# Click AI — portable skills for AI agents > Self-contained playbooks any AI agent can read. Each skill is a SKILL.md plus the > templates and scripts it needs. Source: https://github.com/timharris707/skills (MIT). 12 skills in 5 regions. ## Install ``` /plugin marketplace add timharris707/skills /plugin install advisory-board@skills /plugin install team-workflow@skills /plugin install writing-for-agents@skills ``` ## Orient Bind the discipline to a repo, and find your way around it. - [router](https://clickai.dev/skills/router.md): Entry point for the team-workflow pack — names every pack skill and when to reach for it. Use when unsure which team-workflow skill applies, or to orient a new session/repo on what the pack offers. - [setup](https://clickai.dev/skills/setup.md): Once-per-repo binding interview for the team-workflow pack — scan the repo, confirm the mandatory bindings (tracker, verify commands, decider, binding-doc home), seed the anchor binding doc, templates, and the session-start handoff hook, and refresh idempotently on re-run. Use when installing the pack into a repo or updating an existing installation. ## Decide Settle what is still open before anyone writes a line of it. - [grilling](https://clickai.dev/skills/grilling.md): Interview the decider relentlessly to turn a half-formed plan, design, or idea into shared understanding — a design tree worked in rounds until nothing is silently assumed. Use when asked to grill, stress-test, or pressure-test thinking, and before charting a decision map or writing a spec off a conversation nobody has pressure-tested. - [decision-map](https://clickai.dev/skills/decision-map.md): Chart or work a decision map for genuinely foggy work — a new primitive, a milestone charter, an integration nobody can spec in one sitting — before any build slice is written. Use when asked to chart a decision map, work a map ticket, or plan a decision-heavy effort whose open questions gate each other. - [advisory-board](https://clickai.dev/skills/advisory-board.md): Convene a multi-model advisory board (a round table) where subscription-backed Claude, Codex, Gemini, and Grok CLIs each review the same material independently, debate across rounds by reading one another's findings, and converge on a single working handoff. Use when the user asks for an advisory board, round table, or panel; a multi-model or multi-provider review; a skilled debate among models; an adversarial review of a plan, design, architecture, document, decision, or strategy; an Anthropic/OpenAI/Google/xAI cross-check; or a consensus handoff from several frontier models. ## Investigate Answer what discussion cannot — from sources, or from running code. - [research](https://clickai.dev/skills/research.md): Run an autonomous research lane against primary sources, ending in a cited findings file linked from the driving ticket — and, when the missing facts are human-held, a questionnaire. Use for investigations of vendor materials, regulations, upstream repos, recorded calls, or any fact-finding that should run fire-and-report. - [prototype](https://clickai.dev/skills/prototype.md): Build throwaway prototype code that answers a design question — UI variants on a live route, or a terminal UI over a pure logic module. Use when a question is "how should this look / behave / feel in action" and discussion or static artifacts cannot settle it. ## Run Get decided work onto the board, through the lanes, and handed on. - [to-tickets](https://clickai.dev/skills/to-tickets.md): Turn a plan, a spec, a closed decision map, or a pressure-tested conversation into tracer-bullet work items on the repo's tracker, each an issue-as-spec with its blocking edges wired. Use when asked to file tickets, break work down, or move from "we've decided" to "it's on the board". - [wizard](https://clickai.dev/skills/wizard.md): Generate an interactive bash wizard that walks a human through a procedure only they can perform — third-party dashboards, credentials, DNS records, CI secrets, one-off cutovers. Use when a task stalls on steps an agent cannot take, or when a manual setup is tedious to re-explain every time. Not for steps the agent can perform itself. - [orchestrate](https://clickai.dev/skills/orchestrate.md): Run a session as the orchestrator of parallel agent-assisted work — routing items to working sessions, auditing results, and owning integration, instead of implementing. Use when the user says "orchestration mode", asks one session to coordinate several lanes/sessions, or hands over an orchestrator role. - [handoff](https://clickai.dev/skills/handoff.md): Write a structured session handoff so a fresh session resumes losslessly. Use when context is filling up (around half the window), when wrapping a work session, or when the user says "handoff", "checkpoint", "wrap up", or "save state". ## Author The standard the rest of this catalog is written against. - [writing-for-agents](https://clickai.dev/skills/writing-for-agents.md): Write and prune documents an agent consumes — a SKILL.md, an AGENTS.md or CLAUDE.md, a reference file reached by a pointer. Use when authoring or revising a skill, editing standing agent instructions, or diagnosing why a document fires unreliably or gets skimmed. ## Formats - Append `.md` to any skill URL for its full SKILL.md. - https://clickai.dev/skills — the catalog. - https://clickai.dev/sitemap.xml — every page.