's ecosystem, grounded in captured sources; the orchestrator is the sole writer that merges into one FEATURE_LIBRARIES.md. Stack-agnostic (npm, PyPI, crates.io, Go, Maven). Use when the product has more than 3 dist...Votes: 0GitHub stars: 7
- Feature Library ScoutResearch and recommend community-vetted best-in-class libraries for each feature problem in the product (lists, camera, forms, keyboard, sheets), ranked by adoption signal (downloads, dependents, recency, stars-trend, maintenance, platform fit) relative to the project's ecosystem. Stack-agnostic across registries (npm, PyPI, crates.io, Go, Maven). Researches five angles (web, repo, registry, AAA practices, reference repos) and writes FEATURE_LIBRARIES.md, grounding every pick in a captured RE...Votes: 0GitHub stars: 7
- Foundation AuditCompare design tokens in code against foundation docs and optionally Figma variables to detect drift (tokens added without documentation, documented tokens not in code, value mismatches). Use when the design system has been evolving and you want to verify foundations are in sync. Do not use when no foundation docs exist (run design-bootstrap first).Votes: 0GitHub stars: 7
- Frontend Architecture ReviewReview a frontend architecture at scale and gate micro-frontend adoption BEFORE building. Starts with an adopt-or-don't-adopt decision (default: prefer a modular monolith until 3 or more independently deploying teams and real coordination pain exist), then a checklist covering team and domain boundaries, independent deployability, shared dependencies, runtime isolation, the composition tier, state at scale, and governance. Do not use to design one system (use frontend-system-design), to revie...Votes: 0GitHub stars: 7
- Frontend System DesignProduce a staff-grade frontend system-design RFC for the active task: a 12-section design document (problem, requirements, architecture, data model, API contract, rendering and delivery, state, performance, accessibility, security, rollout, trade-offs) covering web and mobile, persisted as FRONTEND_SYSTEM_DESIGN.md. An --interview mode reframes the same structure for an interview round. Do not use to frame whether the problem is right (use problem-framing), to slice an already-designed change...Votes: 0GitHub stars: 7
- Godot Runtime VerifyVerify a built Godot 2D or 3D scene at runtime: run the scene (press-play or headless), read the captured debugger output, classify any runtime errors against a Godot-specific taxonomy, and decide a PASS/FAIL runtime gate for the slice's acceptance behavior. The run's real output IS the Layer-1 runtime evidence (ADR-0048); a claimed-but-not-shown run is unverified. MCP-agnostic about how the scene is run; it verifies and routes fixes, it does not apply them. Use after a Godot slice is impleme...Votes: 0GitHub stars: 7
- Godot Scene PlanPlan the Godot scene and node structure for a 2D or 3D game feature before any GDScript is written: the scene tree, node types and responsibilities, autoloads, signal wiring, the input map, and the resources and sub-scenes to create. Produces GODOT_SCENE_PLAN.md, a design-time plan an editor or a human builds against. Capability-routed and MCP-agnostic. A 3D plan SHALL declare its renderer tier or it is incomplete. Do not use to frame whether the game idea is right (use problem-framing in its...Votes: 0GitHub stars: 7
- Graphql Contract ReviewReview a GraphQL schema and a Backend-for-Frontend (BFF) contract BEFORE implementation, against a GraphQL-specific checklist: schema shape and nullability (null-bubbling), errors-as-data unions, N+1 and DataLoader, query cost and depth limits, cursor-connection pagination, federation entity ownership, breaking-change gate (schema checks), auth layering and BFF token posture, BFF thinness, and partial-failure degradation. Distinct from api-contract-review (REST and HTTP) and review-hard (post...Votes: 0GitHub stars: 7
- Harvest Session LearningsScan the current working session and the active task's artifacts for reusable, generalizable lessons (what was tried, what failed and why, what surprised us, what the next task should do differently) and propose anchored entries to append to the task's LEARNINGS.md, the produce-side counterpart to the ADR-0017 consume path that task-init already reads. Append-only and read-only on existing entries; de-duplicates against what is already captured; keeps durable lessons and drops one-off task tr...Votes: 0GitHub stars: 7
- Im StuckBreak the task out of a loop, confusion state, or false-progress state, and determine the fastest safe path forward. Diagnoses whether the issue is technical, workflow-related, or scope-related, then routes to the right recovery command and editor mode (Ask by default; Debug if the stuckness is a concrete technical failure; Plan if it is a phase or contract or sequence issue). Use when progress is looping or stalling, the same questions or reviews are being repeated, the wrong command or wron...Votes: 0GitHub stars: 7
- Image To SpecGenerate a design-system spec from a raw image file (a screenshot, mockup, or captured app screen) when there is no Figma source. Reads the image with vision and emits a COMPONENT_SPEC.md-shaped doc (--component) or a SCREEN_SPEC.md-shaped doc (--screen), auto-detecting the mode when no flag is given. A gated --gameplay mode (ADR-0084, off by default) instead derives a MECHANICS_SPEC.md behavior contract for a 2D or 3D game from screenshots, extracted video frames, and playtest notes, with ev...Votes: 0GitHub stars: 7
- Impact AnalysisUnderstand the requested change deeply enough to make safe workflow decisions, then persist it as IMPACT_ANALYSIS.md. Identifies blast radius, contract impacts, schema and runtime risks, and integration points before planning or coding. Per-repo subsections when multi-repo. Use when a task was just initialized, when it is still partly understood, or when the change may affect contracts, schema, integrations, runtime behavior, or critical user flows. Do not use when a valid impact analysis alr...Votes: 0GitHub stars: 7
- Implement Approved SliceImplement only the approved slice with minimal, explicit, review-friendly changes, then persist execution evidence in slice notes and TASK_STATE.md. The single official execution path of the workflow. Supports an opt-in test-first mode, per slice or via --tdd, that writes the failing test before the code. Use when the plan is valid, the current slice is defined and approved, correctness-critical ambiguity is resolved, and the files in scope are known well enough to edit safely. Do not use dur...Votes: 0GitHub stars: 7
- Implement FleetOrchestrator-workers variant of implement-approved-slice that executes independent approved slices in parallel. Reads per-slice Scope and Depends-on from IMPLEMENTATION_PLAN.md, builds the slice DAG, computes parallelizable waves (ready slices whose file scopes are pairwise disjoint with no shared migration, lockfile, codegen, or barrel export), validates disjointness before dispatch, runs one worktree-isolated worker per slice per wave (each executing the implement-approved-slice contract), ...Votes: 0GitHub stars: 7
- Implement Slice ComplementExecute a bounded micro-delta (adjustments, fixes, polish, missed checklist items) that stays inside the same slice intent and the locked decisions, then record evidence in slice notes without churning unrelated artifacts. Use when a slice is implemented or ready-to-close-with-follow-ups, you found a narrow gap (bug, typo, test, log line, copy, small refactor under the same acceptance story), and you can state it as a numbered micro-delta list over a small named file set. Do not use when the ...Votes: 0GitHub stars: 7
- Implementation PlanDefine an incremental, reviewable, production-safe implementation plan for the active task and persist it as IMPLEMENTATION_PLAN.md plus a TASK_STATE.md update. Breaks work into the smallest safe slices with objective, exact scope, ordering rationale, key risks, validation approach, exit criteria, and work complexity per slice. No code is written. An annotate-only retrofit mode backfills per-slice Scope and Depends-on plus Execution waves onto an in-progress plan so it can adopt implement-fle...Votes: 0GitHub stars: 7
- Incident TriageTriage a concrete observed technical failure (stack trace, error, failing test, runtime symptom, production alert), classify the failure type (REGRESSION/NEW_BUG/CONFIG/EXTERNAL_DEPENDENCY/REPRODUCIBILITY/DIAGNOSTIC_INSUFFICIENT), recommend fix size (HOTFIX/SLICE/INVESTIGATION/ESCALATE), and validate against locked decisions and invariants. Defends HOTFIX paths against unnecessary ceremony with explicit safety justification. Use when there is concrete failure evidence, an active task folder e...Votes: 0GitHub stars: 7