Categories › AI & Agents › Multi-agent, orchestration & workflows
Search and load free AI skills, workflows, agents and prompts. Read-only, no sign-in.
Remote server: your requests and data go to useaiblocks.com. Claude Code: claude mcp add --transport http ai-blocks https://useaiblocks.com/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
start_outcome — For a goal or problem with no deliverable named yet, in the owner's own words ("more customers", "my ad costs are rising"). For a named piecadvance_outcome — For an engagement from start_outcome only; a team job from start_job moves with advance_job. Apply one event to an engagement. This server krecord_outcome_decision — Record what the owner chose, the options considered (best-ranked first), what they passed over and why. Passing over the top option needs a record_outcome_experiment — Register a test before it goes live (action register: change, metric, baseline, window, minimum volume, guardrails), then close it (action cread_back_outcome_experiment — Use while an experiment from record_outcome_experiment is live (that tool registers and closes it). Without a reading: the read-back schedulprepare_outcome_pattern — After a finished round, returns the exact anonymised PATTERN.json the owner would share (names, figures, links and contact details removed) prepare_job_context — The first call for any named piece of work: a page, ad, email, copy, audit, analysis, plan or code. Then start_job. A goal with no deliverabstart_job — Use after prepare_job_context (send from_context: true so the brief is not repeated); not for a goal with no deliverable (start_outcome). Deadvance_job — For a team job from start_job only; an engagement from start_outcome moves with advance_outcome. Send the latest complete state and state_diget_approaches — Use to compare the different ways a job can be done before choosing one: source-backed approach families, methods, lenses and needed tools. get_job_templates — For team jobs: JOB-METHOD.md (the short team method), JOB-RECORDS.md (every record field; open it only when advance_job refuses a record) anget_job_preferences — On this anonymous service, return recommended choices and a local-file template. Signed-in connections use the scoped private preference recset_job_preferences — Anonymous calls only prepare local preference files; they save nothing on the server. Signed-in connections require the selected workspace wfind_specialist — Find worker candidates for a deliverable. Compare their remit and outputs, then use prepare_specialist to onboard the chosen worker. Keep unprepare_specialist — Supply role_id only to load a complete base specialist: README, setup, SOUL, intake, playbook, handoff and best-practice files, pinned methosearch_library — Use to browse or look up catalogue items by keywords, job or date. Not for doing a piece of work (prepare_job_context) or a business goal (splan_workflow — Use when a multi-step job has no steps chosen yet: it finds candidate steps. Once you have step ids, in order, use prepare_workflow to checkget_resource — Use after get_item to read one file from its file list (a script, template or reference), at that exact skill revision. Text returns boundedprepare_workflow — Use when you already have the step ids, in order, and the user wants to see, check or change a workflow (swap, add, remove or reorder steps)get_item — The one tool to read an item: any kind, by the id from a search_library or plan_workflow row (skill, workflow, agent, prompt, mind, AI tool search — Only for ChatGPT deep research and company knowledge, which need this exact shape: results with id, title and url. Read one with fetch. Everfetch — Only for ChatGPT deep research and company knowledge: read one item by the id from search (such as skill/ad-angle-planner). Every other clieNot tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.