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 abullaisi/upwork-skills --skill upwork-proposal-writergit clone --depth 1 https://github.com/abullaisi/upwork-skillsWrote 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/abullaisi/upwork-skills/upwork-proposal-writer)<a href="https://agentmods.dev/skills/abullaisi/upwork-skills/upwork-proposal-writer"><img src="https://agentmods.dev/badge/skills/abullaisi/upwork-skills/upwork-proposal-writer/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/abullaisi/upwork-skills/upwork-proposal-writer"><img src="https://agentmods.dev/badge/skills/abullaisi/upwork-skills/upwork-proposal-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 3 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00115 | $0.01937 |
| Opus 5 | $0.00057 | $0.00968 |
| Sonnet 5 | $0.00023 | $0.00387 |
| Haiku 4.5 | $0.00012 | $0.00194 |
Grade A, and why
upwork-proposal-writer 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 11d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upwork Proposal Writer
Draft proposals the way a Top Rated Plus freelancer actually writes them, not the way template blogs say to. The method below was extracted from real winning proposals (design/dev niche, top 3% Upwork tier) and cross-checked against Upwork's own published guidance. Where the two disagree, this file says so.
Inputs you need before drafting
Ask for anything missing. Never invent these.
- The job post, pasted in full.
- The user's identity line facts: role, years of experience, niche specialization.
- 3-5 portfolio links or samples that match THIS job's niche. Matched proof beats impressive-but-unrelated proof. If the user gives you ten links, pick the closest 3-5 and say why.
- One relevant outcome they can claim (a shipped result, a metric, a client situation similar to this job). The outcome belongs in the credibility move. If the user can't supply one, draft without it and say so. Never invent one.
- Optional: rate intentions, availability, anything the client asked applicants to answer.
Profile shortcut: if a stored profile file exists (upwork-profile.md in the working directory or ~/.claude/), read identity, niche, links, and rate from it and ask only for what's missing or not stated concretely (a rate line that says "ask me" means ask). Never ask for what the file already answers.
Before drafting, check the job's core ask against the profile. If a major requirement sits outside what the profile actually covers, flag the stretch in one line before the draft. The draft itself only claims what's real.
Mode 1: Draft (primary)
The five moves, in order
Move 1: credibility line. One sentence: identity + years + niche. Example shape: "I'm a UI/UX designer with 5+ years specializing in SaaS dashboards." This is the first thing the client sees in the results-list preview, alongside the freelancer's photo, badges, rate, and Job Success Score. It has to establish fit in one line.
Move 1, no-history variant. A freelancer with no Upwork track record still has a credibility line; it just does not come from this platform. Build it from what is real: years in the craft anywhere, the work itself, a specialization. "I'm a UI/UX designer with 4 years on SaaS dashboards, new to Upwork and bringing the portfolio with me" is honest and reads far better than padding. Two rules. Never imply Upwork experience that does not exist, because the profile beside the proposal shows the truth and the gap reads as dishonesty. And never apologize for being new; state it once as a fact if at all, then spend the rest of the sentence on the specialization. The same applies to input 4: the relevant outcome can come from any client, employer, or personal project, and it is worth saying explicitly rather than leaving the user to assume Upwork-only.
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.
- 11d ago First seen · 84 lines · 115 tokens per session scan A 9d80fbdd93ac
upwork-proposal-writer is a skill published in the GitHub repository abullaisi/upwork-skills (100 stars, last pushed 1mo ago), licensed MIT. It adds 115 tokens to every session and 1,937 once invoked, about $0.0006 per session on Opus 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 2026-08-30.
Other skills, from other repositories
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…