Productivity

>- Put Amazon Bedrock AgentCore infrastructure behind a plan-only CI gate. Generates a GitHub Actions workflow that, on pull requests touching the infrastructure, runs the static AgentCore review (`ACR0xx`), `terraform fmt -check`, `init`, `validate`, a saved `plan` (Terraform or Terragrunt) with a read-only OIDC role, `show -json`, and the plan policy (`CI0xx`: no delete or replace of memories, gateways, credential providers, workload identities, user pools or tables without an explicit per-address allowance; no `*` on `*`; no gateway with `authorizer_type = NONE`; pinned MCP revisions), then uploads the plan JSON. Nothing in it applies. The plugin's stdlib-only library is vendored into `ci/agentcore/` so the job needs nothing from the plugin, and action pins are reused from the repository's own SHA-pinned workflows. `policy_check.py` also runs locally on any saved plan. Use when asked to "add CI for the AgentCore Terraform", "gate the plan", "block destructive changes", "policy check the plan", "plan on ...

Stand up and run a LinkedIn employee advocacy program for a marketing or sales team. Covers 14-day launch playbook, brand-guideline governance, per-post time budget, cadence benchmarks, and team ROI (reach, engagement, pipeline). Triggers on \"employee advocacy\", \"get the team posting\", \"scale LinkedIn across team\", \"advocacy ROI\". Not for planning one person's own calendar (use linkedin-content-planner).

>- SOLID C++ / ESP32 firmware guardrails: file/class size, no nested classes, strict DI at composition roots, no UNIT_TEST / test ifdefs in production headers (and avoid them in .cpp), no hardcoded secrets, one type per public header, public API /// comments, dual-core radio pinning (PRO_CPU 0 / APP_CPU 1), FreeRTOS-safe patterns. Use when editing ESP-IDF, Arduino-ESP32, PlatformIO firmware, or ESP-NOW / BLE / Wi-Fi tasks.

Reverse engineer a competitor's full online marketing (positioning, traffic, SEO, AI visibility, ads, funnel, tech stack, email, social, PR) and deliver a prioritised action plan.

Resume qué tengo por delante leyendo mi sistema y, si están conectados, mi calendario y mi correo. Úsala cuando el usuario diga "/brief", "qué tengo hoy", "qué tengo pendiente", "por dónde voy", "en qué estaba", "arma mi día" o al empezar una sesión de trabajo.

Audit a Salesforce org read-only, turn the findings into a reviewed, prioritized task list, and create the tasks in ClickUp or GitHub through MCP. Asks before it acts, and never creates a task the person has not approved.

Transforms a meeting transcript into auditable minutes: decisions and action items with provenance, presumed agreements for asynchronous confirmation, action items in JSON, and discovery input.

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies, getSession, getUser, getClaims, RLS); Supabase CLI or MCP server; schema changes, migrations, declarative schemas, security audits, Postgres extensions (pg_graphql, pg_cron, pg_vector); debugging and troubleshooting errors or unexpected behavior on Supabase projects (HTTP errors, Postgres errors, RLS surprises, permission denied, schema cache issues, timeouts, Edge Function crashes, Realtime drops, Storage failures) and reading or querying logs (Logs Explorer, ClickHouse).

Manage a project's agent skills across four modes — T0 start-up inventory (read-only), T1 gap-driven single install mid-task, T2 batch install after the plan is settled, and a library audit mode (duplicates, conflicts, bloat, dead references). Local-first. Use when the user says "初始化项目技能/管理项目技能", "给这个项目配技能/装技能", "审计技能库", "audit skills", or a task hits a durable capability gap. NOT for authoring skills (use skill-creator) or one-off answer lookups (search docs or `npx skills find` instead, install nothing).

Guide production application development across web, mobile, and backend systems. Use when implementing or auditing production workflows; route to the applicable domain and supporting guidance.

Audit whether a benchmark grader measures the intended behavior rather than superficial labels or leaked answers. Use before freezing evaluations, accepting model comparisons, or interpreting task-success claims.

Preserve productive progress in an authorized multi-task autonomous session when a workstream is blocked by approval, dependency, tooling, or environment failure. Classify blocker scope, checkpoint evidence, switch only to independently authorized tasks, and stop for global safety issues or when no safe work remains.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks. Also use when the user says "openspec apply", "opsx apply", or "openspec implement".

Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete. Also use when the user says "openspec archive" or "opsx archive".

>- Use when executing any user request in Claude Code where the core task must be completed without unnecessary commentary, preambles, or "enrolando atoa". Triggers: user expects direct execution, requests clarification before any speculation, or wants minimal post-task explanation only when explicitly asked.

Cut a release on GitHub: update the changelog, bump the version (preferring the repo's own release task or script over a manual edit), tag, push, then watch the release workflow until the GitHub Release exists. Use when asked to 'cut a release', 'release version X', 'ship a new version', 'bump the version and tag', 'publish a release', or '/gh-release'. For repos where a tag push triggers a GitHub Actions workflow that creates the release.

Replace this with what the skill does and when to use it, using the words a user would actually type. Mention the task, the artifacts, and the triggers.

>- Pre-flight checklist before letting an automated agent send outbound email, post publicly, or run scheduled outreach crons. Use when enabling any cron that sends messages, restarting outreach automation, or handing an agent a sender identity - prevents the classic spam-trap, wrong-identity, and runaway-cron failures.

Full client for the Motion (usemotion.com) REST API — all 27 documented endpoints across tasks, projects, recurring tasks, comments, custom fields, users, workspaces, statuses and schedules, plus a raw escape hatch (with cursor pagination) for anything undocumented. Handles X-API-Key auth, cursor pagination, rate-limit backoff, and gates every delete behind an explicit confirmation flag.

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks. Also use when the user says "openspec apply", "opsx apply", or "openspec implement".

Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete. Also use when the user says "openspec archive" or "opsx archive".

Retrieve version-aware library documentation with Context7 and configure its CLI or MCP when requested. Use for ctx7 or Context7 tasks; general skill installation belongs to the available skill installer.

Maintain CodexMonitor and Codex app-server protocol parity. Use when asked to audit supported or missing app-server notifications/requests, trace event routing, diagnose schema drift in app-server payloads, or update docs/app-server-events.md after upstream Codex changes.

Reusable structural + citation check for workflow artifacts. Use after each artifact group finishes and before the next group starts, and whenever quality gate G8 (artifact structure) is evaluated. Reports PASS/FAIL per check with findings and the responsible agent.