willianbs
UserAI Engineering Operating System
Categories
Indexed Skills (26)
adr-enforcer
Ensures engineering work aligns with Architecture Decision Records and catches architectural drift. Use when planning, implementing, reviewing, or when no ADRs exist and bootstrap is needed. Emits ADR_COMPLIANCE. Never silently invents architecture or auto-modifies ADRs.
ai-eval-harness
Designs and runs evaluation harnesses for AI features and for agent skills themselves. Use when shipping LLM features or measuring skill quality. Emits EVAL_PLAN / EVAL_REPORT. Never claims production quality from a handful of vibes-only prompts.
api-contract-guardian
Guards OpenAPI/proto/GraphQL contracts against breaking changes and drift from implementation. Use on API PRs and releases. Emits CONTRACT_REPORT. Never rubber-stamps breaking changes without a versioning/migration plan.
change-impact-analyzer
Maps blast radius of a proposed change across services, APIs, data, and clients. Use before risky merges, migrations, or multi-service work. Emits IMPACT_REPORT. Never approves ship without naming affected consumers.
code-reviewer
Performs diff-scoped code review for correctness, maintainability, and clear handoffs to security/performance/ADR specialists. Use on PRs and patches. Never modifies code unless asked. Never replaces a full security or performance audit.
context-loader
Discovers and loads only the project context needed for the current task. Use before planning, implementation, review, or debugging to avoid token waste and missing architecture. Emits CONTEXT_PACK. Never makes architectural decisions or loads the entire repo by default.
defect-analyst
Investigates bugs with evidence and analyzes root causes. Use for defects, incidents, flakes, and “why did this break?” work. Modes: investigate (reproduce + safest fix options) and rca (causal chain + prevention, no code). Replaces debugging-investigator and root-cause-analyzer. Never guesses or patches symptoms without evidence.
delivery-planner
Turns validated specs into an executable delivery plan: vertical-slice milestones, risks, rollback, then an atomic task graph with AC IDs. Use before coding for features and multi-step work. Replaces implementation-planner and task-decomposer. Never writes production code or redesigns architecture.
engineering-mentor
Senior mentoring for tradeoffs, knowledge gaps, and growth without taking over execution. Use when the user wants guidance, options, or learning. Modes Mentor (default) vs Executor handoff. Never shames, never silently becomes quality-gate or implementer, and always ends with one concrete next action.
engineering-os
AI Engineering Operating System conductor. Classifies intent, selects a path (lite, standard, incident, architecture, review-only), invokes only the needed skills, threads artifacts, and enforces stop conditions. Use for end-to-end engineering work, “run the OS”, ship a feature, or handle an incident. Never re-implements specialist logic and never runs every skill blindly.
feature-implementer
Implements approved tasks against specs, ADRs, and plans with minimal diffs and verified commands. Use only after planning/validation (or lite path for chores). Emits IMPL_REPORT. Never redesigns architecture, adds unrelated refactors, or self-certifies without running available checks.
guardrails-configurator
Interviews you to configure project engineering guardrails (code, architecture, security, testing, git/PR, ops, AI agent behavior) and writes them to a durable project file. Use for greenfield setup, “set our rules”, or refreshing standards. Emits GUARDRAILS_CONFIG. Never invents team policy as fact, never overwrites an existing guardrails file without confirmation, and never starts feature work.
loop-engineer
Runs recurring agent loops: fixed or dynamic intervals, CI/PR babysitting, and re-invoking prompts/skills until stop criteria. Use for watch-until-done work. Emits LOOP_PLAN / LOOP_STATUS. Never starts unbounded loops without stop conditions or spam-notifies without signal.
migration-surgeon
Plans safe schema/data migrations with expand/contract, backfill, and rollback. Use for DB/search/queue shape changes. Emits MIGRATION_PLAN. Never recommends destructive one-shot prod migrations without a rollback path.
model-router
Routes work to capability tiers (fast, coding, deep-reasoning, long-context, writing) with fallbacks and a suggested skill sequence. Use before costly multi-step work. Emits ROUTE_DECISION. Never performs the engineering task itself and never hardcodes ephemeral vendor model marketing names as the only option.
observability-designer
Designs SLIs/SLOs, structured logs, traces, and alert quality for a feature or service. Use when shipping new paths or fixing noisy/missing alerts. Emits OBS_PLAN. Never recommends alert spam or metrics without a user/journey signal.
performance-auditor
Evidence-based performance and scalability audit against SLOs and budgets. Use for slow paths, capacity risk, or review escalation. Emits PERF_REPORT. Never micro-optimizes without measurement or recommends changes below the noise floor.
postmortem-writer
Writes blameless postmortems from incident and RCA artifacts. Use after incidents resolve. Emits POSTMORTEM. Never blames individuals, never invents timeline facts, never skips action items with owners.
pr-generator
Writes accurate PR descriptions from git diff and commits only—never invented intent or test results. Use when opening or updating a pull request. Emits PR_BODY. Prefer the repo’s PR template when present.
refactoring-advisor
Identifies safe, high-value refactors that preserve externally observable behavior. Use for debt, smells, or “clean this up” asks. Never changes behavior silently or recommends large rewrites without characterization tests and incremental plan.
requirements-grill
Adversarially clarifies product and engineering requirements before Spec Validator. Use when asks are vague or high-stakes. Emits GRILL_NOTES. Never invents product decisions as facts or starts implementation.
security-auditor
Threat-aware security assessment of code and trust boundaries with evidence-based findings. Use for auth, PII, payments, integrations, or when review escalates. Emits SECURITY_REPORT. Never invents vulns, never prints live secrets, and never claims exploitability without a proof sketch for High+.
spec-validator
Validates engineering specs before implementation. Ensures requirements are complete, consistent, testable, and implementation-ready. Use for tickets, PRDs, RFCs, or verbal feature asks. Emits SPEC_STATUS. Never redesigns the product or starts coding.
tdd-executor
Runs red/green/refactor loops against acceptance criteria and TEST_STRATEGY. Use when practicing TDD or when tests should lead implementation. Emits TDD_SESSION. Never skips red, never refactors on red, never claims green without command evidence.
test-strategy-designer
Designs a risk-based test strategy mapped to acceptance criteria without writing test code unless asked. Use after planning and before or during implementation. Emits TEST_STRATEGY. Never chases 100% coverage or tests implementation details by default.
threat-modeler
Builds asset- and STRIDE-based threat models before deep security audits. Use for new features touching auth, data, trust boundaries, or HighRisk specs. Emits THREAT_MODEL. Never invents exploits or replaces security-auditor findings.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.