Skills in this repository
SkillsMP has collected 752 skills from Agents-Store/codex-plugins. Open a skill to review its source and details.
Agents-Store/codex-pluginsShowing 40 of 752 collected skills.
Diagnose schema-side NocoDB errors — read-only fields, type-change rejections, broken Lookups, formula errors, view config validation, version mismatches. Use when: - "field type change rejected" - "Lookup not working" - "formula returns ERR" - "cannot delete…
Create, configure, and delete NocoDB views — Grid, Form, Gallery, Kanban, Calendar, Map, Gantt, Timeline, List. Use when: - "create a kanban view" - "add a calendar / gantt / timeline view" - "build a form for intake" - "make a gallery of products" - "set up…
Configure NocoDB webhooks (HookV3) on a table — insert, update and delete triggers, field scoping, and notification targets URL, Email, Slack, Discord, Telegram, Whatsapp, Twilio or Script, plus listing, updating, testing and deleting hooks. Use when a NocoDB…
List, execute, and inspect NocoDB Workflows (the platform's built-in automation engine) via Meta API v3; author drafts over MCP on Cloud/licensed. Use when: - "list NocoDB workflows" - "execute a workflow" - "view workflow execution" - "trigger workflow on…
Build an aggregation report from NocoDB table data Arguments: <table-name> [aggregation-type] [field].
Create a new record in a NocoDB table Arguments: <table-name> <field=value pairs>.
NocoDB workflow examples, scenario walkthroughs, and practical patterns. Use when: - "show me a NocoDB example" - "workflow examples" - "scenario walkthroughs" - "how do I use NocoDB for..." - "NocoDB use case"
Import data into NocoDB tables and export records out. Use when: - "import CSV into NocoDB" - "load data into this table" - "bulk create records" - "export records to CSV" - "migrate data between tables" - "import JSON data" - "extract all records" -…
List records from a NocoDB table with optional filtering Arguments: <table-name> [where-filter].
NocoDB MCP tools reference for data work -- which tools the server lists, which sit behind listTools/callTool, the Community vs Cloud/licensed contract, and the exact parameter shapes (100-record batches, sort objects, filter vs where, date sub-operators).…
Create, read, update and delete records in NocoDB tables — single and bulk creates, finding a record and changing it, counting records that match a condition, deduplicating and restoring deleted records. Use when working with the data inside a NocoDB table.…
NocoDB filter syntax for searching, filtering and sorting records — the where clause and structured filter, text, numeric, date and multi-select operators, relative date ranges, AND/OR groups, null and empty checks, and sort objects. Use when writing or…
Search records in a NocoDB table by keyword Arguments: <table-name> <query>.
Verify NocoDB connection and MCP setup. Use when: - "check my NocoDB connection" - "verify MCP is working" - "test NocoDB setup" - "is NocoDB connected?" - "troubleshoot NocoDB access"
Diagnose and fix NocoDB errors, connection issues, and MCP problems. Use when: - "NocoDB not working" - "connection error" - "getting 401 error" - "MCP tool not responding" - "debug NocoDB" - "filter not working" - "timeout error"
Build reports, summaries, and dashboards from NocoDB data. Use when: - "create a report" - "summarize this table" - "show sales by region" - "build a dashboard" - "aggregate data" - "what views exist on this table?" - "kanban board" - "monthly summary" -…
Use NocoDB webhooks from the business side — which events exist, how to set one up in the UI, what the receiving system gets (payload), conditions, the Button trigger, and testing. Use when: - "trigger something when a record changes" - "send NocoDB data to…
Guide for creating and customizing AGENTS.md — the operating rules, procedures, and behavioral guardrails for an OpenClaw agent. Use this skill whenever the user is working on agent behavior, operating procedures, session startup sequences, memory management…
Full fleet audit in an isolated agent — one prioritised report with a ready repair line under every finding Arguments: [selector] [--focus auth|versions|memory|cron|secrets|security|shared|all].
Guide for BOOTSTRAP.md (first-run setup ritual) and BOOT.md (gateway restart checklist) in OpenClaw. Use this skill whenever the user is setting up a new agent for the first time, configuring onboarding flows, creating first-run discovery processes, or…
Use when an OpenClaw instance config is about to be read, changed, restored, split or explained — a model chain, channel, tool, plugin, skill, session or memory setting, a secret reference, an include, a gateway that refuses to start after an edit, a config…
Use when anything about OpenClaw is about to be stated or recommended that could have changed — a config key, a CLI flag or subcommand spelling, an auth method, a release channel, a current version, a model name, whether a feature exists or is deprecated —…
Use when a whole OpenClaw fleet job is in view rather than a single answer — first contact with an unknown host, a fleet that lost its provider login, an upgrade with an unclear rollback, a new instance to stand up and prove isolated — or when the question is…
Run one openclaw CLI call against selected instances through the single audited door Arguments: <selector> -- <openclaw args…> [--json] [--timeout <s>].
Use when an OpenClaw instance is misbehaving or suspected of it — health green but nothing is happening, a container restarting or unhealthy, an empty or ignored config, models returning unauthorized or reporting logged out, tokens that are present but empty,…
Use when work touches an OpenClaw gateway instance or several of them on one host — inventory, status, health, logs, provider auth, config, secrets, memory, shared skills, upgrades, cloning — or when an instance is named or selected, or when the alternative…
Guide for OpenClaw heartbeats — the periodic background turn that surfaces anything needing attention. Current releases keep heartbeat instructions in the heartbeat monitor's scratch (a database row, managed with `openclaw automations scratch`) and the…
Guide for creating IDENTITY.md — the agent's name, creature type, vibe, emoji, and avatar in OpenClaw. Use this skill whenever the user is naming their agent, choosing an emoji or avatar, setting up the agent's visual identity, or asking how agent identity…
Use when a new OpenClaw instance is to be created from an existing one — cloning the reference, standing up a canary or a throwaway test instance, adding an instance for a new workload or tenant, picking a free gateway port for one, deciding what a new…
Use when an OpenClaw instance or fleet is being upgraded, or when the question is which OpenClaw version to move to — version drift between instances, the current stable release, a release channel or registry dist-tag, an image tag or digest pin, a soak or…
Fan out gateway logs across selected instances, redacted, with per-instance headers Arguments: [selector] [--tail <n>] [--since <dur>] [--grep <re>] [--errors-only].
Use when OpenClaw memory or its embeddings are involved — embedding calls failing authorization or reporting an invalid token, vector search paused or returning nothing useful, an index-identity warning, a last-index timestamp far in the past, search still…
Guide for OpenClaw's memory system — MEMORY.md curation, daily logs, memory flush, and vector search. Use this skill whenever the user asks about how the agent remembers things between sessions, wants to configure memory management, needs to understand daily…
Use when model-provider credentials are in question — unauthorized responses, an instance reporting itself logged out, tokens present but empty, an expiry approaching or passed, several instances losing the same account at once, a login that has to be…
The only repair funnel — dispatch one catalog finding id through its eight-block plan, apply on a later turn, verify Arguments: <selector> --issue <finding-id> [--all-findings] [--yes].
Use when secrets reach an OpenClaw instance through an injection wrapper and something about that is in question — a feature silently off while the config looks right, an instance receiving far fewer keys than its siblings, a plaintext env file inside the…
Use when the security posture of an OpenClaw instance or of the whole fleet is in question — a gateway port that may be reachable from outside the host, firewall rules that read correctly but may not apply to published ports, an operator bearer token that may…
Techniques for analyzing OpenClaw session transcripts (listed through the CLI, exported as a trajectory bundle, then queried with jq) to understand user behavior, tool effectiveness, error patterns, token costs, and active hours. Use this skill whenever the…
Use when skills or plugins are shared across OpenClaw instances on one host — shared trees mounted but empty, the same skill copied into every instance, a shared copy edited with no change in behaviour, an installed asset that never appears in the registered…
Deduplicate skills and plugins across instances, promote the identical ones into the shared trees, register them, remove the local copies that shadow them, and verify on four levels Arguments: [selector] [--adopt-duplicates] [--restart] [--yes].