Results for “oom”

Orchestrator for the experimentation skill suite — turn assumptions and product questions into rigorous, well-instrumented experiments and decision-grade readouts. Routes through backlog → spec → runbook → readout based on user need and existing artefacts. Platform-agnostic with PostHog as the primary binding. Load when the user asks to design an experiment, A/B test something, set up an experiment, run a holdout, test a hypothesis, decide what to test next, read out experiment results, analyse a test, or says "should we A/B test this", "experiment on the landing page", "is this lift real", "ship or kill this test", "what should we test next", "build an experiment backlog", "test the pricing page", "validate this with an experiment".

The English summary is being prepared. Showing the original description.

Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent is doing in production, set up Langfuse or Phoenix or LangSmith, debug why my agent gave a bad answer, or track LLM cost per request. Also fires when agent-system-architecture or setup-evaluation requires an observability plan for an agent-chain product. NOT for tracing the coding agent itself — that is run-trace. Precondition for runtime-learning-loop.

The English summary is being prepared. Showing the original description.

Set a deliberate visual direction before any UI is built — the single biggest lever against generic AI output. Derives a posture from product-soul/PRD/specs, scores a curated archetype palette, then generates 2-3 GENUINELY DISTINCT directions and compares them side-by-side before committing to one. Load when the user asks to pick an aesthetic, choose a design direction, decide what a UI should feel like, explore visual options, says "what should this look like", "make it feel like [Linear/Apple/ Duolingo]", "give me design directions", "explore some looks", or when frontend-design routes here. Replaces design-archetype. Sub-skill of frontend-design.

The English summary is being prepared. Showing the original description.

Harden an application against common security risks — validate inputs at boundaries, least-privilege access, safe secrets handling, dependency hygiene, and secure defaults. Load when shipping user-facing code, adding auth/session flows, handling untrusted data, exposing APIs, or the user asks for "security hardening", "OWASP hardening", "secure this feature". Not for skill-library security gates (use secure-skill family).

The English summary is being prepared. Showing the original description.

Surface every assumption embedded in a plan, strategy, or document, assess how critical and how validated each one is, and identify which ones to test first. Load when the user asks to map assumptions, surface hidden beliefs, find what must be true for this to work, run an assumption audit, or when deep-thinking diagnoses an assumption frame. Also triggers on "what are we assuming", "what must be true for this to work", or "find the untested beliefs". Based on David Bland and Alex Osterwalder's assumption mapping method from Testing Business Ideas.

The English summary is being prepared. Showing the original description.

Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude Code / Ampcode native parallelism (Task tool). Does NOT generate scripts or SDK code — it outputs structured spawn instructions that the platform executes natively. Never invoked directly by the user. Never launches without a setup-evaluation PASS.

The English summary is being prepared. Showing the original description.

Write the executable feature specification — the WHAT and WHY artifact that agents and reviewers treat as source of truth. Owns both /specify and /clarify modes. Load when the user asks to write a feature spec, write a specification, write an executable spec, define functional requirements, capture acceptance criteria as Given/When/Then, or when the spec-driven-development orchestrator routes here. Also triggers on "feature spec", "executable spec", "/specify", "/clarify", "write the spec for this feature", "specification for", "spec-driven", "machine-readable spec". Output: docs/specs/YYYY-MM-DD-<slug>-feature-spec.md. Hard gate: cannot Approve while [NEEDS CLARIFICATION] markers remain.

The English summary is being prepared. Showing the original description.

Turn a rough idea into a fully approved design before any code is written. Load when the user wants to brainstorm, explore ideas, design a feature, think through approaches, plan a new capability, or figure out what to build. Also triggers on "let's think through", "help me design", "explore options", "what's the best approach for", "I have an idea for", "before we build", or any request to design something before implementation. Enforces a hard gate: no code, no implementation until user approves a design. For executable feature specs (FRs, NFRs, ACs as Given/When/Then), route to `feature-spec` instead — brainstorming owns approach and architecture, not machine-readable requirements.

The English summary is being prepared. Showing the original description.

Review a built frontend against its chosen direction, catch drift back to generic AI defaults, enforce state coverage, ethical patterns, UX heuristics, and polish, and check contrast with APCA (not the legacy WCAG ratio). Produces specific, prioritized fixes — never vibes-based feedback. Works with pasted screenshots or Playwright MCP automated capture. Load when the user asks to review a UI, audit a design, check if a frontend looks generic or vibecoded, evaluate visual quality or polish, says "review this UI", "is this design good", "audit my frontend", "does this feel like [product]", "design QA", or when frontend-design routes here. Sub-skill of frontend-design.

The English summary is being prepared. Showing the original description.

Test and debug browser UIs using Chrome DevTools MCP — DOM inspection, console errors, network requests, performance traces, and visual verification. Load when building or debugging anything that renders in a browser, verifying a UI fix, profiling Core Web Vitals in a real page, or the user asks for browser testing with DevTools. Requires chrome-devtools MCP configured. Not for backend-only or CLI work. Pairs with frontend-design and performance-optimization.

The English summary is being prepared. Showing the original description.

Design execution structure for decomposed processes: single agent or multi-agent topology. Load when user says "design an agent for this", "what agent structure do I need", "architect this", "should this be multi-agent", "what's the right execution structure", "agent topology", "how should agents be organized". Takes process-decomposer output as primary input. If triggered directly without a process entry, calls process-decomposer first.

The English summary is being prepared. Showing the original description.

Gracefully retire a skill that is redundant, superseded, or no longer earning its place in the context window. Load when improve-skills finds a skill scoring 0-5/14 AND research confirms the domain is now handled natively by current models, when two skills have overlapping triggers and one subsumes the other, when the user asks to remove a skill, retire a skill, delete a skill, or clean up redundant skills, or when validate-skills flags a skill as a duplicate trigger risk. Handles removal cleanly: updates all callers, removes from AGENTS.md, updates README, and archives rather than deletes so the skill can be recovered if needed.

The English summary is being prepared. Showing the original description.

Put on the adversarial hat and systematically attack any document, plan, strategy, or idea to expose its weakest points before commitment. Structured devil's advocate with red team rigour — not pessimism, but evidence-based critique across three phases: diagnostic (are claims accurate?), creative (is the problem artificially constrained?), challenge (are solutions robust?). Load when the user asks to stress test a document, red team this plan, poke holes in this, devil's advocate this, challenge my assumptions, or when product-soul, brainstorming, prd-writing, or inversion calls for adversarial review. Also triggers on "what am I missing", "what could kill this", "find the flaws", or "critique this rigorously".

The English summary is being prepared. Showing the original description.

Pick the right business-model canvas (Lean Canvas, Business Model Canvas, or Value Proposition Canvas) for the stage and fill it with specifics — one segment, one primary canvas, top-3 assumptions, no fluff in the moat or channel boxes. Load when the user asks to fill a business model canvas, lean canvas, value proposition canvas, model this business, map the business model, says "fill the BMC", "make a Lean Canvas", "Value Proposition Canvas for this", "model this idea", "what's the business model", "design the business model". Sub-skill of `venture-exploration`. Hard-bans "everyone" segments, generic channels ("SEO/social/content/ads"), and "unfair advantage = AI/data/network effects" with no concrete asset. Does NOT score viability — for that use `idea-evaluation`.

The English summary is being prepared. Showing the original description.

Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition, method (A/B, holdout, switchback, quasi-experiment, MAB), MDE/duration plan, peek policy, validity threats, and pre-committed decision rule. Platform-agnostic. Load when the user has a candidate experiment and needs to spec it before launch, or says "spec this experiment", "write the test plan", "design this A/B test", "what's the hypothesis", "how big a sample do we need", "how long should we run this", "define the metrics for this test", or when the experimentation orchestrator routes here.

The English summary is being prepared. Showing the original description.

Turn a chosen design direction into a canonical DESIGN.md plus production tokens that don't look vibecoded — state-level colors (8-step neutral ramp, rest/hover/active/ disabled, focus ring), APCA-checked contrast, typography, spacing/radius/motion/elevation, an icon strategy, and component contracts for the core atoms. Emits tokens in the project's stack format (shadcn HSL vars or Tailwind v4 @theme). Load when the user asks to build a design system, generate design tokens, create a DESIGN.md, set up a theme, design a color or type system, pick icons, or when frontend-design routes here. Replaces design-tokens-craft and icon-craft. Sub-skill of frontend-design. Reads DIRECTION.md first.

The English summary is being prepared. Showing the original description.

Deprecate APIs, features, or systems safely — announce, migrate consumers, sunset on a timeline, and document alternatives. Load when removing an old API, migrating users between implementations, sunsetting a feature, or the user asks about deprecation policy, migration guides, or breaking changes. Not for deleting dead code with zero consumers (use code-simplification). Distinct from meta `deprecate-skill` (skill library retirement).

The English summary is being prepared. Showing the original description.

Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry. Load when a structured plan step fails, an unexpected observation arrives, or the user asks what to try next after an error. Also triggers on "try another approach", "route around this failure", "replan on failure", "if X fails try Y", or outcome-based branching during multi-step work. Pairs with structured-planning and debug-and-fix. Does not replace root-cause debugging — adds plan-level path selection.

The English summary is being prepared. Showing the original description.

Strip a problem to its irreducible fundamental truths and rebuild the solution from the ground up — free from analogy, convention, and inherited assumptions. Load when the user feels constrained by how something has always been done, when existing solutions feel expensive or inefficient for no good reason, when the user asks to think from first principles, challenge the fundamentals, or rebuild this from scratch. Also triggers on "why does it have to work this way", "what are the actual constraints here", "ignore what everyone else does", or when deep-thinking diagnoses a convention-break frame. Based on Aristotle's first principles method, popularised by Musk and Feynman. Produces genuinely novel solutions by eliminating convention.

The English summary is being prepared. Showing the original description.

Orchestrator + builder for distinctive, production-grade frontends that don't look AI-generated. Derives stack and design context from product-soul/PRD/specs, then runs the anti-slop chain — explore distinct directions, lock a DESIGN.md system, build from golden examples with mandatory polish + every interactive/empty/loading/error state, then review. Load when the user asks to build a UI, design a frontend, build a landing page or dashboard or web app, beautify or redesign a page, make a UI look premium/playful/editorial, says "build me a frontend", "make this not look AI-generated", "design this interface", "give this real polish", or "frontend design". Routes to design-direction, design-system, design-review.

The English summary is being prepared. Showing the original description.

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output orchestrator.

The English summary is being prepared. Showing the original description.

Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causally, make a ship/iterate/kill decision against the pre-declared rule, and append to cumulative learnings. Forces honest readouts — strips significance claims from underpowered or peek-violating tests; never lets directional results masquerade as causal wins. Load when results exist, or when the user says "read out this experiment", "analyse the test", "did the test win", "interpret the results", "what did we learn", "ship or kill", or when the experimentation orchestrator routes here.

The English summary is being prepared. Showing the original description.

Design stable APIs and module boundaries — contract-first types, consistent errors, boundary validation, additive changes. Load when designing REST or GraphQL endpoints, public module interfaces, component props, or FE/BE contracts. Also triggers on "API design", "interface design", "design the API", "module boundary", "API contract", "define the interface". Complements feature-spec (product layer). Routes breaking retirement to api-deprecation-and-migration when it exists.

The English summary is being prepared. Showing the original description.

Find the earliest decisive failure in an agent run trace and propose an evidence-backed targeted repair. Load when a run failed, results are wrong, or the user asks what went wrong in an agent session. Also triggers on "localize the fault", "first incorrect step", "debug this run", "trace attribution", "why did the agent fail", or after run-trace captures errors. Pairs with debug-and-fix for code defects and dynamic-routing for plan faults.

The English summary is being prepared. Showing the original description.