Use this skill to dispatch any task across multiple LLM models in parallel and consolidate their outputs into a single artifact.
This skill should be used for RESEARCH.md artifact reviewer — validates that all findings cite evidence, confidence levels are justified, pitfalls are actionable, and…
This skill should be used for SB-owned post-deploy canary and runtime watch evidence after releases, deploys, or high-risk runtime changes.
This skill captures phase context, decisions, assumptions, constraints, and open questions before planning.
This skill should be used for 3-tier complexity triage: trivial → gsd-fast, medium → gsd-quick with flags, complex → silver-feature escalation.
This skill should be used when ending a session and needing a reusable, project-level handoff prompt for the next session.
This skill should be used for SB-orchestrated bug investigation and fix: triage → path A/B/C → TDD regression test → plan → execute → review → verify → ship
This skill triages review findings, rejects weak findings, fixes valid blockers, and captures deferred work.
This skill creates UI implementation contracts covering layout, states, accessibility, copy, tokens, and acceptance criteria.
This skill verifies completed SB work against plan, spec, tests, UAT criteria, and artifact requirements.
This skill should be used for SB-orchestrated infrastructure/CI-CD workflow: intel → silver-blast-radius → devops-skill-router → devops-quality-gates (7 dims) → plan → execute (no…
This skill writes SB phase plans with dependencies, assumptions, waves, TDD policy, acceptance criteria, and verification steps.
This skill should be used for SB-owned public content, documentation, search-readiness, migration, optimization, and article-writing workflows.
This skill should be used for DESIGN.md artifact reviewer — validates design quality against the SB design template: required sections, non-empty screen/component fields, behavior…
This skill should be used for full SB-orchestrated UI/frontend workflow: intel → product-brainstorm → brainstorm → testing-strategy → gsd-ui-phase → execute+TDD → gsd-ui-review →…
This skill should be used for REQUIREMENTS.md artifact reviewer — validates requirements quality: required sections, REQ-ID format and uniqueness, testable acceptance criteria,…
This skill should be used for AI-guided Socratic spec elicitation: interactive dialogue producing SPEC.md + REQUIREMENTS.md from scratch or augmenting an existing draft
This skill should be used to route freeform text to the right Silver Bullet or GSD skill automatically
This skill should be used for CONTEXT.md artifact reviewer — validates that all discussion points are resolved (locked decision or Claude's Discretion), decisions are specific…
This skill should be used for SB-owned test engineering: test writing, E2E route discovery, test repair, test audit, test performance, and mutation-style challenge workflows.
This skill should be used for SB-owned isolated git worktree setup, finish, merge/PR handoff, and cleanup safety.
This skill performs systematic debugging with reproduction, hypotheses, evidence, root cause, fix plan, and regression guard.
This skill should be used for SB-owned benchmark and adversarial evaluation workflows across agents, models, providers, prompts, or implementation approaches.
This skill audits implemented UI for visual quality, accessibility, responsiveness, interaction quality, and performance.
This skill should be used for VERIFICATION.md artifact review -- validates that verification evidence is fresh, substantive, traceable, and sufficient for SB completion claims.
This skill frames a code review request with scope, risks, artifacts, and reviewer instructions.
This skill should be used for SB-owned engineering retrospectives over a release, date range, incident cluster, or workflow history.
This skill should be used to create, convert, or audit Silver Bullet workflows and atomic flows — analyzes reusable catalog AFs/workflows, plans with review-fix-ladder, implements…
This skill should be used for SB-orchestrated milestone release: silver-quality-gates → audit → gap-closure (max 2x) → docs → release notes → gsd-ship → gsd-complete-milestone
This skill should be used to read .planning/review-analytics.jsonl and produces summary reports showing pass rates, average rounds, and common findings by artifact type
This skill should be used for external artifact ingestion: JIRA/Figma/Google Docs to SPEC.md + DESIGN.md via MCP connectors, plus cross-repo spec fetch with version pinning
Design systems, services, and architectures. Trigger with "design a system for", "how should we architect", "system design for", "what's the right architecture for", or w — from…
Run iterative audit/fix/verify loops for bounded artifact sets by escalating through model and reasoning levels one pair at a time until two consecutive clean passes are achieved…
Create PLAN.md with task breakdown, requirements mapping, and verification steps
Canonical Kay delegation workflow for the Kay sidekick. Use when activating Kay mode before delegated implementation work.
DEPRECATED — use silver-scan for retrospective session scan or silver-context for phase context.
Review changed files for bugs, security issues, and code quality; produce REVIEW.md — from alo-exp/silver-bullet
Enforces dependency injection, pure functions, observable state, and seam-based design
Update the installed Silver Bullet for Forge skill+agent set to the latest release. Re-runs the installer and verifies skill/agent files are refreshed.
Internal external-agent implementer contract for Codex/Cursor delegation child sessions. Not user-invocable — loaded by delegate wrappers when SB_AGENT_DELEGATE_V2=1.
Enforces small, focused modules so any change fits in context without compaction
Delegate the current phase's implementation work from this Forge runtime to another runtime (Claude-SB, Codex-SB, OpenCode-SB, or another Forge) under the parent's existing…
Design test strategies and test plans. Trigger with "how should we test", "test strategy for", "write tests for", "test plan", "what tests do we need", or when the user n — from…
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help…
Draft marketing content across channels — blog posts, social media, email newsletters, landing pages, press releases, and case studies.
Enforces stateless design, efficient resource usage, and patterns that handle 10x-100x growth
Initialize Silver Bullet workflow for a project on Forge — sets up AGENTS.md, .planning/ scaffold, project conventions, and verifies the SB skill+agent set is installed.
Progressively review and fix scoped artifacts or user-confirmed repo-wide work by escalating through every rung of a host-aware model/reasoning ladder, requiring two consecutive…
Canonical Kay stop workflow. Use /sidekick:kay-stop to deactivate delegation and return to direct host behavior.
Identify, categorize, and prioritize technical debt. Trigger with "tech debt", "technical debt audit", "what should we refactor", "code health", or when the user asks abo — from…
Canonical Codex stop workflow. Use /sidekick:codex-stop to deactivate delegation and return to direct host behavior.
Enforces safe AI usage practices, prevents prompt injection, and ensures model safety
Full workflow: brainstorm → specify → quality-gate → plan → execute → verify → secure → ship
Enforces open-closed design, plugin architectures, stable interfaces, and versioning
Migrate a Silver Bullet project from older SB conventions or from Claude Desktop SB to Forge SB — reconciles paths, removes hook-only artifacts, and generates Forge-equivalent…
Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the us — from…
Use when `/silver:clear-stack-state` is invoked or the five-tool stack compression mutex is dirty (sb_stack_double_compression) and tool calls are blocked — clears mutex state and…
Brainstorm product ideas, explore problem spaces, and challenge assumptions as a thinking partner. Use when exploring a new opportunity, generating solutions to a product — from…
This skill should be used when designing, planning, implementing, or reviewing any non-trivial change, or when the user asks to "improve error messages", "better UX for X — from…
This skill should be used when the user runs `/silver:doctor` or asks to audit whether the local Silver Bullet installation and project activation are correct for the active host…