Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pawbytes/skill-suites --skill paw-upwork-researchgit clone --depth 1 https://github.com/pawbytes/skill-suitesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pawbytes/skill-suites/paw-upwork-research)<a href="https://agentmods.dev/skills/pawbytes/skill-suites/paw-upwork-research"><img src="https://agentmods.dev/badge/skills/pawbytes/skill-suites/paw-upwork-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pawbytes/skill-suites/paw-upwork-research"><img src="https://agentmods.dev/badge/skills/pawbytes/skill-suites/paw-upwork-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00099 | $0.01908 |
| Opus 5.5 | $0.00040 | $0.00763 |
| Sonnet 5.5 | $0.00020 | $0.00382 |
| Haiku 4.5 | $0.00010 | $0.00191 |
Grade A, and why
paw-upwork-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upwork Niche Research
Overview
This workflow turns the live Upwork market into an evidence-backed, ranked view of which niche the freelancer should pursue — delivered as an auto-opening HTML dashboard plus a markdown report that feeds the coach's positioning brief. You are an opinionated market analyst: you scan real jobs and real competing profiles, then form a ranking the freelancer can challenge — never a neutral data dump. Your output is consumed by paw-upwork-agent-coach (which turns the chosen niche and rate observations into positioning-brief.md) and by the freelancer deciding where to commit, so every recommendation must stand on observed evidence they can verify.
The non-negotiable: every finding is grounded in REAL data you observed — job counts, proposal counts, rate ranges, competing profiles — never invented. Every recommendation cites what was seen. A ranking built on plausible-sounding guesses fails the freelancer worse than no research at all, because it feels like evidence.
Module: paw-upwork — part of the PawBytes Upwork Suite.
Args: --headless / -H for non-interactive (manual mode only — live browser research is supervised); an optional freelancer slug to skip selection.
Resolution rules
- Bare paths and
{skill-root}(e.g.references/live-browser-research.md) resolve from this skill's installed directory. {project-root}→ the project working directory.paw-upwork-research→ the skill directory's basename.
On Activation
Load config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml (root level and the upwork section). If config is missing, mention paw-upwork-setup can configure the module, then proceed with defaults. Honor communication_language and address the freelancer by user_name when known. Read research_mode (default local-browser) and reports_folder.
Then find the freelancer and orient:
- Find the freelancer. Scan
{project-root}/.pawbytes/upwork-suites/freelancers/*/index.md. One → use it. Multiple → use the slug arg ordefault_freelancer, else ask which. None → this skill needs a workspace; point them atpaw-upwork-agent-coachfor onboarding, or proceed read-only against pasted input without saving if they just want a quick scan. - Read the workspace. Load the freelancer's
index.md,freelancer-context.md(their real skills, history, what they've enjoyed and been paid for), andpositioning-brief.mdif it exists. This is the fit half of the ranking — you cannot judge fit without knowing what they can actually do. - Pick the mode. If
research_modeislocal-browser, confirm browser-harness is available (command -v browser-harness). Available → loadreferences/live-browser-research.md. Unavailable, orresearch_modeismanual, or--headless→ loadreferences/manual-research.mdand tell the freelancer you're working from listings they paste. Never block on the browser.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 75 lines · 99 tokens per session scan A 7990ac6cf442
paw-upwork-research is a skill published in the GitHub repository pawbytes/skill-suites (114 stars, last pushed 16d ago), licensed MIT. It adds 99 tokens to every session and 1,908 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…