canopyops
1657Skill Claude CodeCodex
🌿 Cannabis health, climate, and yield.
not rated 11
changed yesterday A 14 tokens
agents-md
1658Skill Claude Code needs its repo
Generate a portable AGENTS.md at project root from the project's .add/ state. AGENTS.md is the cross-tool open standard for project-level agent instructions — any agent (Claude Code, Cursor, Codex CLI, Windsurf, Amp, Devin, Copilot) will read it on session start. Publishing one lets mixed-toolchain teams respect the…
not rated 11 1mo ago A 32 tokens
original MIT
prevu
1659Skill Claude CodeCodex
Use when running, configuring, or debugging the Prevu CLI (prevu binary) - managing preview environments, exposing ports, SSH access, API tokens, signing in, listing envs, and service commands. Mentions: prevu, prevu env, prevu auth, prevu keys, prevu.cloud, app.prevu.cloud, prevu.page, PREVUTOKEN, preview…
not rated 11 3mo ago A 87 tokens
original MIT
runpod-job
1660Skill Claude CodeCodex
Default Runpod workflow for user-managed Pods. Ask the human to create a Pod with the desired GPU, get the podid and SSH access details, save a manual Pod profile, and use opencolab gpu ssh sessions as the default control path. Use OpenColab gpu server and gpu job only when the user explicitly wants managed…
not rated 11 1mo ago A 86 tokens
original MIT
know-before-act
1661Skill Claude CodeCodex
Reduce decision-relevant uncertainty before execution. Use at the start of tasks where missing goals, constraints, context, or preferences could materially change the plan; ask at most one high-information question at a time and otherwise proceed with reasonable assumptions.
not rated 11 1mo ago A 51 tokens
original MIT
wwind123/coding-review-agent-loop
Skill Claude CodeCodex
This skill lets you run the coding-review-agent-loop orchestration directly inside an interactive Claude Code session, without calling claude -p for Claude turns.
not rated 11
changed today A 0 tokens
original MIT
possible
1663Skill Codex
Discover proven Outcomes and turn a rough request into one complete execution prompt for a fresh agent. Also author and validate source-owned Outcomes for Possible.
not rated 11
changed 10d ago A SkillSpector: warn 30 tokens
original MIT
deslop
1664Skill Claude CodeCodex
Deslop, humanize, edit, or audit AI-sounding, robotic, generic, corporate, or ChatGPT-like copy while preserving the writer's voice.
not rated 11 1mo ago A 35 tokens
original MIT
skill-creator
1665Skill Claude CodeCodex
Create or optimize Claude Code skills with best-practice structure, bundled resources, and prompt engineering patterns.
not rated 11 5mo ago A 24 tokens
original Apache-2.0
agent-vision
1666Skill Claude Code
Visually verify rendered output before claiming a UI/visual task is done. Use whenever you generate or edit a visual artifact — frontend HTML/CSS/JSX, a generated chart or plot, an SVG/diagram, a PDF, or an exported image. AgentVision renders the artifact, "sees" it, and returns a machine-graded report (pass/warn/fail…
not rated 11 3d ago A 101 tokens
original MIT
dear-agent
1667Skill Claude Code
A procedure for following this workspace’s documentation rules, including its required project files and single handoff document. A handoff records what was done, what comes next, and what is blocked.
not rated 11 1mo ago A 125 tokens
original MIT
obai-strategy
1668Skill Claude CodeCodex
Quantitative equity strategy design and backtesting via the OBaI backtest MCP server (http://localhost:8007/mcp). Use when the user wants to build, test, backtest, optimize, refine, repair, or compare a trading strategy, run walk-forward robustness validation, inspect trade logs, or follow up on a backtest job.…
not rated 11
changed 5d ago A 111 tokens
reconcile-shelf
1669Skill Claude CodeCodex
Check the shelf against the returns that were approved, and report what is missing.
not rated 11 5d ago A 21 tokens
original MIT
ragcode-agents
1670Skill Codex
Orchestrate multi-agent workflows through RagCode. Turn a natural-language collaboration pattern (e.g. "Gemini plans, Claude breaks down, Codex implements, Claude reviews") into a validated DAG workflow spec, then run it with the RagCode agent workflow engine. Trigger when the user asks to coordinate multiple AI…
not rated 11 1mo ago A 96 tokens
original MIT
hitl-protocol
1671Skill Claude CodeCodex
HITL Protocol — the open standard for human decisions in autonomous agent workflows. When a website or API needs human input, it returns HTTP 202 with a review URL. Autonomous agents like OpenClaw, Claude, Codex, or Goose forward the URL, poll for the structured result, and continue. Use this skill to make any website…
not rated 11 2mo ago B 163 tokens
original Apache-2.0
openwiki-operator
1672Skill Claude CodeCodex
Use when working with OpenWiki or configured OpenWiki MCP tools to search, add sources, propose pages or edits, validate proposals, review/apply changes, monitor agent activity, or explain wiki Git history.
not rated 11 2d ago A SkillSpector: pass 46 tokens
original MIT
Codomyrmex
1673Skill Claude CodeCodex needs its repo
Full-spectrum coding workspace skill providing 627 production MCP @mcptool lines across 130 top-level modules. USE WHEN user says 'verify codomyrmex', 'codomyrmexVerify', 'audit codomyrmex', 'trust codomyrmex', 'codomyrmexTrust', 'trust tools', 'enable destructive tools', 'check pai status', 'codomyrmex tools'…
not rated 11 today A SkillSpector: pass 185 tokens
original MIT
daily-rundown
1674Skill Claude CodeCodex needs its repo
The owner's morning brief — inbound updates awaiting acknowledgment (via the rundown tool), today's meetings and due-or-overdue reminders from the CRM and the real calendar, the emails worth seeing from Gmail, and the Slack threads that need their eyes — each source folded in when connected and stitched into one short…
not rated 11 2mo ago A 87 tokens
original Apache-2.0
skill-creator
1675Skill Claude CodeCodex
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 11 6d ago A 64 tokens
AGPL-3.0
opendexter
1676Skill Claude CodeCodex
Use hosted OpenDexter through one authorized connection to discover services with Indexter, create and inspect opaque purchase intents, call approved paid or wallet-gated resources, and read the session-bound Dexter Wallet and governed portfolio.
not rated 11
changed 9d ago A 48 tokens
grape
1677Skill Claude CodeCodex
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
not rated 11 2mo ago A 48 tokens
original MIT
anneal-memory
1678Skill Claude CodeCodex
Persistent four-layer agent memory (episodic + continuity + Hebbian + affective) plus a prospective spore layer and an on-demand crystallized-pattern tier, via anneal-memory. Use in any project wired for anneal-memory — an ANNEALMEMORYDB env var, an anneal://continuity MCP resource, or memory instructions referencing…
not rated 11
changed 9d ago A 170 tokens
original MIT
hetzner-provision
1679Skill Claude CodeCodex
Spin up and tear down complete Hetzner infrastructure end to end through the hetzner-mcp tools, safely, with a live price preview and an explicit confirmation before anything billed. Use when the user wants to provision a server, a full stack, a network, a firewall, storage, or to clean it all up afterward.
not rated 11 yesterday A 73 tokens
charted
1680Skill Claude CodeCodex
Generate SVG or PNG charts from raw numbers or a CSV using charted, a zero-dependency Python chart library. Covers bar, column, line, scatter, bubble, pie, polararea, radar, area, box, histogram, heatmap, gantt, combo, and sankey, plus multi-series data, named palettes, and a CLI. Use when asked to plot, chart, or…
not rated 11 2mo ago A 90 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: