slash commands
Reference
Commands, agents, and skills
This page is generated from the repository so the public reference follows the plugin as it changes.
specialist agents
skills across five tiers
Commands
Slash command surface
commands/guild-audit.md
/guild:audit
Security audit of installed Guild scripts — SHA-256 hash every file, flag network/filesystem access patterns, and record results. Per guild-plan.md §13.1 and §15.1 #12.
commands/guild-evolve.md
/guild:evolve
Kick off skill evolution — runs the eval loop, shadow mode, and flip-gating promotion pipeline. Manual mode pauses at the promotion gate for user review; --auto runs unattended if the gate criteria are met without regressions. Per guild-plan.md §13.1.
commands/guild-rollback.md
/guild:rollback
Revert a skill to a previous version by snapshotting the current state as vN+1 and restoring vN (or vN-n). Non-destructive — every rollback is itself a versioned artifact. Per guild-plan.md §13.1 and §11.3.
commands/guild-stats.md
/guild:stats
Show usage stats — task count, completion rate, flip counts, top-used skills, top-requested specialists, open reflection backlog, and audit drift summary. Pure read; never writes. Per guild-plan.md §13.1.
commands/guild-team.md
/guild:team
Team operations — propose a new team, show the current team, or edit it. Per guild-plan.md §13.1. Dispatches to guild-team-compose skill. `edit --allow-larger` lifts the 6-specialist cap from §7.2.
commands/guild-wiki.md
/guild:wiki
Wiki operations — ingest a source, query the wiki, or run lint. Per guild-plan.md §13.1. Dispatches to guild:wiki-ingest / guild:wiki-query / guild:wiki-lint.
commands/guild.md
/guild
Top-level Guild entry. Runs the 7-step lifecycle: brainstorm → team-compose → plan → context-assemble → execute-plan → review → verify-done. Per guild-plan.md §13.1.
Agents
Specialist roster
agents/architect.md
architect
Owns systems design, architectural tradeoff analysis, and ADR authoring. Produces design docs, tradeoff matrices, and Architecture Decision Records — not implementation code.
agents/backend.md
backend
Owns API contracts, data layer, migrations, service integrations, queue consumers, and worker jobs.
agents/copywriter.md
copywriter
Owns long-form blog writing, product microcopy, lifecycle email sequences, and voice-guide authoring.
agents/devops.md
devops
Owns CI/CD pipelines, infrastructure-as-code, observability stacks, release/rollout, and incident runbooks. Produces pipeline configs, Terraform/Pulumi/CDK, dashboards, alerts, SLOs, runbooks — not application code.
agents/marketing.md
marketing
Owns positioning, GTM launch plans, campaign briefs, and A/B copy-variant programs.
agents/mobile.md
mobile
Owns native and cross-platform mobile implementation for iOS (Swift/SwiftUI), Android (Kotlin/Compose), and React Native / Expo, plus mobile performance tuning, store submission, and mobile build/release (Fastlane, Xcode Cloud, EAS, TestFlight, Play Console).
agents/qa.md
qa
Owns test strategy, coverage decisions, property-based tests, snapshot tests, regression-suite shape, and flaky-test investigation. Produces test plans, suite-level test code, and flakiness diagnoses — not app code, not CI config.
agents/researcher.md
researcher
Owns deep-dive investigations, paper/source digests, and comparison tables that synthesize external knowledge before a decision. Produces research briefs with cited sources — not designs, not code, not ADRs.
agents/sales.md
sales
Owns outbound revenue motion — cold outreach, discovery, proposals, follow-ups, objection handling.
agents/security.md
security
Owns threat modeling, dependency/CVE auditing, auth/authz flow review, and secrets scanning. Produces threat models, audit reports, auth-flow findings, and secrets-scan results — not production code, not pipeline config.
agents/seo.md
seo
Owns search-discoverability work across keyword research, on-page optimization, technical audits, and internal-linking strategy.
agents/social-media.md
social-media
Owns platform-native social content and the calendars that sequence it.
agents/technical-writer.md
technical-writer
Owns API reference docs, user manuals, tutorials, how-to guides, and release notes / changelogs.
Skills
Skill catalog
core skills 1
guild-principles
Guild's five operating principles — Think-before-doing, Simplicity-first, Surgical-changes, Goal-driven-execution, Evidence-over-claims — loaded as the mandatory prelude for every Guild specialist (engineering, writing, or commercial). The first four are Karpathy's 4; the fifth...
skills/core/principlesmeta skills 13
guild-audit
Security audit of Guild plugin scripts — SHA256 hashes, source, network + filesystem flags. Produces a static report listing every hook script, tooling script, and MCP server with (a) file hash, (b) declared tool access / allowed-tools frontmatter, (c) any network/egress calls (...
skills/meta/auditguild-brainstorm
Socratic clustered-question flow that turns a vague user brief into an approved `.guild/spec/<slug>.md`. Captures the seven planning-contract fields from `guild-plan.md §8.1` — goal, audience, success criteria, non-goals, constraints, autonomy policy, and known risks/rollback —...
skills/meta/brainstormguild-context-assemble
Assembles per-specialist 3-layer context bundle: Universal (~400 tokens — guild:principles + project-overview + goals) + Role-dependent (~800–1500 — standards + 2–4 entity pages matching role) + Task-dependent (~800–1500 — lane from plan + named refs + upstream contracts + activ...
skills/meta/context-assembleguild-create-specialist
Runs the §12 7-step workflow to mint a new shipping specialist — interview, draft under agents/proposed/, boundary scan of existing agents/*.md, propose adjacent-boundary edits (DO NOT
skills/meta/create-specialistguild-decisions
Captures Q&A during specialist work as structured ADR-lite decisions under .guild/wiki/decisions/<slug>.md per `guild-plan.md §10.3`. Required when a specialist reaches uncertainty (principle #1 "ask") and the answer is non-trivial — user supplies the answer, this skill writes t...
skills/meta/decisionsguild-evolve-skill
Runs the §11.2 10-step evolve pipeline on one named skill — snapshot, load evals, dispatch paired subagents (A=current, B=proposed), drafter writes assertions, grader evaluates, benchmark + flip report, shadow mode, promotion gate, description optimizer, commit or archive. NEVER...
skills/meta/evolve-skillguild-execute-plan
For each specialist lane in the plan: invoke `guild:context-assemble` to build the bundle, then dispatch the specialist via Agent tool (subagent backend, default) or agent-team teammate spawn (opt-in). Parallelize lanes when `depends-on:` allows. Collect per-lane handoff receipt...
skills/meta/execute-planguild-plan
Turns an approved `.guild/spec/<slug>.md` plus `.guild/team/<slug>.yaml` into a per-specialist lane plan at `.guild/plan/<slug>.md`. Each lane carries `task-id`, `owner`, `depends-on:`, `scope`, `success-criteria`, and `autonomy-policy` so `guild:execute-plan` can dispatch paral...
skills/meta/planguild-reflect
Post-task reflection. Consumes a compact run summary (from scripts/trace-summarize.ts), handoff receipts, and verify.md, and emits proposals to .guild/reflections/<run-id>.md. Proposals cover (a) skill-improvement candidates (a skill triggered wrong N times, or body needs a new...
skills/meta/reflectguild-review
Two-stage review of per-specialist handoff receipts (spec compliance first, then quality). Consumes compact receipts from `.guild/runs/<run-id>/handoffs/` — NOT full specialist conversations. Writes `.guild/runs/<run-id>/review.md` with per-lane pass/fail + blocker list.
skills/meta/reviewguild-rollback-skill
Rolls back a skill to a previous version from .guild/skill-versions/<skill>/v<N>/. The rollback ITSELF is a snapshot — non-destructive, appends a new vN+1 with "source: rollback-from-vX" metadata. Can walk the stack (rollback N steps at once, default 1). Re-runs the restored ver...
skills/meta/rollback-skillguild-team-compose
Match spec domains to Guild's 13 shipping specialists, present existing + gaps with A/B/C/D options (auto-create / skip / substitute / compose from scratch), enforce cap-6 and default 3–4 rules, choose subagent (default) vs agent-team backend, and write `.guild/team/<slug>.yaml`.
skills/meta/team-composeguild-verify-done
Final gate before task close. Runs (1) tests the spec defined, (2) scope check — every changed file traces to a lane, (3) success-criteria match, (4) no open blocker `followups:`, (5) assumptions reviewed. Writes `.guild/runs/<run-id>/verify.md` — pass/fail + run summary. On pas...
skills/meta/verify-doneknowledge skills 3
guild-wiki-ingest
Promotes raw sources into .guild/wiki/<category>/ with §10.1.1 frontmatter (type, owner, confidence, source_refs, created_at, updated_at, expires_at, supersedes, sensitivity). Copies the immutable source to .guild/raw/sources/<slug>/original.<ext> with sha256 checksum + metadata...
skills/knowledge/wiki-ingestguild-wiki-lint
Audits .guild/wiki/ for contradictions between pages, stale claims (expires_at passed), missing §10.1.1 frontmatter fields, orphan pages (not linked from index.md), concepts referenced ≥3x without a page, missing source_refs resolution to .guild/raw/sources/<slug>/, and decision...
skills/knowledge/wiki-lintguild-wiki-query
Searches .guild/wiki/ by category, tag, freshness, confidence, or full-text. Under ~200 pages uses ripgrep/filesystem via Grep/Glob tools. Above that scale, delegates to guild-memory MCP (optional P6). Resolves source_refs back to .guild/raw/sources/<slug>/ when users ask "where...
skills/knowledge/wiki-queryfallback skills 5
guild-finish-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — presents structured options for merge, PR, or cleanup. The Guild fallback chained off `guild:execute-plan` once all lanes report DONE and `guild:verify-done` is green.
skills/fallback/finish-branchguild-request-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements. The Guild fallback that surfaces a fresh-context review subagent for any specialist's output.
skills/fallback/request-reviewguild-systematic-debug
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. The Guild fallback engineering and ops specialists (devops, qa, security, hook-engineer, tooling-engineer) load when their T5 skills don't yet cover the debugging discipline.
skills/fallback/systematic-debugguild-tdd
Use when implementing any feature or bugfix, before writing implementation code. The Guild fallback that engineering specialists (backend, qa, devops, security, mobile) load when their T5 specialist skills do not yet cover the methodology layer.
skills/fallback/tddguild-worktrees
Use when starting feature work that needs isolation from the current workspace, or before executing implementation plans — creates isolated git worktrees with smart directory selection and safety verification. The Guild fallback dispatched-from `guild:execute-plan` and `guild:fi...
skills/fallback/worktreesspecialists skills 50
architect-adr-writer
Writes a full Architecture Decision Record (ADR) with Context / Drivers / Options / Decision / Consequences / Date / Status. Output: `.guild/runs/<run-id>/adr/<slug>.md`. Pulled by the `architect` specialist.
skills/specialists/architect-adr-writerarchitect-systems-design
Multi-component system design. Produces a design doc at `.guild/runs/<run-id>/design/<slug>.md` with component diagram (text/mermaid), data-flow, failure modes, and non-functional requirements (latency, availability, cost envelope). Pulled by the `architect` specialist.
skills/specialists/architect-systems-designarchitect-tradeoff-matrix
Scores 2–4 architecture options across named axes (cost, complexity, performance, ops burden, time-to-ship, reversibility, etc.) and surfaces a recommendation. Output: markdown table with per-cell rationale plus a final pick. Pulled by the `architect` specialist.
skills/specialists/architect-tradeoff-matrixbackend-api-contract
Designs REST / GraphQL / RPC endpoints — routes, methods, request/response schemas, error envelope, auth, versioning, pagination. Output: OpenAPI/GraphQL SDL fragment or a markdown spec the backend can implement against. Pulled by the `backend` specialist.
skills/specialists/backend-api-contractbackend-data-layer
Designs database schemas, access patterns, indexes, and query shapes for a single storage boundary. Output: DDL (SQL) or schema fragment plus query-pattern notes and indexing plan. Pulled by the `backend` specialist.
skills/specialists/backend-data-layerbackend-migration-writer
Authors a safe, reversible database migration — up and down files, data-backfill plan, lock-budget analysis, and rollback strategy. Pulled by the `backend` specialist.
skills/specialists/backend-migration-writerbackend-service-integration
Integrates a service with an external HTTP/gRPC/webhook API — client module, timeouts, retries with backoff, circuit breaker, idempotency, error mapping, and observability. Output: integration module + config + error-mapping table. Pulled by the `backend` specialist.
skills/specialists/backend-service-integrationcopywriter-email-sequences
Writes lifecycle, onboarding, transactional, re-engagement, and drip email sequences — the sequence plan (triggers, timing, branching) plus per-email subject, preview, and body copy. Pulled by the `copywriter` specialist.
skills/specialists/copywriter-email-sequencescopywriter-long-form
Writes long-form marketing copy — blog posts, case studies, thought-leadership pieces, landing-page longform — with a clear angle, an intro-body-CTA arc, and H1/H2 scaffolding a reader can scan. Pulled by the `copywriter` specialist.
skills/specialists/copywriter-long-formcopywriter-product-microcopy
Writes in-product strings — button labels, empty states, error messages, tooltips, form labels, confirmation dialogs, toast copy. Output is a string table keyed by component/key so engineering can drop it straight into i18n files. Pulled by the `copywriter` specialist.
skills/specialists/copywriter-product-microcopycopywriter-voice-guide
Authors or refreshes a brand voice guide — principles, do/don't examples, sample rewrites, tone-by-surface matrix. Output is a `voice.md` the whole team writes against. Pulled by the `copywriter` specialist.
skills/specialists/copywriter-voice-guidedevops-ci-cd-pipeline
Designs a CI/CD workflow — build/test/deploy stages, artifact promotion between envs, manual/auto gates, rollback hooks. Output: pipeline YAML (GitHub Actions / GitLab / CircleCI / Buildkite) plus a gate matrix showing which env needs which approval. Pulled by the `devops` speci...
skills/specialists/devops-ci-cd-pipelinedevops-incident-runbook
Writes a concrete on-call runbook for a specific failure mode — symptoms, diagnose steps, mitigate, rollback, and postmortem link. Output: markdown runbook keyed off the alert name. Pulled by the `devops` specialist.
skills/specialists/devops-incident-runbookdevops-infrastructure-as-code
Authors Terraform / Pulumi / CDK for a cloud component — compute, networking, storage, IAM — with state backend, drift detection, and module boundaries. Output: IaC source files plus backend/state configuration and a module-tree note. Pulled by the `devops` specialist.
skills/specialists/devops-infrastructure-as-codedevops-observability-setup
Wires metrics, logs, traces, SLO dashboards, and alerts for a service. Output: dashboard-as-code (Grafana / Datadog / CloudWatch JSON), alert rules, and the SLO → alert mapping. Pulled by the `devops` specialist.
skills/specialists/devops-observability-setupmarketing-ab-copy-variants
Authors A/B (or multivariate) copy variants with a testable hypothesis, a single changed variable, a control, sample-size math, and a pre-registered success metric. Pulled by the `marketing` specialist.
skills/specialists/marketing-ab-copy-variantsmarketing-campaign-brief
Writes a campaign brief that commissions downstream work from copywriter, social-media, and seo — tight goal, audience, message, channels, assets-needed, deadlines, and success criteria. Pulled by the `marketing` specialist.
skills/specialists/marketing-campaign-briefmarketing-launch-plan
Plans a product or feature launch across channels with a pre-registered metric stack, asset list, timeline (pre-launch, launch day, sustain), and per-channel owners. Pulled by the `marketing` specialist.
skills/specialists/marketing-launch-planmarketing-positioning
Authors a positioning statement — ICP, category frame, unique value, competitive alternatives, and a sharp "not-for" list. Pulled by the `marketing` specialist.
skills/specialists/marketing-positioningmobile-android-kotlin
Authors idiomatic Kotlin for Android (Jetpack Compose or View system, chosen by fit), with structured coroutines, Flow / StateFlow, and leak-safe context handling. Output: Kotlin source plus Gradle / manifest notes. Pulled by the `mobile` specialist.
skills/specialists/mobile-android-kotlinmobile-ios-swift
Authors idiomatic Swift for iOS (SwiftUI or UIKit, chosen by target version and fit), with Swift Concurrency, proper main-actor isolation, and no force-unwraps. Output: Swift source files plus a build-notes section for SPM / Xcode integration. Pulled by the `mobile` specialist.
skills/specialists/mobile-ios-swiftmobile-performance-tuning
Profiles and optimizes mobile apps — startup, scroll jank, memory, battery — with before/after metrics on real devices. Output: instrument plan, baseline, fix list, post-fix metrics. Pulled by the `mobile` specialist.
skills/specialists/mobile-performance-tuningmobile-react-native
Authors React Native / Expo components with platform-aware behavior, minimal JS-bridge traffic, and native-module notes where required. Output: TypeScript source for the component plus notes on any native modules / platform code. Pulled by the `mobile` specialist.
skills/specialists/mobile-react-nativeqa-flaky-test-hunter
Diagnoses flaky tests — classifies the cause (timing / ordering / resource / external), quarantines the test safely, and lays out a fix plan. Output: per-test flakiness report, quarantine list, and remediation plan. Pulled by the `qa` specialist.
skills/specialists/qa-flaky-test-hunterqa-property-based-tests
Authors property-based tests (Hypothesis / fast-check / proptest / QuickCheck) for a target function or module — invariants, generators, shrink strategies. Output: a property-test module plus generator definitions. Pulled by the `qa` specialist.
skills/specialists/qa-property-based-testsqa-snapshot-tests
Authors snapshot tests with governance — what to snapshot, granularity, update-review policy, and rot prevention. Output: a snapshot test suite plus a short update-review policy doc. Pulled by the `qa` specialist.
skills/specialists/qa-snapshot-testsqa-test-strategy
Picks the test shapes (unit / integration / e2e / contract) for a feature, sets coverage targets per layer, and captures the matrix. Output: `test-strategy.md` plus a coverage-target matrix that downstream test writers implement. Pulled by the `qa` specialist.
skills/specialists/qa-test-strategyresearcher-comparison-table
Produces an N-option comparison table — libraries, vendors, frameworks, models — with named axes, cell rationale, and takeaways. Output: markdown table + 3–5 bullet takeaways + source list. Pulled by the `researcher` specialist.
skills/specialists/researcher-comparison-tableresearcher-deep-dive
Produces a structured research brief on a topic — key findings, sources, confidence-per-claim, open questions. Output: `.guild/runs/<run-id>/research/<slug>.md`. Pulled by the `researcher` specialist.
skills/specialists/researcher-deep-diveresearcher-paper-digest
Summarizes a single academic paper or long-form article with a critical read — Problem / Approach / Results / Limitations / Relevance. Output: `.guild/runs/<run-id>/research/digests/<slug>.md`. Pulled by the `researcher` specialist.
skills/specialists/researcher-paper-digestsales-cold-outreach
Writes cold outbound sequences (email + LinkedIn) targeted to a named ICP, with per-step copy, cadence, triggers, and a stated value hypothesis per touch. Pulled by the `sales` specialist.
skills/specialists/sales-cold-outreachsales-discovery-framework
Designs a discovery-call framework — stage-gated question sets, qualification scoring, disqualification criteria, and next-step decision rules. Pulled by the `sales` specialist.
skills/specialists/sales-discovery-frameworksales-follow-up-sequence
Writes post-meeting and post-proposal follow-up cadences — triggered touches with per-step copy, value-add hooks, disposition rules, and a clean exit path. Pulled by the `sales` specialist.
skills/specialists/sales-follow-up-sequencesales-proposal-writer
Writes sales proposals — scope, deliverables, pricing, terms, assumptions, decision criteria, and clear next steps. Pulled by the `sales` specialist.
skills/specialists/sales-proposal-writersecurity-auth-flow-review
Reviews an authentication / authorization flow (OAuth2 / OIDC / session / token / SAML) — threat-maps the flow, finds weaknesses, lists fixes. Output: `auth-review.md` with step-by-step flow, threat map, and remediation. Pulled by the `security` specialist.
skills/specialists/security-auth-flow-reviewsecurity-dependency-audit
Audits dependencies for CVEs, license risk, and transitive exposure; writes a remediation plan with ownership. Output: audit report (per package: CVE / license / fix status) plus a patch plan. Pulled by the `security` specialist.
skills/specialists/security-dependency-auditsecurity-secrets-scan
Scans repo and build artifacts for leaked secrets (keys, tokens, certs) and proposes a prevention policy — pre-commit hooks, CI check, rotation plan. Output: findings report, remediation steps (rotate / revoke / invalidate), and hook/CI proposals. Pulled by the `security` specia...
skills/specialists/security-secrets-scansecurity-threat-modeling
Runs a STRIDE-style threat model on a component — assets, entry points, trust boundaries, threats, mitigations — with each threat anchored to an owner and a ticket. Output: `threat-model.md` with the full asset / boundary / threat table. Pulled by the `security` specialist.
skills/specialists/security-threat-modelingseo-internal-linking
Plans an internal-link structure — link graph across pillars/clusters, anchor-text variance, orphan-page fixes, sitewide nav vs in-content links, link-equity flow. Output: link graph + recommendations. Pulled by the `seo` specialist.
skills/specialists/seo-internal-linkingseo-keyword-research
Identifies target keywords with search intent, volume, difficulty, and SERP feature notes; clusters them into topics; produces a content gap analysis against current pages. Pulled by the `seo` specialist.
skills/specialists/seo-keyword-researchseo-on-page-optimization
Optimizes a specific page — title tag, meta description, H1/H2 hierarchy, URL slug, schema.org markup, internal links, image alt text, content depth against SERP intent. Output: before/after diff + checklist. Pulled by the `seo` specialist.
skills/specialists/seo-on-page-optimizationseo-technical-audit
Audits technical SEO health — crawlability, robots/sitemaps, indexation, canonicals, redirects, Core Web Vitals (mobile first), hreflang, HTTPS, JS rendering. Output: severity-tagged findings with owner assignment. Pulled by the `seo` specialist.
skills/specialists/seo-technical-auditsocial-media-content-calendar
Builds a content calendar across platforms — dated entries with platform, topic, format, owner, status, cross-pollination notes, and weekly themes. Output: calendar.md or YAML. Pulled by the `social-media` specialist.
skills/specialists/social-media-content-calendarsocial-media-engagement-templates
Builds a reusable reply / DM / comment template library for community management — tagged by use-case (welcome, feature request, complaint, praise, press inquiry, outage), with personalization slots and escalation rules. Pulled by the `social-media` specialist.
skills/specialists/social-media-engagement-templatessocial-media-platform-post
Writes a single platform-native post — Twitter/X, LinkedIn, Instagram, Threads, Bluesky — with post copy matched to platform norms, a media plan (image/video spec), and hashtag set. Pulled by the `social-media` specialist.
skills/specialists/social-media-platform-postsocial-media-thread
Writes a multi-post thread or carousel — Twitter/X threads, LinkedIn carousels, Threads chains, Instagram carousels — with thread outline, a hook that earns the click, per-post copy, and a closing CTA. Pulled by the `social-media` specialist.
skills/specialists/social-media-threadtechnical-writer-api-docs
Documents an existing API contract — reference pages per endpoint, example requests/responses, error table, auth section, pagination rules, versioning notes. Reads the source spec (OpenAPI/SDL/code); never invents endpoints. Pulled by the `technical-writer` specialist.
skills/specialists/technical-writer-api-docstechnical-writer-release-notes
Authors release notes / changelog entries for a version — grouped as Added / Changed / Fixed / Deprecated / Removed / Security, with breaking-change callouts and upgrade notes. Pulled by the `technical-writer` specialist.
skills/specialists/technical-writer-release-notestechnical-writer-tutorial
Writes a walk-through tutorial — getting-started, first-project, end-to-end integration — with numbered steps, expected output per step, and a troubleshooting section. Pulled by the `technical-writer` specialist.
skills/specialists/technical-writer-tutorialtechnical-writer-user-manual
Writes user-facing product documentation — task-based pages organized around what a user is trying to do, with steps, screenshots, caveats, and a glossary. Pulled by the `technical-writer` specialist.
skills/specialists/technical-writer-user-manual