epicsagas
UserAlcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid search for precision retrieval, tree-sitter code indexing so agents understand your codebase structure, and policy enforcement for doc consistency.
Categories
Indexed Skills (53)
alcove
HTTP API-based documentation server (always running). Questions about project architecture, conventions, decisions, code structure, tech debt, env config, progress, or doc health. Also: init project, audit docs, lint, validate, promote note, rebuild index, search vaults.
debug
Systematic root-cause isolation for test failures, runtime errors, or unexpected behavior. Narrow hypothesis → verify → fix.
discover
Trigger: vague/unfocused request or solution-without-problem. Also invoked via /discover command. Reframes goal before acting.
orchestrate
Trigger: active multi-agent run. Handles inbox reading, dep resolution, message formatting, handoffs. Also provides status dashboard and intervention control via internal modes.
perf
Performance optimizer for loops, DB queries, rendering, and batch operations. Catches N+1 queries, missing indexes, and unnecessary re-renders.
secure
Security review checklist with optional engagement scoping. Use when auth, DB, API, infra, or secrets code is touched.
simplify
Code simplification for high-complexity files. Targets deep nesting, copy-paste patterns, and god functions.
tdd
Test-Driven Development enforcer. Red→Green→Refactor cycle with no production code without a failing test first. Use for new features and bug fixes.
verify
Pre-merge verification gate. Build, test, and lint must all pass before marking done or shipping.
code-reviewer
Code smell detector and refactoring advisor. Triggers on: file path mentioned, 'review this code', 'find smells', 'analyze', 'refactor', or code shared. Calls Episteme HTTP API (analyze + refactor endpoints) immediately. Outputs smell table, ranked refactorings, principle violations.
episteme-researcher
Use this agent when you need to explore or research software engineering knowledge — finding design patterns, refactorings, laws, and code smells, or mapping relationships between concepts in the Episteme knowledge graph.
episteme
Software engineering knowledge graph — patterns, laws, refactorings, smells. Activates on any code quality concern, design decision, architecture review, or engineering question — even when the user describes problems informally. Uses Episteme HTTP API (resolved via `epis api env`) via curl.
benchmark
Executes Bare-vs-Epic A/B benchmarking, Ring 0 Guard 50 challenge, and full golden set evaluation for epic-harness. Orchestrates worker sessions, enforces strict workspace isolation, and synthesizes multi-dimensional comparison reports in TUI. Triggers: /benchmark, 'benchmark', 'a/b test', 'eval harness', 'smoke test', 'full eval'.
_critic
HarnessX Critic (Tier 2.1) — adversarial review of evolved-skill proposals against trace evidence. Detects reward hacking and manifest/evidence contradictions. Out-of-band LLM counterpart to the in-loop deterministic critic in src/evolve/critic.rs.
_dispatch
Core router. Always active. Auto-invokes matching skill before every response. Runs confusion protocol on high-risk ambiguity.
agent-introspection
Loop-breaking self-diagnosis. Use when 3+ consecutive failures occur, circular retries persist, or context overwhelms the session.
audit
Audit phase. Parallel review: code quality + security + tests. Semantic dedup of cross-mode findings. Outputs PASS/WARN/FAIL per dimension. Validates spec coverage.
commit
Conventional Commits 1.0 generator. Stages relevant files, infers type(scope): description, never uses --no-verify.
document
Documentation generator for public APIs, functions, and modules. Use when exports, signatures, or new modules are added or changed.
eval
Quality and performance evaluation with baseline comparison. Sub-modes: correctness, performance, quality, regression. Outputs PASS/WARN/FAIL per dimension. Use for pre-ship evaluation or regression checks.
evolve
Ring 3 evolution engine. Analyzes session observations, generates and improves evolved skills, shows metrics dashboard. Subcommands: status, history, rollback, reset. Use for post-session review and skill improvement.
go
Go phase. Reads the approved SPEC file, maps Requirements to tasks (plan), executes via TDD (build), and integrates results verifying all Acceptance Criteria.
orbit
State-persisted autonomous pipeline: spec → go → audit → eval → ship → evolve in one command. Auto-detects direct/council/interactive mode. Crash-recoverable via PIPELINE-*.json. Hands-off until PR.
reflect
On-demand human self-assessment of AI usage quality. Scores 5 dimensions from session data. Not agent performance review.
ship
Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.
spec
Spec phase. Converts user requirements into a numbered Requirements + Acceptance Criteria document saved as SPEC-{timestamp}.md. Prompts /team suggestion when 3+ requirements are detected.
threat-model
Threat modeling and attack surface analysis. Use when assessing security boundaries, modeling threat actors, or generating threat scenarios.
triage
Adversarial validation of vulnerability findings. Use when triaging security findings, validating vulnerabilities, or prioritizing remediation.
vuln-scan
Systematic vulnerability scan across injection, auth, data exposure, and dependencies — traced by reading code, not grepping for keywords. Use when scanning for vulnerabilities, reviewing security, or validating threat models.
architecture-analyst
Use this agent when you need to evaluate a system architecture or technology decision — identifying scalability risks, structural smells, law violations (Conway, Amdahl, Gall), and design pattern misuse using the Episteme knowledge graph.
episteme-advisor
Use this agent when the user faces an engineering decision, trade-off, or architecture question — choosing between patterns, resolving design conflicts, or applying refactorings. Grounds every recommendation in the Episteme knowledge graph.
council
4-voice parallel deliberation (Architect · Skeptic · Pragmatist · Critic) for architecture, tech selection, or design decisions with no clear answer. Anti-anchoring: each voice gets independent context. Records decision in harness-mem.
council
Multi-model council (claude + codex + agy + grok). Independent answers, anonymized cross peer-review with self-exclusion, then chairman synthesis. Use for architecture decisions, contested technical questions, and high-stakes judgments where a genuinely independent second opinion matters. Invoke as "/council <question>".
context
Working-state snapshot guidance. Restates task/files/decisions in one block so state survives context compaction. Compaction timing is the host's job.
team
Org-level agent team designer via `epic team` CLI (cross-project, append-merge). Subcommands: list, show, sync, link, unlink, history. Use when setting up agents, designing teams, or /spec yields 3+ requirements.
agent-glance
Connect a GeekMagic SmallTV (SD_RU/SDPro ESP8266 or SmallTV Ultra stock firmware — auto-detected) as a Claude Code status monitor. Use when the user wants to show Claude's working/waiting/done state, model, context %, and token counts on the SmallTV display. Triggers on "smalltv", "geekmagic", "status monitor", "기기에 상태 표시", "시계 모니터".
ag-setup
Onboard and set up the GeekMagic SmallTV as an agent status monitor — finds the device, saves its IP, backs up the device, and switches it to dedicated-display mode. Use when the user wants to connect, onboard, or configure a SmallTV status monitor for the first time, or when they say "setup smalltv", "기기 연결", "모니터 설정".
ag-status
Health check for the SmallTV monitor — device reachability, display state, config, and recent errors. Use when the SmallTV display stops updating, shows the wrong screen, or the user asks whether the monitor is working ("status monitor 상태", "화면이 안 바뀐다", "smalltv 진단").
ag-restore
Revert the SmallTV to the clock/themes it had before the monitor took it over. Use when the user wants their original clock back, wants to undo the monitor takeover, or says "원래대로", "시계로 돌려줘", "restore smalltv".
ag-test
Push a test frame (working / waiting / done) to the SmallTV to check rendering. Use when the user wants to verify the display renders correctly, preview a state or GIF preset, or says "테스트 프레임", "화면 확인", "smalltv test".
ag-theme
Switch the SmallTV screen — weather, forecast, clocks, or back to the monitor (SmallTV Ultra firmware only). Use when the user wants to show a different screen on the device, or says "날씨 보여줘", "일기예보", "시계로 바꿔", "smalltv theme".
wishket-apply
Draft Wishket project proposals. Writes a markdown `draft.md` for local review and a plain-text `form.txt` for the Wishket paste form. Recommends and ranks portfolio attachments. 위시켓 공고 지원서·제안서 작성. "위시켓 지원서 써줘", "이 공고 지원할 건데 제안서", "제안서 작성" 등에 사용. 포트폴리오 추천·선별 포함.
wishket-dashboard
Launch the Wishket local dashboard web UI. View and manage inbox triage (interested/skip), pipeline stages, proposals, profiles, portfolios, and reports. 위시켓 로컬 대시보드 webui 실행. "대시보드", "웹 UI 켜줘", "지원 현황 화면으로 보여줘", "공고 분류할래", "dashboard" 등에 사용.
wishket-deadline
Register Wishket project deadlines into macOS / Google Calendar. Generates .ics files and offers direct AppleScript addition. 위시켓 공고 마감을 macOS 캘린더/구글 캘린더에 등록. "마감 캘린더에 넣어줘", "이 공고 마감 알림 설정", "마감 등록해줘" 등에 사용.
wishket-feedback
Calibrate matching profile using historical application outcomes. Analyzes win rates by grade in the pipeline store (state.db applications) to suggest profile.yaml adjustments. 지원 결과 데이터로 매칭 프로필 보정. "매칭 잘 안 되네", "프로필 점검해줘", "수주율 높여줘", "피드백 분석" 등에 사용.
wishket-onboard
Onboarding for Wishket plugin. Verifies binary installation, sets up tech profile, executes baseline scan, and provides action guides. 위시켓 플러그인 온보딩 (바이너리 설치 확인 + 프로필 생성 + 베이스라인 스캔 + 다음 행동 요령). "위시켓 시작할게", "위시켓 세팅해줘", "온보딩" 등에 사용.
wishket-pipeline
Track Wishket application pipeline. Manages project stages across the 10 Wishket phases in the pipeline store (state.db), calculating conversion and win rates. 위시켓 지원 파이프라인 추적. 관심 공고 관리 및 10단계 상태 갱신, 수주율/전환율 계산. "위시켓 지원했어", "지원 현황", "파이프라인 보여줘", "미팅 잡혔어", "계약했어", "떨어졌어", "탈락" 등에 사용.
wishket-portfolio
Draft Wishket portfolio entries. Analyzes site URLs, GitHub repositories, requirement documents (PDF/PPT/DOCX/XLSX), or project folders to generate formatted plain-text portfolio drafts. 위시켓 포트폴리오 등록 폼 작성. "포트폴리오 작성해줘", "위시켓 포트폴리오 만들어줘", "이 프로젝트로 포트폴리오 써줘" 등에 사용.
wishket-quote
Estimate project cost and man-days for Wishket postings. Decomposes project requirements into functional units and provides low/standard/high estimates. 위시켓 공고 견적 산출. "견적 계산해줘", "이 공고 얼마 정도 불러야 해?", "공수 산정", "견적 잡아줘" 등에 사용. 휴리스틱 기반 견적.
wishket-scout
In-depth analysis and report generation for new Wishket projects. Scans new projects, analyzes top candidates via wishket-analyst, and creates a report. 위시켓 신규 공고 심층 분석·리포트. "위시켓 분석", "스카우트", "리포트 뽑아줘", "심층 분석해줘" 등에 사용. 목록만 보려면 wishket-scan.
wishket-profile
View or edit technical matching profile. Use when asked to view Wishket profile, change skill weights, add/remove skills, or update matching criteria. 매칭용 기술 프로필 조회/편집. "내 위시켓 프로필 보여줘", "rust 가중치 올려줘", "react 스킬 추가", "매칭 기준 바꿔줘" 등에 사용.
wishket-scan
Diff scan for new Wishket projects registered since the last scan. Use for quick new project checks. 위시켓 신규 프로젝트 diff 스캔 (마지막 스캔 이후 신규만). "위시켓 스캔", "새 프로젝트 있어?", "새 외주 올라온 거 있나?" 등에 사용. 심층 분석·리포트는 wishket-scout.
wishket-search
Ad-hoc search for Wishket projects without recording to seen cache. Use for keyword searches and browsing project listings. 위시켓 프로젝트 임시 검색 (캐시 기록 없음, 일상 조회용). "위시켓 검색", "위시켓에 flutter 프로젝트 있어?", "외주 찾아줘", "외주 프로젝트 검색해줘" 등 키워드 검색·페이지 이동에 사용. 신규 diff는 wishket-scan, 심층 리포트는 wishket-scout.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.