Menu
SkillsMP a collecté 52 skills depuis wfprieto/wcbs-build-kit. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 52.
Use when a WCBS plan, remediation backlog, migration, release, or multi-slice engineering objective has dependent work that requires requirement-to-node traceability, topology validation, READY-frontier scheduling, or evidence-backed node locking. Also…
Langue du texte source : anglais
Use when the task involves any build, fix, audit, debug, optimization, release, verification, prompt, skill, or agent-design task. Activates the APIVR lifecycle and Elite Build Goals guardrails from this repository before task-specific work.
Langue du texte source : anglais
Use when a build, fix, plan, audit, skill, agent, or pipeline has more than one viable design and the agent must choose the simplest safe option or challenge unjustified complexity.
Langue du texte source : anglais
Use when the task involves code review, PR review, implementation audit, specialist review passes, review-army dispatch, security/performance/testing/API/data/migration/maintainability review, scope-drift detection, and APIVR Phase 4 Audit Implementation…
Langue du texte source : anglais
Use when a user asks to create a feature, change behavior, design a workflow, or build a product and the desired design has not been explicitly approved. Clarifies intent one question at a time before implementation.
Langue du texte source : anglais
Use when designing, auditing, or implementing dashboards, exports, recurring reports, analytics outputs, CSV/PDF/spreadsheet artifacts, API reporting endpoints, notification reports, audit ledgers, compliance reports, or business outcome reporting.
Langue du texte source : anglais
Use when choosing, auditing, changing, deploying, migrating, or troubleshooting hosting, deployment environments, cloud tiers, preview/staging/production setup, persistent versus ephemeral workloads, infrastructure cost, rollback, scaling, or runtime…
Langue du texte source : anglais
Use when changes affect developer experience, setup, commands, documentation, README files, examples, onboarding, API docs, release notes, handoffs, or maintainability of instructions. Reviews docs for accuracy, discoverability, task fit, redaction, and APIVR…
Langue du texte source : anglais
Use when an older WCBS link names this skill for a bug, regression, flaky test, or unknown failure. This compatibility alias routes immediately to the executable systematic-debugging procedure.
Langue du texte source : anglais
Use when software work needs durable business vocabulary, domain concepts, entity boundaries, state transitions, glossary terms, ubiquitous language, ADRs, bounded contexts, workflow nouns, or reduction of generic/ambiguous naming before implementation.
Langue du texte source : anglais
Use when executing an approved APIVR implementation plan sequentially in the current session without subagents, while preserving TDD, review, ledger, and release gates.
Langue du texte source : anglais
Use when calling, adding, auditing, replacing, or troubleshooting third-party APIs, SDKs, webhooks, OAuth flows, API keys, rate limits, retries, idempotency, external data syncs, or integration failure handling.
Langue du texte source : anglais
Use when implementation tasks are complete and the branch or worktree needs final verification, merge/PR/keep/discard decision support, cleanup, and release-readiness evidence.
Langue du texte source : anglais
Use when deciding whether to generate, retrieve, reference, transform, optimize, cache, license, or deliver images, video, audio, documents, icons, logos, fonts, generated media, CDN assets, or user-uploaded files.
Langue du texte source : anglais
Use when converting ideas, audits, requests, strategy notes, PRDs, specs, or implementation plans into product requirements and vertical issue slices with independent acceptance criteria, exact evidence, non-goals, dependencies, and APIVR-ready execution…
Langue du texte source : anglais
Use when review comments, pull-request findings, audit observations, or change requests arrive. Verifies each finding before accepting, rejecting, fixing, or closing it.
Langue du texte source : anglais
Use when asking another agent or person to review a change, branch, pull request, migration, or release candidate. Produces a bounded review package with exact scope, evidence, risks, and questions.
Langue du texte source : anglais
Use when requirements are ambiguous, underspecified, internally inconsistent, too broad, or based on assumptions. Runs one-question-at-a-time alignment, decision-tree clarification, doc-backed grilling, scope narrowing, and APIVR evidence classification…
Langue du texte source : anglais
Use when designing, auditing, or implementing scheduled jobs, cron tasks, webhooks, queues, event-driven workflows, background workers, always-on processes, recurring automations, monitors, reminders, data refreshes, or operational automations.
Langue du texte source : anglais
Use when a test, command, install, runtime, integration, or user workflow fails, flakes, regresses, hangs, or behaves unexpectedly. Establishes a causal reproduction before any symptom patch.
Langue du texte source : anglais
Use when the task involves any code implementation, bug fix, refactor, feature, integration, automation, API, UI behavior, or data-change task where tests or executable verification can be written. Enforces APIVR Phase 3 test-first implementation with…
Langue du texte source : anglais
Use when starting feature implementation, plan execution, or risky edits that should be isolated. Detects existing isolation, prefers native worktree tools, and falls back to manual git worktrees only when no native tool exists.
Langue du texte source : anglais
Use when starting a WCBS-enabled session or before any project action, including questions, exploration, planning, edits, tests, reviews, or release work. Routes work to the smallest applicable WCBS skill before acting.
Langue du texte source : anglais
Use when claiming a task, fix, install, migration, review response, release candidate, or branch is complete. Maps every claim to direct evidence and blocks completion on unverified critical conditions.
Langue du texte source : anglais
Use when creating, revising, splitting, or validating a portable WCBS skill so its trigger, gate, evidence, and runtime behavior survive model pressure.
Langue du texte source : anglais
Use when the task involves architecture, module design, refactors, interface boundaries, adapters, dependency direction, deep module design, deletion tests, locality, leverage, encapsulation, and codebase structure decisions before or during APIVR planning…
Langue du texte source : anglais
Use when a verified fix, feature, audit, incident, release, or repeated workflow produces reusable learning that should improve future APIVR plans, reviews, reports, or release decisions without becoming a parallel source of truth.
Langue du texte source : anglais
Use when reviewing implementation plans, architecture plans, refactor plans, migration plans, technical proposals, and APIVR Phase 2 blueprints for engineering soundness, risk, module boundaries, dependency direction, testability, operational readiness, and…
Langue du texte source : anglais
Use when planning, building, auditing, debugging, testing, deploying, or declaring done for any feature where an outside system calls the app or the app depends on provider callbacks, including Stripe payments/webhooks, Resend webhooks, Supabase Auth…
Langue du texte source : anglais
Use when the task involves QA planning, manual workflow verification, browser testing, UI regression review, issue taxonomy, QA health scoring, screenshot/video evidence, adverse-state testing, fix loops, and APIVR Phase 5 verification for frontend, workflow,…
Langue du texte source : anglais
Use when preparing to merge, ship, deploy, publish, hand off, or declare done. Applies release readiness dashboards, changelog discipline, deploy/canary/post-release checks, rollback readiness, evidence classification, and APIVR release-gate enforcement.
Langue du texte source : anglais
Use when creating, reviewing, improving, merging, compressing, or finalizing high-stakes prompts, agents, skills, source files, implementation plans, audit prompts, code changes, release instructions, runbooks, templates, or any artifact where accuracy,…
Langue du texte source : anglais
Use when recording, auditing, debugging, or designing traceability for agent work, long-running tasks, subagents, tool calls, MCP use, evidence ledgers, run ids, checkpoints, model/runtime metadata, failure reasons, artifacts, or handoff records. Applies to…
Langue du texte source : anglais
Use when auditing, building, testing, or releasing AI applications, LLM apps, RAG systems, vector databases, embedding pipelines, prompt templates, system prompts, tool-using agents, model routing, AI data leakage, prompt injection, jailbreak resistance,…
Langue du texte source : anglais
Use when writing, rewriting, editing, auditing, or reviewing copy that must sound human, specific, direct, and free of generic AI tone. Applies to emails, website copy, landing pages, reports, proposals, prompts, client-facing writing, internal strategy…
Langue du texte source : anglais
Use when work includes cybersecurity review, app security, web application security, AI security, MCP/tool security, vulnerability triage, incident response, supply chain security, cloud/IAM/container security, phishing/red-team/scanning requests, or any…
Langue du texte source : anglais
Use when deciding whether to split work across parallel agents or keep it sequential for audits, investigations, implementation slices, reviews, verification, repository analysis, debugging, or multi-domain APIVR work. Provides dispatch decision rules,…
Langue du texte source : anglais
Use when auditing, refreshing, consolidating, replacing, or deleting stale skills, knowledge docs, templates, solved-problem lessons, provenance notes, or load-order references so the Super Build Kit stays current without parallel truth.
Langue du texte source : anglais
Use when planning, running, auditing, or handing off long-running agent work that may span many steps, subagents, files, tools, checkpoints, summaries, workspaces, generated artifacts, or hours of execution. Applies to Comprehensive or Forensic tasks, large…
Langue du texte source : anglais
Use when adding, enabling, configuring, auditing, or troubleshooting MCP servers, tool connectors, plugin tools, external tool access, tool auth, OAuth, tool secrets, overlapping file/network/database tools, or agent tool governance. Applies to MCP config…
Langue du texte source : anglais