By alo-exp
Enforce a structured AI-assisted software engineering lifecycle with quality gates, artifact validation, and automated workflows for planning, building, reviewing, deploying, and releasing code.
File a work item with Silver Bullet
Run Silver Bullet benchmark workflow
Assess the blast radius of a change
Fix a bug with Silver Bullet discipline
Run Silver Bullet post-deploy canary workflow
This skill should be used when designing, planning, implementing, or reviewing any system that involves LLM agents, tool use, prompt construction, or agentic workflows, or when the user asks to "add guardrails", "prevent prompt injection", "sanitize LLM output" — enforces prompt injection defense, tool safety, and context integrity
This skill should be used to triage artifact reviewer findings into MUST-FIX / NICE-TO-HAVE / DISMISS based on artifact contract -- prevents over-zealous reviews
This skill should be used for framework for artifact review — defines the standard interface, 2-pass loop, state tracking, and audit trail that all SB artifact reviewers implement
---
Every SB artifact reviewer MUST implement this interface. Reviewers that deviate from this contract are non-conformant and will not integrate with the review loop.
This skill should be used when designing, planning, implementing, or reviewing any system that involves LLM agents, tool use, prompt construction, or agentic workflows, or when the user asks to "add guardrails", "prevent prompt injection", "sanitize LLM output" — enforces prompt injection defense, tool safety, and context integrity
This skill should be used to triage artifact reviewer findings into MUST-FIX / NICE-TO-HAVE / DISMISS based on artifact contract -- prevents over-zealous reviews
This skill should be used for framework for artifact review — defines the standard interface, 2-pass loop, state tracking, and audit trail that all SB artifact reviewers implement
This skill should be used to apply 7 IaC-adapted quality dimensions against infrastructure and DevOps changes. Use after /silver:blast-radius and before /silver:plan in the devops-cycle workflow. Skips usability because IaC has no direct user interface. All dimensions must pass — any ❌ is a hard stop.
This skill should be used for context-aware routing table that maps IaC toolchain, cloud provider, and DevOps context to the best available plugin skill. Used by the devops-cycle workflow at contextual trigger points. Not a workflow step — a lookup utility.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Agentic Process Orchestrator for AI-native Software Engineering and DevOps.
Silver Bullet is the lifecycle orchestration and enforcement layer for AI-native software engineering. It owns the core project flow: intent routing, context, planning, execution, verification, review, security, documentation, shipping, and release discipline. Hook-backed gates keep agents from skipping required steps before code, PRs, deploys, or releases.
Plain version: describe what you want to do. Start with /silver. Silver Bullet
classifies the task, composes the right SB-owned workflow, and records the
evidence needed to continue safely.
"There is no single development, in either technology or management technique, which by itself promises even one order-of-magnitude improvement..." - Fred Brooks, 1986
Brooks was right. Silver Bullet is not one magic technique. It is the coordinated process layer that makes AI-native delivery less dependent on agent memory and operator vigilance.
Silver Bullet now owns the knowledge-work and lifecycle behaviors it explicitly depends on as SB-owned skills. Optional plugins remain useful when they extend SB into DevOps, provider, data, documentation, or tool-specific domains, but they are no longer required for the core software engineering lifecycle.
| Area | Silver Bullet owns |
|---|---|
| Entry point | /silver routes freeform work into a task-shaped workflow |
| Workflow shape | Dynamic composition from 18 atomic flows |
| Process discipline | Hook-enforced, state-tracked lifecycle evidence |
| Quality | Product, security, DevOps, docs, UAT, CI, and release gates |
| Delivery safety | Mechanical blocks on unsafe edits, PRs, deploys, and releases |
| Continuity | Session logs, handoff, issue capture, knowledge capture, anti-stall checks, and forensics |
Silver Bullet is an Agentic Process Orchestrator (APO):
Silver Bullet can still call optional extension plugins when a selected workflow needs a domain-specific capability, especially DevOps/provider tools. It does not use lifecycle-overlap knowledge-work plugins as default lifecycle dependencies.
You normally start with:
/silver improve the account settings page and ship it safely
The router classifies the request, displays the selected route, and invokes the appropriate SB-owned workflow. Examples:
| Intent | Typical route | Why |
|---|---|---|
| Build or enhance a feature | silver:feature | Runs SB context, planning, execution, review, verification, and ship |
| Fix a regression | silver:bugfix | Inserts debug/TDD before the normal lifecycle |
| Work on UI | silver:ui | Adds SB design contract and UI quality review around execution |
| Change infrastructure | silver:devops | Adds blast radius, IaC gates, promotion, and rollback discipline |
| Research a decision | silver:research | Produces a decision artifact before implementation |
| Prepare a release | silver:release | Runs documentation, UAT, milestone, release, and publication gates |
| Make a small safe edit | silver:fast | Routes low-risk work through a lighter path |
| Explicit legacy lifecycle request | SB equivalent by default | Legacy lifecycle names are compatibility routes unless the user explicitly asks for an external plugin |
Silver Bullet starts from two workflow families, then composes the exact flow chain needed for the task:
| Workflow family | Use for | Composition surface |
|---|---|---|
full-dev-cycle | Applications, APIs, CLIs, libraries, plugin work | Clarify, specify, plan, execute, review, secure, verify, document, ship, release |
devops-cycle | Terraform, Kubernetes, Helm, CI/CD, cloud, ops | Incident path, blast radius, IaC quality, environment promotion, deploy/rollback, release |
The canonical flow catalog lives in docs/composable-flows-contracts.md. It contains 18 atomic flows:
BOOTSTRAP -> ORIENT -> CLARIFY -> DECIDE -> SPECIFY -> PLAN
-> DESIGN CONTRACT -> EXECUTE -> UI QUALITY -> REVIEW -> SECURE
-> VERIFY -> QUALITY GATE -> SHIP -> DEBUG -> DESIGN HANDOFF
-> DOCUMENT -> RELEASE
Sidekick — AI coding-agent delegation workflows for Claude Code, Codex, and Cursor. Kay and Codex are the supported sidekicks: Kay installs through Sidekick, while Codex delegates to the local OpenAI Codex CLI. The Claude-facing workflow bodies are generated from skills into agents/claude.
npx claudepluginhub alo-exp/silver-bullet --plugin silver-bulletComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.