345 件 ・ 関連度順
概要と使いどころ
Performs a white-box security review of Atlassian Forge apps using structured, Forge-specific security rules and evidence-driven reporting. Use when the user asks for a Forge security review, security audit, vuln assessment, pentest-style code review, authz review, tenant isolation analysis, web trigger hardening, or static analysis execution for a Forge app.
日本語の概要は準備中です。原文の説明を表示しています。
Choose, reuse, restore, park, or clean up Git workspaces while preserving work and host ownership. Create isolation only when it resolves a real conflict; inspection does not authorize creation or deletion.
日本語の概要は準備中です。原文の説明を表示しています。
Sandbox escape playbook. Use when breaking out of Python sandbox, Lua sandbox, seccomp filter, chroot jail, container/Docker, browser sandbox, or namespace isolation to achieve unrestricted code execution or file access.
日本語の概要は準備中です。原文の説明を表示しています。
Top-level orchestrator for the Gaia Skill Tree evidence verification pipeline. Run this when you want to do a full evidence pass — collecting raw sources, verifying live GitHub star counts, running Phase 2B benchmark-source verification, adversarially auditing for quality/formatting issues, and checking that every URL is reachable — all in one coordinated sequence. Trigger phrases: "run the evidence pipeline", "full evidence pass", "verify evidence", "evidence verification pipeline", "run ev-pipeline", "check all evidence", "audit the data lake", "evidence quality sweep", "refresh evidence", "validate evidence sources". Also aliased as /evidence-verification-pipeline. Use the individual sub-skills (ev-collection, ev-star-verification, ev-adversarial-audit, ev-link-validation) only when you need to re-run one phase in isolation; for end-to-end work, always start here.
日本語の概要は準備中です。原文の説明を表示しています。
Builds a safe, isolated environment for detonating and analyzing malware using virtualization, host-only or simulated networking, and snapshotting. Activates for requests about creating a malware lab, sandbox VM, isolated analysis environment, or safe detonation setup.
日本語の概要は準備中です。原文の説明を表示しています。
Generate and maintain browser demos of Pulp audio plugins (both web ABIs — WAM and WCLAP) from one declarative config, so every demo mounts the SAME shared player and the two ABIs stay in lockstep. Invoke it whenever you publish/update a browser demo of a Pulp plugin, add a plugin to a demo gallery, stand up a new gallery, or touch demo pages/hosting. It runs a deterministic generator (config → stamped WAM+WCLAP site + owned-files manifest) and a blocking validator (config schema, cross-origin-isolation coverage, OG metadata, regeneration ownership). Customization is declarative config in <repo>/.pulp-web-demo/config.json (schema bundled) plus at most two typed module seams; the shared player (pinned @danielraffel/web-player) holds all UX behavior and is never vendored. Works in Claude and Codex.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of a Conveyor Operator — diagnosing a mistracking belt before it becomes edge damage or spillage, verifying every lockout/tagout isolation point on a conveyor with a gravity take-up or incline before entering the nip zone, calculating each conveyor's actual delivered capacity in a multi-conveyor line to find the true bottleneck, deciding whether a mechanical or vulcanized splice fits a given tension rating, or judging whether a pinch-point guarding gap needs an immediate stop versus a scheduled fix.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an Automotive Engineer — computing weight transfer and tire friction-circle limits for a braking-while-cornering maneuver to set brake-force distribution, sizing a powertrain and gear ratio against a 0-60 mph acceleration target while checking traction versus power limits, sizing a crumple zone's crush distance against FMVSS 208 occupant-deceleration limits, or checking a powertrain-mount or driveline natural frequency against engine firing-order excitation for NVH isolation. Distinct from an automotive-service-technician (diagnoses and repairs a vehicle already designed) — this role owns the system-level design decisions (structure, powertrain sizing, suspension geometry, restraint/crash structure, NVH) that produce the vehicle the technician later services.
日本語の概要は準備中です。原文の説明を表示しています。
Use when a task needs the judgment of an Animal Caretaker — triaging daily husbandry when kennel census exceeds staffing capacity, reading a Fear-Anxiety-Stress (FAS) score change or appetite/output drop against an escalation threshold, deciding brush-out vs. shave-down on a matted coat, or setting isolation and vaccination-lead-time protocol for a new intake or boarding admission.
日本語の概要は準備中です。原文の説明を表示しています。
Playwright-first strategy for shared DB + shared test accounts. Use when E2E tests collide in QA/staging, need safe parallelism, or require deterministic cleanup without touching baseline data. Covers per-test ownership, namespacing, ID-based teardown, serial shared-state suites, and optional stale-data janitor jobs.
日本語の概要は準備中です。原文の説明を表示しています。
Guidance for Tauri v2 architecture concepts, process model, and IPC isolation patterns.
日本語の概要は準備中です。原文の説明を表示しています。
Use when deploying or managing Kubernetes workloads. Invoke to create deployment manifests, configure pod security policies, set up service accounts, define network isolation rules, debug pod crashes, analyze resource limits, inspect container logs, or right-size workloads. Use for Helm charts, RBAC policies, NetworkPolicies, storage configuration, performance optimization, GitOps pipelines, and multi-cluster management.
日本語の概要は準備中です。原文の説明を表示しています。
Audit whether a product is ready for enterprise sales. Use when you need to assess SSO/SAML/SCIM support, RBAC maturity, multi-tenancy data isolation, audit logging coverage, public API quality, SLA operational readiness, SOC2/ISO27001 certification gaps, GDPR data residency controls.
日本語の概要は準備中です。原文の説明を表示しています。
Scaffold an isolated CLOUD dev box per agent (via crabbox + Daytona) for any codebase — the parallel-safe counterpart to dev-local-setup. Each agent gets its own full stack (own DB + dev server) and an in-box browser for e2e, so concurrent loops never collide on ports/state. Sets up the snapshot image, .crabbox.yaml, an idempotent setup.sh (also boots the stack locally), and a cbx.sh wrapper. Use when the user says "set up crabbox", "give each agent its own box", "add cloud testing", "make this repo testable in the cloud / on Daytona", "parallel-test this", or when setup-codebase-harness needs true per-agent isolation.
日本語の概要は準備中です。原文の説明を表示しています。
Audits Google Cloud Filestore instances across projects for disaster recovery readiness (missing or stale backups), security access governance (overly permissive NFS export rules, 0.0.0.0/0 exposure, missing ROOT_SQUASH), and reliability compliance (Physical Zone Isolation PZI and Physical Zone Separation PZS). Use when assessing storage health posture, auditing NFS export permissions, identifying unprotected file shares, or validating zone failure domains. Don't use for Cloud Storage buckets, Persistent Disk, or NetApp Volumes.
日本語の概要は準備中です。原文の説明を表示しています。
An Agentforce agent is moving from build or sandbox to live end-user traffic and the team needs a comprehensive readiness gate: coverage testing, Trust Layer config, guardrails, cost telemetry, observability, rate limits, permissions, rollout strategy, rollback plan, performance benchmarks. Triggers: 'we want to ship our Agentforce agent next week', 'pre-prod readiness review for our Service Agent', 'what do we need before turning the agent on for real customers', 'agent went live and is hallucinating, what should we have caught', 'cost monitoring for our internal sales agent', 'rollout strategy from internal pilot to GA'. NOT for the lighter five-block activation sign-off artifact — use agentforce/agent-deployment-checklist. NOT for authoring the guardrails themselves — use agentforce/agentforce-guardrails. NOT for building the test harness — use agentforce/agentforce-eval-harness. NOT for Trust Layer feature setup in isolation — use agentforce/einstein-trust-layer.
日本語の概要は準備中です。原文の説明を表示しています。
Guidance on non-obvious runtime behaviors of Salesforce standard objects — polymorphic lookups, lead conversion field loss, PersonAccount dual-nature, CaseComment trigger isolation, and Activity date fields. Also covers which trigger actually fires for a person account, the either/or Event duration contract, the Closed status category behind Task.CompletedDateTime, the 3-record merge cap and its single delete + single update trigger events, and the CaseComment post-insert write lock. Trigger keywords: person account trigger not firing, Contact trigger person account, Event required field EndDateTime, DurationInMinutes, CompletedDateTime null, merge MasterRecordId, CaseComment cannot be edited, IsNotificationSelected null, lead conversion triggers disabled. NOT for the Activity object model — use admin/activity-and-task-patterns. NOT for writing TYPEOF queries — use apex/apex-polymorphic-soql.
日本語の概要は準備中です。原文の説明を表示しています。
Configure related lists on Salesforce records — column choice on Page Layouts (max 10 fields per related list), sort field selection, the Spring '24 Enhanced Related Lists component (which adds filtering, mass actions, and 10-row inline display), the choice between Related Lists / Related Lists - Single / Related List - Quick Links in Lightning App Builder, per-record-type related-list assignments, and the View All / pagination UX. NOT for FSL WorkOrderMilestone-on-Work-Order layout (use admin/fsl-sla-configuration-requirements), NOT for the Lightning page performance Related List - Single vs Full tradeoff in isolation (use admin/lightning-page-performance-tuning), NOT for Industries Timeline-as-related-list (use admin/health-cloud-timeline), NOT for offline-priming related-list caps (use admin/fsl-mobile-app-setup).
日本語の概要は準備中です。原文の説明を表示しています。
Router for the 106 SfSkills `architect` skill packages. Solution and platform architecture: multi-org strategy, scalability limits, licensing, Well-Architected reviews and architecture decision records. Use when the request mentions architecture, solution design, ADR, Well-Architected, scalability, large data volume, multi-org, licensing, tenant isolation, HA/DR, technical debt. Finds and opens the exact skill package to read; it does not contain the guidance itself.
日本語の概要は準備中です。原文の説明を表示しています。
Safely manage multiple GitHub identities (EMU + personal) in agent workflows
日本語の概要は準備中です。原文の説明を表示しています。
Retrospective learning from a completed experience. Takes a project, incident, decision that played out, or time period; gathers ground truth (observations) separately from recollections; spawns reflectors applying different lenses (what-worked-vs-got-lucky, what-didn't, what-surprised, system-rewards-vs-intent, decisions-that-aged, what-to-tell-past-self, patterns-that-recur) in isolation; synthesizes into updated mental models as first-class output. Produces feedback only — no code, no tickets, no artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Abductive reasoning about causes. Takes a phenomenon, separates observations from interpretations, then spawns diagnosticians applying different reasoning lenses (technical, human-factors, process, incentive-structure, environmental, temporal, measurement-artifact, statistical) in isolation. Orchestrator evaluates candidate causes for fit-against-evidence, calibrates confidence honestly, and reports leading candidate(s) with distinguishing evidence needed. Produces feedback only — no code, no tickets, no artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Good-faith divergent brainstorming for achieving a goal. Validates assumptions, then spawns brainstormers running different techniques (first-principles, working-backwards, lateral, analogical, constraints-shift, etc.) in isolation, and synthesizes the pool into a report of standouts, reasonable ideas, and hybrid combinations. Produces feedback only — no code, no tickets, no artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Prospective failure imagination for a plan, decision, or running system. Operates in two modes — **plan mode** (a plan has not yet been committed to; imagine its catastrophic failure broadly) and **scenario mode** (a specific catastrophic scenario is posed against an existing system; investigate causes against the actual code and architecture). Spawns parallel pre-mortemers in isolation across three categories of lens: standard failure classes (technical, operational, estimation, scope, adoption, dependency, team, incentive, detection, reversibility, adversarial), 0-3 ad-hoc target-specific lenses the orchestrator names when warranted, and a first-principles lens that always runs to catch what the prescribed taxonomy misses. Synthesizes into a prioritized risk register with early-warning signals. Produces feedback only — no code, no tickets, no artifacts.
日本語の概要は準備中です。原文の説明を表示しています。