Claude Skills by alo-exp

Explore multiple approaches before committing to a design

Adaptive questioning to surface assumptions and lock decisions before planning

Execute PLAN.md with atomic commits, deviation handling, and TDD discipline

Orient in the existing codebase before planning or implementing changes

Create PLAN.md with task breakdown, requirements mapping, and verification steps

Show current phase status, remaining tasks, and next actions

Address code review findings systematically with atomic commits

Review changed files for bugs, security issues, and code quality; produce REVIEW.md

Security audit of changes; enforce defense in depth and OWASP best practices

Push branch and create PR; refuses to ship without passing verification

Validate that implementation matches spec and requirements

Execute verification steps from PLAN.md and produce VERIFICATION.md

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 /gsd:plan-phase 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.

This skill should be used when designing, planning, implementing, or reviewing any non-trivial change, or when the user asks to "add plugin point", "make this pluggable", "add hooks for X" — enforces open-closed design, plugin architectures, stable interfaces, and versioning so systems grow without breaking existing consumers

Merge, PR, or cleanup decisions for completing a branch

Delegate the current phase's implementation work from Claude-SB to a Forge subagent under the parent's existing phase-lock. Spawns `forge -p <envelope>` with SB_PHASE_LOCK_INHERITED=true so the child does not double-claim, then integrates the structured Forge result into the parent phase artifacts.

This skill should be used when designing, planning, implementing, or reviewing any non-trivial change, or when the user asks to "split this file", "decouple X from Y", "refactor into modules" — enforces small, focused modules so any change fits in context without compaction

This skill should be used when designing, planning, implementing, or reviewing any non-trivial change, or when the user asks to "add retries", "add error handling", "add circuit breaker", "handle failures" — enforces graceful degradation, proper error handling, retry strategies, and fault-tolerant patterns so systems stay up when things go wrong

This skill should be used when designing, planning, implementing, or reviewing any non-trivial change, or when the user asks to "generalize this", "extract shared util", "deduplicate this" — enforces DRY, well-defined abstractions, and composable components so code is written once and used many times

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 (not vague), and no contradictions exist between decisions

This skill should be used for cross-artifact consistency reviewer -- validates alignment across SPEC.md, REQUIREMENTS.md, ROADMAP.md, and DESIGN.md. Detects unmapped ACs, orphaned requirements, missing design coverage, and phantom phase requirements.

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 and state tables, and orphaned component detection against SPEC.md

This skill should be used for INGESTION_MANIFEST.md artifact reviewer — validates that all source artifacts are listed, statuses are accurate, failed artifacts have corresponding ARTIFACT MISSING blocks in the linked SPEC.md, and the manifest supports resumability

This skill should be used for REQUIREMENTS.md artifact reviewer — validates requirements quality: required sections, REQ-ID format and uniqueness, testable acceptance criteria, priority fields, traceability frontmatter, and SPEC.md criterion coverage

This skill should be used for RESEARCH.md artifact reviewer — validates that all findings cite evidence, confidence levels are justified, pitfalls are actionable, and recommendations are concrete and implementable

This skill should be used for ROADMAP.md artifact reviewer — validates roadmap quality: required phase fields, 100% requirement coverage, no phantom requirements, no circular phase dependencies, success criteria derivation, and plans field completeness

This skill should be used for SPEC.md artifact reviewer — validates spec quality against the SB spec template: required sections, non-empty overview, user story format, testable acceptance criteria, assumption completeness, and frontmatter fields

This skill should be used for UAT.md artifact reviewer — validates that every SPEC.md Acceptance Criterion has a UAT row, evidence is substantive (not 'looks good'), spec-version matches, and all results have pass/fail status with evidence

This skill should be used when designing, planning, implementing, or reviewing any non-trivial change, or when the user asks to "handle more load", "scale this out", "optimize for throughput" — enforces stateless design, efficient resource usage, and architectural patterns that handle 10x-100x growth without redesign

This skill should be used when designing, planning, implementing, or reviewing any non-trivial change, or when the user asks to "harden X", "add auth", "validate input", "check for vulnerabilities", "secure endpoint" — enforces defense in depth, input validation, secure defaults, and OWASP best practices to prevent vulnerabilities before they ship

This skill should be used to classify and file any deferred or identified work item to the correct PM destination — GitHub Issues + project board (when issue_tracker=github) or local docs/issues/ markdown (when issue_tracker=gsd or absent) — and return a stable, referenceable ID.

This skill should be used to assess the blast radius of a proposed infrastructure or DevOps change before planning. Maps change scope, downstream dependencies, failure scenarios, rollback plan, and change window risk. Required before /devops-quality-gates in the devops-cycle workflow.

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

Turn vague ideas or requirements into a decision-ready brief that merges PM framing and Superpowers brainstorming before handing off to GSD.

This skill should be used to generate structured release notes from git history since the last tag, then create a GitHub Release (for GitHub repos) or output notes for manual publishing

This skill should be used for SB-orchestrated infrastructure/CI-CD workflow: intel → silver:blast-radius → devops-skill-router → devops-quality-gates (7 IaC dims) → GSD plan/execute/verify → review → secure → ship

This skill should be used to bootstrap, reconcile, and semantically audit complete task-level documentation updates from docs/doc-scheme.md + docs/doc-scheme.json

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 for full SB-orchestrated feature development workflow: orient → clarify/decide → silver:quality-gates → GSD plan/execute/verify → ship

This skill should be used for root-cause investigation for completed sessions, abandoned sessions, verification failures, or mid-session stalls — classifies failure, walks investigation path, writes report to <project-root>/docs/silver:forensics/

This skill should be used when ending a session and needing a reusable, project-level handoff prompt for the next session. It summarizes project state, active milestone, key docs, constraints, verification/release status, and open follow-ups without defaulting to task-specific detail unless explicitly requested.

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

This skill should be used to initialize Silver Bullet enforcement for a project — checks dependencies, auto-detects project, scaffolds silver-bullet.md + config + workflow files, and reconciles any existing project instruction file in place without creating one

This skill should be used when the user runs `/silver:migrate` or asks to migrate an older Silver Bullet project from the retired single-file WORKFLOW.md model to per-instance `.planning/workflows/<id>.md` tracking.

This skill should be used for dual-mode: design-time checklist (pre-plan) or adversarial audit (pre-ship). Mode auto-detected from artifact state.

This skill should be used for SB-orchestrated milestone release: silver:quality-gates → audit → gap-closure (max 2x) → docs → GSD ship/complete milestone → silver:create-release