ascent
Planning career strategy for job change/side-business/independence. Owns self-analysis, market & salary research, positioning, skill-gap plans, job search…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Agents & models
25,404 results
agent-loadout
Configures persistent pi-subagents model and thinking overrides using three capability tiers or individual roles. Use when the user explicitly invokes…
soia-dev-agent-cli-dispatch
General-purpose external AI model/CLI dispatcher (codex/claude/agy/gemini/kimi/opencode/qwen, not host built-in sub-agents), usable by any host AI for coding, review, analysis, research, documentation, and content tasks: supports explicit model + reasoning depth or automatic selection by difficulty, and outputs…
soia-dev-prompt-clarity
Chinese-English general-purpose prompt skill: A draft from scratch, B diagnose and optimize, C rewrite legitimate requests to prevent false positives, D compile complex requirements into verifiable specifications; supports native English authoring, bilingual delivery, and on-demand domain frameworks. By default it only produces output; if information is insufficient, clarify first. Triggers: "write a prompt", "write an English prompt", "optimize an English prompt", "Chinese-English bilingual prompt", "write a prompt", "improve…
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's…
agent-orchestrator
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with…
delegate
Delegate a prompt to an installed CLI in the current directory and return its output. Use when the user names a provider, model, or family for a one-shot.
create-skill
Create research-backed, spec-compliant Agent Skills with cited references, workflow templates, and anti-hallucination guardrails. Use when asked to "create a…
grill-to-plan
Grill a data-analysis or software request into an agreed plan for delegated work.
planning-workflows
Spec and no-spec planning workflows derived from local slash commands (requirements, design, tasks).
e2e-test-coverage-mapping
Map automated end-to-end tests (Playwright, Cypress, WebdriverIO, CodeceptJS, Puppeteer, Appium) to source code files and produce a `coverage.e2e.yml` mapping…
clawdbot-config
Comprehensive Clawdbot configuration and skills system management. Use when working with Clawdbot setup, configuration files, creating/modifying…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
agent-native-audit
Run comprehensive agent-native architecture review with scored principles
install
Install all dotai registry items in one command
ai-product-operating-model
Designs operating models for AI in product teams. Use when planning platform ownership, provider strategy, data boundaries, evals, or sensitive-data controls.
ai-scaling-laws
Sizes models and token budgets using Kaplan/Chinchilla scaling laws. Use when reasoning about compute-optimal N and D, tokens-per-parameter ratios, or…
foundations-ai-planning-search
Applies planning/search theory (A*, CSP, MCTS, PDDL, HTN) to agents. Use when ordering tool calls, enforcing preconditions before side effects, or validating a…
foundations-decision-theory
Chooses under uncertainty: value of more data, cost-based thresholds, abstention, when to stop a test and ship, robust choice. Use when deciding, not…
foundations-distributed-systems
Designs consensus, quorums, leases, idempotency, and CRDTs. Use when facing split brain, fencing tokens, exactly-once claims, duplicate retries, stale reads,…
vp-session-wrapup
Close out an agent session: summarize the outcome and open items, then find leftover state such as scratch files, uncommitted or unpushed Git work, running…
arkcli-agent
arkcli agent: manages ARK Managed Agents, including Agent / Skill / Env / Session / File / Memory Store / Vault / MCP OAuth. The control plane preferentially uses ForTop/OpenTOP, while Session runtime and Files use direct data-plane connections.
proactive-agent
An architecture design that turns an AI assistant from "waiting for tasks" into "proactively anticipating." Includes battle-tested patterns such as the WAL protocol, Working Buffer, and automatic scheduled tasks.
sandcastle
Run a Sandcastle lane — a sandboxed implement→review loop over a fixed batch of work in its own worktree, ended by an agent-authored PR.