Browse Templates

Create issues, update status, and post comments in Linear with explicit project placeholders.

linear

tracker

project-management

Requires: LINEAR_PROJECT_ID

Pages

skill

Publish human-readable task outputs as DB-backed shareable pages (HTML or JSON) via `create_page` — no server, no tunnel. Covers auth modes, share URLs, versioning, the injected browser SDK, the `<swarm-diff>` primitive, print/PDF export, limits, and the minimalist taste baseline plus report-density layer every page should follow.

skill

A procedure for improving workflows through small tested revisions.

workflows

authoring

Daily Compounding Reflection

schedule

Capture lessons from the day into memory, skills, and workflow improvements.

memory

skills

operations

Requires: SLACK_CHANNEL_ID, TIMEZONE

Linear Drain Loop

workflow

Break down a Linear parent issue and process ready child issues through workers.

Implementation-focused worker that turns plans into working code, creates PRs, and resolves review feedback fast

linear

triage

Requires: LINEAR_PROJECT_ID, REPO_URL

Coder

worker

official

worker

Content quality gate using LLM-as-judge pattern with a different model than the writer, providing structured scoring and evolving review criteria

worker

Content strategy and analytics specialist that decides what to write, manages the content calendar, and feeds performance data back to the review process

worker

Content creation specialist that generates SEO-optimized blog posts, release notes, how-to guides, and location pages in TSX format with meme generation

Discoverability Optimizer

worker

official

Optimizes web pages for discoverability through SEO, AEO, schema markup, and metadata — structural changes only, no content creation

seo

aeo

schema-markup

metadata-optimization

web-analysis

discoverability

Max tasks: 2v1.0.0

Forward Deployed Engineer

worker

official

Field engineer that handles on-site maintenance, monitoring, debugging, incident response, and operational fixes in production environments

lead

Orchestrator agent that coordinates workers, decomposes tasks, and builds institutional knowledge across sessions

worker

Research-focused worker that analyzes codebases, reviews documentation, and produces structured findings for the swarm

worker

Code review specialist that traces state machines, catches edge cases, and ensures quality before code ships

worker

QA specialist that verifies features through browser automation, runs E2E tests, and catches regressions with evidence-based reporting

worker

Analyzes frontend codebases to extract, maintain, and evolve UX principles. Detects component inconsistencies, accessibility gaps, design token violations, and UX anti-patterns.

skill

Canonical AgentMail send-message API reference for swarm agents. Pins the base URL, required field names, text-only rendering workaround, BCC policy, and ready-to-copy curl / swarm-script examples so agents do not rediscover the API surface at runtime.

communications

Requires: COMPANY_SIGNATURE

Apps

skill

Build and iterate on schema-backed Swarm Apps with live models, named queries, custom actions, and json-render interfaces using the app-upsert, app-get, app-list, and app-patch tools.

skill

Store durable task outputs (reports, screenshots, exports, logs) in agent-fs or the shared workspace, and serve interactive web content to a public auth-protected URL via localtunnel. Use when asked to save evidence for a PR/ticket, share a file, "create an artifact for X", "host this for me", "spin up a web server", or "give me a live link". Covers agent-fs writes and verification, binary uploads, naming and attachment conventions, the `agent-swarm artifact` CLI, Hono apps, PM2 daemonization, HTTP Basic auth, and the injected browser SDK.

skill

Conventions for asking the user questions during a workflow via the AskUserQuestion tool. Other skills reference this to keep prompts consistent and structured.

skill

Use canonical asset namespace keys to group, find, inherit, and move tasks, workflows, schedules, pages, and mapped files. Use when organizing swarm work under shared/ or personal/{userId}/ paths, setting or filtering asset keys, or calling the asset-management API.

skill

Generic Attio CRM REST API v2 recipes for querying records, upserting companies/people/deals, writing notes/tasks/comments, managing lists, and handling webhooks.

attio

crm

sales

Requires: ATTIO_API_KEY

Brainstorming

skill

Interactive exploration of ideas through Socratic Q&A. Produces progressive documents that serve as lightweight pre-PRDs feeding into research.

skill

Run browser automation tasks with bounded polling and explicit artifacts.

browser

automation

Requires: BROWSER_USE_API_KEY

Code Health Scan

skill

Run a multi-language code health scan and publish prioritized findings.

Requires: REPO_URL

skill

Two-axis code review of a diff — Standards (is the code well built?) and Spec (does it actually solve the stated problem?) — run as parallel sub-agents and reported separately, never merged. Use when reviewing implementation output (a phase, a wave, a branch, a PR), when the user says "review the code", "review the diff", "review this phase", or when another desplega skill (implementing, v-implementing, verifying, delegate-work) calls for a per-phase or final code review. For reviewing DOCUMENTS (plans, research, brainstorms), use desplega:reviewing instead.

skill

Use Composio from Agent Swarm through the `agent-swarm x composio` CLI route, the `swarm_x` MCP tool, or a registered `ctx.api.composio` script connection. Trigger when a task needs connected third-party app tools such as Gmail, Google Calendar, Google Docs, Google Drive, GitHub, Slack, Notion, or HubSpot through Tool Router sessions, Connect Links, or connected accounts. This is the HUB skill — for Google apps see the sibling skills `composio-gmail`, `composio-google-calendar`, `composio-google-docs`.

composio

integrations

tools

Requires: COMPOSIO_API_KEY

Composio Gmail

skill

Per-app playbook for driving Gmail through Composio (toolkit slug `gmail`). Verified GMAIL_* tool slugs and argument shapes for reading, searching, sending, drafts, labels, and threads. Use alongside the `composio` hub skill whenever a task reads or sends Gmail for a connected user. Covers the metadata-first reads, the GMAIL_SEND_EMAIL HTML flag, and reply-to-thread.

composio

gmail

Composio Google Calendar

skill

Per-app playbook for driving Google Calendar through Composio (toolkit slug `googlecalendar`). Verified GOOGLECALENDAR_* tool slugs and argument shapes for listing, finding, creating, and updating events plus free/busy. Use alongside the `composio` hub skill. CRITICAL — covers the "events from a year ago" trap: GOOGLECALENDAR_EVENTS_LIST has no default timeMin, so you MUST pass timeMin/orderBy/singleEvents to get upcoming events.

skill

Per-app playbook for driving Google Docs through Composio (toolkit slug `googledocs`). Verified GOOGLEDOCS_* tool slugs and argument shapes for searching, reading plaintext, creating (incl. from markdown), and editing documents. Use alongside the `composio` hub skill whenever a task reads or writes Google Docs for a connected user.

skill

Executor routing policy for ALL delegated work — pick the right model for every sub-agent and the right Codex variant for every implementation slice. Use whenever you are about to spawn a sub-agent/Task (research, review, QA, UI, search), whenever a desplega skill (implement-plan, v-implement, run-phase, run-step, research) is choosing executors for phases/steps, or when the user says "implement with codex", "delegate this", "which model should do this", or similar. Supersedes codex-implement (its worktree/exec mechanics live here).

skill

Create and maintain living per-system design docs at thoughts/*/design-docs/<system-slug>.md — Purpose, Glossary, numbered testable Invariants (normative for the code-reviewing Spec axis), Boundaries & Non-goals, Interfaces, Decision log, Amendment log. Use when the user says "create a design doc", "write down the invariants", "document the design/contract of X", or when researching/planning/one-shot finds a design doc for the touched system and needs the read-and-abide rules.

documentation

architecture

design

Download Task Attachment

skill

Fetch a file attached to your current task in ONE call. Use whenever a task carries an attachment (an image, PDF, or other file the requester uploaded) and you need its bytes on disk — the dispatch prompt lists attachments with a ready-to-run curl command, but if you're improvising (resumed session, follow-up task, or the recipe scrolled out of context) use this skill instead of reaching for the `agent-fs` CLI directly.

attachments

tasks

files

Engineering Standards

skill

Code-shape policy for ALL code that gets written or reviewed — the senior-engineer bar for minimal complexity. Use whenever you are about to write code, design a module or abstraction, draft a plan phase that shapes code, or review a diff; also when the user asks "is this over-engineered", "can this be simpler", or pushes back on complexity. Sibling of desplega:delegate-work (which picks WHO executes; this skill defines WHAT good output looks like).

skill

Use web search APIs for cited research without over-fetching irrelevant pages.

research

web

Requires: EXA_API_KEY

Implementing

skill

Plan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.

skill

Improve (or bootstrap) an AGENTS.md / CLAUDE.md file using `<important if>` conditional blocks so the agent actually attends to the right guidance at the right time. Use this skill whenever the user mentions AGENTS.md, CLAUDE.md, agent instructions, project rules for AI, "my claude config", onboarding docs for agents, or asks to tighten / shorten / audit / rewrite an existing one — even if they don't explicitly say the filename. Also use when the user complains that an agent keeps ignoring their project rules.

skill

Generic Jira update discipline for issue comments, transitions, and triage.

jira

tracker

project-management

Requires: JIRA_PROJECT_KEY

Kapso WhatsApp

skill

How to interact with Kapso WhatsApp from the swarm — read inbound webhook payloads (text AND media), fetch message history, send free-form messages within the 24h session window (and template messages outside it), mark-as-read, show the typing indicator, send reactions, download media, verify webhook signatures, and resolve contacts to swarm users. Canonical reference for ANY Kapso interaction beyond the thin `send-whatsapp-message` / `reply-whatsapp-message` MCP tools — for templates, media, reactions, typing, mark-as-read, signature verify, contact resolution, conversation history, drop to the REST recipes here. Use whenever a task references a WhatsApp message routed through Kapso, or when a workflow needs to reply on WhatsApp.

messaging

communications

Requires: KAPSO_API_KEY, KAPSO_API_BASE_URL, KAPSO_PHONE_NUMBER_ID, KAPSO_WEBHOOK_HMAC_SECRET

KV Storage

skill

Use the swarm KV store (namespaced, Redis-like) for cross-task / cross-session / per-page state. Auto-scoped to your context (Slack thread / PR / Linear issue / agent / page). Use for counters, cursors, dedup and idempotency keys, schedule state, and page state. Do NOT use for secrets (`swarm_config`), embedded knowledge (`memory`), or files (`agent-fs`).

skill

Compounding knowledge across projects and teams. Captures, searches, and promotes institutional learnings via tiered backends (local/qmd/agent-fs).

skill

Small-scope plan+implement in one session. Assess the prompt, optionally one bundled round of questions, maintain a lightweight yolo plan while implementing, verify, quick code review, commit. Use when the user invokes /one-shot, or asks to "just build/fix/add" something small without the full create-plan → implement-plan pipeline. Small means ≤ ~3 phases inside one subsystem — anything bigger escalates to /desplega:create-plan.

skill

Execute individual plan phases as background sub-agents for context-efficient implementation.

skill

Implementation planning skill. Creates detailed technical plans through interactive research and iteration.

planning

implementation

Profile Corruption Escalation

skill

Diagnose and escalate corrupted agent profile, identity, or setup files.

skill

Functional validation skill. Captures test evidence (screenshots, recordings, links) and produces QA reports in thoughts/*/qa/.

skill

One-shot question answering using the research process. Answers inline without generating documents, then offers handoff to brainstorm or research.

skill

Comprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.

skill

Structured critique of research, plan, and brainstorm documents for completeness, gaps, and quality.

review

documents

quality

Scheduled Task Resilience

skill

Guardrails for polling, scheduled jobs, and long-running external operations. Use whenever a task waits on CI, builds, deploys, browser jobs, or another asynchronous API so work survives heartbeat checks without duplicate delivery.

skill

Generate durable, re-runnable scripts from session intent — validation scripts (PASS/FAIL contract) AND gather/bulk scripts (many API/tool calls in code, one derived summary out). Supports TypeScript, Python, Bash with auto-detection, enforces context-optimal output, and auto-documents scripts in CLAUDE.md. Triggers on "turn this into a script", "I want to test/validate X end-to-end", "wrap this in a re-runnable script" — and, critically, whenever you are about to make (or just made) ~10+ similar tool/API calls or any bulk fan-out over a list: that mechanical middle belongs in a script, not in context.

skill

Launch and inspect durable one-off script workflow runs with journaled swarm-script, raw-llm, and agent-task steps.

skill

Use disposable Linux sandboxes for Docker, risky installs, or isolated experiments.

sandbox

docker

isolation

Requires: SPRITES_API_KEY

Step Running

skill

Execute a single DAG step as an autonomous background sub-agent. Sibling of phase-running for DAG plans produced by v-planning. Reads a step-<n>.md file directly, atomically claims it via frontmatter status, runs the three-bucket Success Criteria, and reports back. Spawned by v-implementing or by /run-step.

skill

Use swarm scripts for bulk SDK calls, repetitive fan-out, and context-efficient data processing.

skill

Work through every review comment on a GitHub PR — fetch the threads, verify each claim against the code, fix what is real, then reply and mark each thread resolved before pushing. Use when the user says "tackle the PR comments", "address the review", "handle the bot comments", "check the comments on the PR", "resolve the review threads", or invokes /tackle-gh-comments. Project-agnostic; works in any repo with a GitHub remote.

github

code-review

pull-requests

Taste Minimalist Skill

skill

Editorial minimalist page design guidance from tasteskill.dev: warm monochrome, strong typography, restrained surfaces.

skill

TDD-focused implementation planning. Creates plans with strict Red-Green-Commit/Rollback cycles for each step.

tdd

planning

testing

Turso / LibSQL Interaction

skill

Safely inspect and update LibSQL databases from agent workflows.

database

libsql

turso

Requires: TURSO_DATABASE_URL

V-Implementing

skill

Parallel DAG-plan implementation skill. Reads a v-planning plan directory (root.md + step-<n>.md files), topologically schedules ready steps, and fans them out as parallel sub-agents. Use whenever the user invokes /v-implement, points at a plan directory produced by /v-plan, or asks to "run the parallel plan", "implement the DAG", or "fan out the steps" — even without those exact words. For linear plans (single .md file), use `implementing` instead.

skill

Vertical / parallel implementation planning skill. Creates DAG-structured plan directories where each step is an independent, QA-able vertical slice that sub-agents can pick up and implement in parallel. Use whenever the user wants a plan that fans out (multiple independent features), invokes /v-plan, or asks for a "parallel plan", "DAG plan", "vertical plan", or "plan that can be parallelized" — even if they don't say those exact words. Prefer the linear `planning` skill for strictly sequential work.

skill

Post-implementation plan verification. Cross-references plans against actual changes for completeness and accuracy.

verification

planning

quality

Workflow Structured Output

skill

When task details contain an actual `outputSchema`, complete with a stringified JSON `store-progress.output` that matches it exactly. Also honor an explicit JSON Output Format or interface as a user contract. Workflow origin and deterministic/validation tags are only cues to inspect task details — never invent a schema. Worker-side counterpart to `workflow-iterate`.

skill

Git worktree management expert for @desplega.ai/wts. Use when the user asks about git worktrees, wts commands, worktree workflows, or wants help managing multiple branches simultaneously.

skill

Safely post, reply, or quote through the X API with account placeholders.

Requires: X_HANDLE

schedule

Ask the lead to summarize stuck work, failing checks, and owner decisions every weekday.

operations

slack

digest

Requires: SLACK_CHANNEL_ID, TIMEZONE

Daily Hacker News Briefing

schedule

Demonstrate web research automation by summarizing relevant technology discussion.

research

briefing

browser

Requires: SLACK_CHANNEL_ID, TIMEZONE

Daily Workflow Health Audit

schedule

Check scheduled jobs and workflows for repeated failures, stale runs, and silent drift.

workflows

schedules

reliability

Requires: SLACK_CHANNEL_ID, TIMEZONE

Weekly Code Health Reports

schedule

Gallery entry point for the community Code Maat + D3 code-health report package. Run a weekly report and update a stable page in place.

Requires: REPO_URL, BRANCH, SCOPE_PATH, REPORT_NAME, PAGE_ID, TIMEZONE

Weekly Dependency Triage

schedule

Review dependency update PRs, group safe patches, and flag risky upgrades.

github

dependencies

maintenance

Requires: SLACK_CHANNEL_ID, REPO_URL, TIMEZONE

Weekly DORA Metrics

schedule

Gallery entry point for the community DORA metrics report package. Run a weekly DORA report and update a stable page in place.

dora

metrics

engineering-productivity

reporting

community-template

Requires: REPO_URL, BRANCH, TAG_PATTERN, REPORT_NAME, PAGE_ID, TIMEZONE

Weekly GTM Metrics Review

schedule

Summarize product, marketing, or sales signals into an operator-friendly weekly review.

gtm

metrics

reporting

Requires: SLACK_CHANNEL_ID, TIMEZONE

Autopilot Feature Pipeline

workflow

Research, review, plan, implement, and verify a feature request through staged agents.

Run an implement-review-fix loop until verification passes or a human decision is needed.

implementation

review

Requires: REPO_URL

Iterative Review Loop

workflow

Pattern for release-note workflows that keep full audit context separate from slim prompt context.

review

iteration

Requires: REPO_URL

LLM-Safe Release Context

workflow