All authors
Claude Skills by desplega-ai
github.com/desplega-ai69 skills0 installs33 views
- Swarm Local E2eGuide for running local E2E tests with API server, Docker lead/worker containers, task creation, log verification, UI dashboard, and cleanupVotes: 0GitHub stars: 844
- Close IssueClose a GitHub or GitLab issue with a summary commentVotes: 0GitHub stars: 844
- Create PrCreate a pull request (GitHub) or merge request (GitLab) from the current branchVotes: 0GitHub stars: 844
- Implement IssueImplement a GitHub issue or GitLab issue and create a PR/MRVotes: 0GitHub stars: 844
- Investigate Sentry IssueInvestigate and triage a Sentry error issueVotes: 0GitHub stars: 844
- Respond GithubRespond to a GitHub issue/PR or GitLab issue/MRVotes: 0GitHub stars: 844
- Review Offered TaskTurn prompt for an offered swarm task: read the offer, accept with task-action and start work-on-task, or reject with a reason.Votes: 0GitHub stars: 844
- Review PrReview a pull request (GitHub) or merge request (GitLab) and provide detailed feedbackVotes: 0GitHub stars: 844
- Start LeaderStart the Agent Swarm LeaderVotes: 0GitHub stars: 844
- Start WorkerStart an Agent Swarm WorkerVotes: 0GitHub stars: 844
- Swarm ChatEffective communication within the agent swarm using internal SlackVotes: 0GitHub stars: 844
- TodosHandle the agent personal todos.md fileVotes: 0GitHub stars: 844
- User ManagementHow to manage the user registry — creating users for new Slack/GitHub/GitLab/Linear identities, managing aliases, resolving users across platforms. Use when a new human interacts with the swarm or when user identity needs updating.Votes: 0GitHub stars: 844
- Work On TaskTurn prompt for an assigned swarm task: find the task, gather context when the message lacks it, use the skill the task names, finish with one of the four endings.Votes: 0GitHub stars: 844
- Agentmail SendingCanonical 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.Votes: 0GitHub stars: 844
- Kapso WhatsappHow 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,...Votes: 0GitHub stars: 844
- Attio InteractionGeneric Attio CRM REST API v2 recipes for querying records, upserting companies/people/deals, writing notes/tasks/comments, managing lists, and handling webhooks.Votes: 0GitHub stars: 844
- ComposioUse 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-goo...Votes: 0GitHub stars: 844
- Scheduled Task ResilienceGuardrails 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.Votes: 0GitHub stars: 844
- Swarm ScriptsBulk, repeat, fan-out, or data-heavy work: write and run swarm scripts (inline `script-run`, named `script-upsert`, durable `launch-script-run`). Covers the script-vs-tool rubric, the authoring contract (`args` first, `ctx` second), the seed catalog, connections and secrets, `db_query`, and exposing a script as an API.Votes: 0GitHub stars: 844
- Assets`operator-skill.png` is an unedited browser capture of GitHub's rendered operator skill, taken on 2026-09-15 at a 1440 × 1080 viewport with agent-browser. Source: [skills/agent-swarm/SKILL.md at 038a4144](https://github.com/desplega-ai/agent-swarm/blob/038a41446186f9f5ab7d6d83a711600dcd3435df/skills/agent-swarm/SKILL.md). It shows the real installation checklist. It does not depict a running deployment or an agent completing the checklist.Votes: 0GitHub stars: 844
- Agent SwarmInstall, self-host, deploy, operate, or use agent-swarm. Covers Docker Compose, Kubernetes, configuration, coding agents, the admin UI, integrations, and connections.Votes: 0GitHub stars: 844
- Agent BrowserDrive a real browser with the agent-browser CLI (headless Chromium over CDP). Use for any browser task: verifying a UI change, taking a screenshot, walking a web page, filling a form, extracting page text, reproducing a frontend bug, or attaching UI evidence to a PR, issue, Linear comment, or Slack thread. Starts with a `command -v agent-browser` check and falls back to manual QA on the slim worker image. Screenshots are shared through agent-fs signed URLs. This is the only browser automation...Votes: 0GitHub stars: 844
- Serply SearchQuery real Google results through Serply, with separate endpoints for news (dated coverage) and scholar (citation counts). Use when the ranking itself, the publication date, or the citation count is the answer.Votes: 0GitHub stars: 844
- Plans YoloImplement PR 1 from the README brainstorm. Publish one discoverable operator skill, simplify the README, and guard its distribution in CI. The landing repository remains a later PR.Votes: 0GitHub stars: 844
- Dashboard UiUse when building or changing UI in apps/ui, the agent-swarm dashboard. Covers pages, components, forms, settings pages, onboarding-style multi-step flows, empty states, motion and animation, keyboard shortcuts, autosave fields, secret inputs, segmented controls, status icons, brand logos, and UI verification with agent-browser. Adds the rules that apps/ui/CLAUDE.md and apps/ui/DESIGN.md do not cover.Votes: 0GitHub stars: 844
- Task Digest GuideRead the task-digest extension's output. Use when someone asks how many tasks completed or failed recently, or which agents did them.Votes: 0GitHub stars: 844
- Ask UserConventions for asking the user questions during a workflow via the AskUserQuestion tool. Other skills reference this to keep prompts consistent and structured.Votes: 0GitHub stars: 36
- BrainstormingInteractive exploration of ideas through Socratic Q&A. Produces progressive documents that serve as lightweight pre-PRDs feeding into research.Votes: 0GitHub stars: 36
- Code ReviewingTwo-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 DOCUME...Votes: 0GitHub stars: 36
- CommsRe-express something so it lands — re-explain your last reply in plain casual language, show the current topic visually (diagram, code-shape sketch, HTML artifact), do both at once, or rewrite artifact text into unambiguous ASD-STE100 English. Use when the user runs /desplega:comms, types /bro, says 'say it simpler', 'bro what', 'I don't follow', 'show me', 'draw this', 'visualize', 'disambiguate this', or 'STE100 rewrite'. Not for creative or marketing copy.Votes: 0GitHub stars: 36
- Delegate WorkExecutor 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...Votes: 0GitHub stars: 36
- Design DocsCreate 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.Votes: 0GitHub stars: 36
- Engineering StandardsCode-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).Votes: 0GitHub stars: 36
- ImplementingPlan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.Votes: 0GitHub stars: 36
- Improve Agents MdImprove (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 th...Votes: 0GitHub stars: 36
- LearningCompounding knowledge across projects and teams. Captures, searches, and promotes institutional learnings via tiered backends (local/qmd/agent-fs).Votes: 0GitHub stars: 36
- One ShotSmall-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.Votes: 0GitHub stars: 36
- Phase RunningExecute individual plan phases as background sub-agents for context-efficient implementation.Votes: 0GitHub stars: 36
- PlanningImplementation planning skill. Creates detailed technical plans through interactive research and iteration.Votes: 0GitHub stars: 36
- QaFunctional validation skill. Captures test evidence (screenshots, recordings, links) and produces QA reports in thoughts/*/qa/.Votes: 0GitHub stars: 36
- QuestioningOne-shot question answering using the research process. Answers inline without generating documents, then offers handoff to brainstorm or research.Votes: 0GitHub stars: 36
- ResearchingComprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.Votes: 0GitHub stars: 36
- ReviewingStructured critique of research, plan, and brainstorm documents for completeness, gaps, and quality.Votes: 0GitHub stars: 36
- Script BuilderGenerate 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+ sim...Votes: 0GitHub stars: 36
- Step RunningExecute 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.Votes: 0GitHub stars: 36
- Tackle Gh CommentsWork 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.Votes: 0GitHub stars: 36
- Tdd PlanningTDD-focused implementation planning. Creates plans with strict Red-Green-Commit/Rollback cycles for each step.Votes: 0GitHub stars: 36
- V ImplementingParallel 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.Votes: 0GitHub stars: 36
- V PlanningVertical / 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 sequent...Votes: 0GitHub stars: 36