truefoundry-prompts
Manages TrueFoundry Prompt Registry. Covers listing, creating, updating, versioning, tagging, and using prompts through the AI Gateway. Agent authoring belongs…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,666 results
rlm-subagent
Master skill for parallel subagent-driven execution with automatic fallback to single-agent sequential mode. Use when implementing plans with multiple…
ts-workflow-explore-plan-review
Run an interactive explore phase followed by a plan-review loop. Only explicitly triggered by user.
ts-workflow-plan-review
Run a plan-review loop. Only explicitly triggered by user.
lead-agent-ownership
Coordinate delegated research or implementation without duplicate work; retain lead-agent ownership of review, integration, and final delivery.
claude-codex-consensus
Get Claude Code and Codex to independently review designs, implementation plans, diffs, or proof strategy, then reconcile the disagreement. Use when the user…
council
Council · Think Tank: Distill real people's thinking frameworks into Advisors, and support multi-Advisor roundtable discussions. All Advisors are stored as persona files in the personas/ directory, managed uniformly by Council. Three use cases: (A) Distill: input a person's name/topic/vague requirement → in-depth research → extract mental models → generate Advisor...
agent-browser
Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to…
slate-ar-next
Slate v2 Autoresearch daily driver. Reads current state, chooses the best next owner, and runs one safe next step without making the user pick…
fan-out-work
Cover a large work-list in parallel without losing correctness or honesty — scout the items inline, then run each through its stages concurrently (map,…
schedule-recurring-agent
Stand up a recurring scheduled agent for standing work (triage, monitoring, audits, digests): a self-contained IDEMPOTENT brief (each run wakes memory-less and…
watch-and-act
Wait on an EXTERNAL signal the harness can't notify you about — CI, a deploy, a queue, an endpoint — polling on a cache-aware cadence (≤270s active, ≥1200s…
skill-optimizer
Improve, debug, benchmark, or refactor an existing Agent Skill from conversation evidence, execution traces, user corrections, eval failures, or target skill…
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
agents-autogpt
AutoGPT platform for building, deploying, and running continuous autonomous agents. Use for visual workflow agents, persistent automation, and multi-step AI…
gsd-audit-milestone
Audit milestone completion against original intent before archiving
gsd-autonomous
Run all remaining phases autonomously — discuss→plan→execute per phase
gsd-fast
Execute a trivial task inline — no subagents, no planning overhead
gsd-insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases
gsd-list-phase-assumptions
Surface the agent's assumptions about a phase approach before planning
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents
gsd-research-phase
Research how to implement a phase (standalone - usually use $gsd-plan-phase instead)
gsd-resume-work
Resume work from previous session with full context restoration
gsd-review
Request cross-AI peer review of phase plans from external AI CLIs