AI Agent Skills Marketplace
55 skills and agents available
token-guard
Stop wasting tokens and money on oversized context. Token-Guard measures what you are about to send, flags the biggest offenders, and tells you what to trim, summarize, or drop before the call. Includes budget thresholds, per-file cost estimates, hard-limit gates, and a report you can act on. Pairs with lean-context and context-offload-hint.
aeo-citation-auditor
Get cited by AI answer engines. Audits a page for AEO/GEO readiness: entity clarity, answer-shaped structure, schema.org JSON-LD, llms.txt, crawler directives, and quotable claims. Returns a scored report with P0/P1/P2 fixes and copy-paste schema blocks. Built for teams who want ChatGPT, Perplexity, and AI Overviews to quote them.
sop-architect
Turn a messy process into an agent-ready SOP. Interviews you about a workflow, then produces a structured spec with roles, inputs, steps, decision points, failure paths, and acceptance checks that an AI agent can execute or automate. Includes templates, a gap analysis, and a validation checklist.
local-review-responder
Turn customer reviews into revenue. Drafts on-brand, policy-safe responses to Google, Yelp, and marketplace reviews, routes negative reviews with an escalation path, and extracts recurring themes into a short action list. Includes tone guardrails, review-bombing handling, and approved-response templates.
data-pipeline-agent
Design and document data pipelines end to end. Turns a business question into a source-to-destination plan: sources, ingestion, transformations, quality checks, scheduling, and failure handling. Produces a runnable spec with schema notes, validation rules, and a monitoring plan. For analysts and engineers who need pipelines that survive production.
outreach-writer
Draft buyer-facing outreach that gets replies. Reads a job brief, a prospect, or a product, then writes a short, specific, non-spammy message with a clear ask and a follow-up. Includes angle selection, personalization slots, tone control, and a checklist to avoid spam triggers. Works for freelance bids, cold email, and warm follow-ups.
lean-context
Cut token spend in long coding sessions. lean-context detects oversized context before you paste it (logs, JSON, big diffs, long docs) and gives concrete ways to split or offload it, then scopes code review to changed files with line counts and token estimates. Pairs with Token-Guard and context-offload-hint.
SKILL.md Snippet Generator
Generate a minimal, valid SKILL.md from a one-liner: frontmatter plus Triggers, Inputs, Procedure, Report, and Example. Designed to feed straight into skl-validator.
Context Offload Hint
Detect oversized content about to be pasted into a model or agent — logs, JSON, big diffs, long docs — and get concrete ways to split or offload it. Feeds into Token-Guard and lean-context.
YAML Frontmatter Fixer
Fix broken SKILL.md YAML frontmatter — quotes, commas, colons, list syntax, invalid characters — and show a before/after for each fix. Helps your skills pass skl-validator faster.
git changed scope lister
List changed/staged files with line counts and a rough token-size estimate, flagging the biggest diffs first. Helps you scope a code review or trim what you feed an agent. Feeds into lean-context/Token-Guard.
Markdown Link Checker
Sanity-check links in Markdown files — relative paths, anchors, and obviously broken targets — and get a fix list keyed by file and line. Handy for docs, READMEs, and SKILL.md files before you ship.
Competitive Intelligence Monitor
Know what your competitors changed this week — with a source for every claim. This recurring kit turns your AI agent into a systematic competitive-intelligence monitor: it keeps a watchlist, collects live competitor pages, detects real changes (pricing, positioning, features, launches, content), scores severity, and writes a decision-ready weekly digest. Two layers do what a prompt cannot: a collection layer that fetches live pages via the tool you already have and saves snapshots so diffs are reproducible; and a grounding layer where every change carries source + timestamp + before→after, inference is labelled READ:, and anything unevidenced is marked UNVERIFIED. Includes the weekly workflow, collection adapters, evidence-ledger rules, watchlist and competitor-profile templates, a severity rubric, digest and change-log templates, diffing methodology, a source matrix, quickstart and install guides, a worked example and demo script. For founders, growth leads and small agencies. No backend.
Canadian Bookkeeping Skills for AI Agents: CRA Mileage Log, T2125 & GST/HST
Four Agent Skills that help your AI assistant do Canadian sole-proprietor bookkeeping using CRA's rules, with current CRA rates, each with its source and as-of date, from the Tallyfern Rates MCP. - CRA mileage log: CRA trip fields, business-use %, the 3-month logbook test, current per-km rates. - T2125 expense sorting: turns bank, Etsy or Shopify CSVs into T2125 lines, applies the 50% meals limit, flags unclear rows. - GST/HST $30,000 check: CRA's small-supplier tests, and when you must register. - Year-end package: a tidy folder for your accountant or tax software. Works with Claude, Claude Code, Codex and Cursor. Single-buyer licence, no redistribution. Not tax advice. Designed by Tallyfern in Ontario with the help of AI tools. The examples are tested by automated checks, and every CRA rate is tested against CRA's published figures before release.
local-jev
Make Laya trustworthy. Fit its confidence to your own labeled data, keep the decisions it gets right local and free on Apple Silicon, and send only the ones it does not know to hosted Jev (TypeSafe System One) or any OpenAI-compatible LLM. Includes a Jev-compatible local server (laya-mlx), per-type temperature calibration with before/after ECE and accuracy, confidence thresholds for a target accuracy, an escalation-rate and cost report, a fail-open TypeScript decide() client, and a playbook to find LLM calls that are really classifications. Use for ticket routing, yes/no gates, rubric scores, replacing prompt-and-parse LLM classification, cutting Jev or LLM spend, and private offline typed decisions.
Notice Trap Pack
Build a SaaS vendor inventory from your CSV (or your own Ramp), catch renewals, score Switch / Renegotiate / Waste with real $, and get an approval-ready vendor counter — never auto-sends. Inventory → score → approval-ready draft. Never auto-emails vendors. Includes vendor-ops-setup, build-spend-inventory, score-savings-opportunity, research-alternatives, draft-vendor-counter, google-sheets-final-check. Missing evidence stays LEAD. Start free: Notice Trap Lite — https://agentpowers.ai/skills/notice-trap-lite
BrandLoom: Project Logos & Covers
Need a logo and cover that feel like they belong to the same project? BrandLoom helps you turn your project idea into a clear, consistent visual set. It reads the project information, files, links, and brand materials you provide, then asks one simple question at a time. You choose the wording, style, fonts, characters, layout, language, and image size before anything is created. BrandLoom can make a square project logo image, a wide cover, and a GitHub social preview in Chinese, English, or both. It can reuse your existing company logo and approved brand assets, keep important text clear, save new versions without replacing old ones, and help with later edits, translations, and style changes. It is made for solo founders, indie developers, AI builders, creators, and anyone launching a GitHub project, Skill, app, or digital product. Made for Codex. Full image creation requires Python 3.12 or newer and access to Codex's built-in image tool.
Cognitive Anchor Sketcher for Chinese Articles
Turn Chinese articles into hand-drawn visuals that explain the idea instead of simply decorating the page. Cognitive Anchor Sketcher reads the article, finds the strongest judgments, turning points, structures, states, and metaphors, then builds a focused shot list before image generation. Each illustration communicates one idea in a clean 16:9 composition with a white background, black hand-drawn linework, generous whitespace, and short Chinese annotations. Use it for newsletters, blogs, Notion pages, product thinking, workflow documents, and methodology content. Choose between minimal-line and emotion-doodle styles, use the included Xiaohei, Tuotuo, and Xingbi characters, or work with an authorized custom IP. A guided QA flow confirms the direction, style, IP, shot list, and output settings. It can also provide cognitive-anchor analysis and illustration planning without generating images. Image generation requires a ChatGPT-authenticated Codex CLI session.
Popular Platform Data Collection Skill
Popular Platform Data Collection Skill is an agent workflow for authorized content research, content archiving, and first-party account backups. It guides users to manually export public, owned, or clearly authorized videos, cover images, page copy, tags, engagement data, and comments through DATATOOL. It validates the input files, uses local OpenAI Whisper to transcribe the complete video audio track, anonymizes comment data when requested, and produces a verifiable Chinese ZIP package containing Excel files, text, subtitles, segmented JSON, and a SHA-256 manifest. Users handle DATATOOL installation, login, verification, authorization, and content export in a normal browser. The Skill does not control DATATOOL, store cookies or passwords, bypass captchas, paywalls, private-content restrictions, or anti-bot controls. Videos are transcribed locally by default and are not uploaded to third-party transcription services.
Project Sentinel - Multi-Project Development Progress Tracker
ENHE Project Sentinel is a local-first, read-only Skill for tracking multiple development projects. It reads authorized Git repositories, project documents, reports, quality signals, and available Codex usage data to generate bilingual project portfolio reports. Reports include progress, elapsed development time, ETA ranges, risks, quality signals, Codex context, token usage, next actions, and agent-ready prompts. It is designed for indie developers, AI product builders, product owners, and small R&D teams. Supports Windows 10/11. By default, it does not modify project code or upload source code, and it clearly marks insufficient evidence instead of inventing precise ETAs.
Verify Paid Work Before Starting
Paid-looking work can fail before implementation: the payer may be unverified, the issue may already be saturated, the rules may prohibit the submission, the requested result may be impossible to validate, or payment may depend on an undefined review. This gate instructs the agent to prove the commercial path before it commits time, credentials, reputation, or money. It checks buyer authority, amount and payment rail, assistance and eligibility rules, full deliverability, repository safety, competition, acceptance evidence, and time-to-cash. Four competitive levers produce a 0-100 score, but hard safety and payability gates always win. The result is one clear PROCEED or BLOCK decision with mandatory scope, exact blockers, a proof plan, the next bounded action, a stop condition, and the official evidence that would justify reconsideration.
Hikvision NVR
Ask your AI agent for the Hikvision footage you need, then walk away while it downloads. Pulling video off a Hikvision DVR or NVR usually means web-UI menus, ISAPI XML, ffmpeg flags, and "why is this video broken" troubleshooting. This skill removes all of it. Once your NVRs are registered, you just tell your agent "pull the lobby camera from 8 to 9 PM yesterday" and a clean MP4 lands in your downloads folder. Speaks Hikvision's ISAPI natively, falls back to RTSP when the NVR throttles, works around firmware quirks that return wrong segment data, clips to the exact time window you asked for, and verifies the output (codec, resolution, duration, on-screen timestamp). Credentials live in your OS keychain, never on command lines or in logs. Validated on DS-9016HWI-ST, DS-7316HQHI-SH, DS-7716NI-I4/16P, DS-9632NI-ST, and DS-7716NI-SP/16 with firmware V3.1.10 through V4.50.000.
AgentPass Local
Install a local credential broker with a desktop GUI, allowed-domain policy checks, and OS-protected sensitive fields. Use it when an approved agent workflow needs a narrow login or API handoff without putting passwords, tokens, recovery codes, or payout details into chat, logs, screenshots, or repositories.
mesh flow
What it does Mesh Flow replaces fragile, implicit prompt-chaining with a robust, artifact-driven DAG (Directed Acyclic Graph) orchestration system. By defining your agent workflows in a structured project.yaml, you move logic out of the prompt and into a compile-time validated system. It enforces hard gates—such as human approval or dependency verification—that the AI cannot bypass or hallucinate past. Why use this skill Standard agentic workflows often fail because the LLM decides to skip steps or "forgets" requirements. Mesh Flow treats your agentic workflow like a CI/CD pipeline. It features a Compile-then-Run architecture that validates your topology for cycles and missing artifacts before single token is generated. This ensures 100% predictable execution paths, explicit failure states (failed, blocked, rejected), and absolute control over recovery paths. Supported tools YAML-based workflow configurations Standardized Adapter Interfaces for cross-skill communication Mermaid DAG visualization for debugging Zod-backed schema validation CLI tools for compilation and execution (mesh compile, mesh run) Output structure The skill produces a normalized execution plan and a detailed execution trace. Every node execution returns a standardized status, a list of produced artifacts, and comprehensive metadata including tool calls and verification reasoning. Use Cases Build multi-step agent pipelines with hard verification gates Enforce human-in-the-loop approval before sensitive code deployments Visualize complex agent task dependencies using Mermaid DAGs Standardize artifact sharing between disparate AI skills and agents