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 tmargolis/career-navigator --skill tailor-resumegit clone --depth 1 https://github.com/tmargolis/career-navigatorWrote 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/tmargolis/career-navigator/tailor-resume)<a href="https://agentmods.dev/skills/tmargolis/career-navigator/tailor-resume"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/tailor-resume/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/tmargolis/career-navigator/tailor-resume"><img src="https://agentmods.dev/badge/skills/tmargolis/career-navigator/tailor-resume.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 Excessive Agency · line 58 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00071 | $0.01725 |
| Opus 5 | $0.00036 | $0.00863 |
| Sonnet 5 | $0.00014 | $0.00345 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
tailor-resume 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 10d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assemble the best possible resume for a specific role, drawn from the user's ExperienceLibrary. Invoke the resume-coach agent to do the work.
Workflow
1. Collect inputs
Job description — required. If the user has not provided one:
"Paste the job description and I'll tailor your resume for it."
Verify the JD against the canonical source — always. Before handing anything to resume-coach, fetch the posting from the company's own careers page or ATS (Greenhouse, Lever, Ashby, Workday, SmartRecruiters). Aggregator listings — Indeed, LinkedIn, Ladders, ZipRecruiter, Jobgether, BuiltIn — are frequently truncated, stale, or reworded, and any job_link stored in recommendations.json may point at one.
How to find the canonical post: search {Company} {Role} careers or {Company} greenhouse OR lever OR ashby {Role}, then fetch it. If the aggregator link is a shortlink (e.g. to.indeed.com/...), it will usually not resolve to usable text — go find the real posting instead of retrying the fetch.
Then diff the canonical JD against whatever the user or recommendations.json supplied, and flag every contradiction to the user before building the resume. Report them plainly:
"The full JD on {source} differs from the listing we had on file: {contradiction}. That changes {what it changes}. Want me to proceed on the canonical version?"
Contradictions that matter most, because they change targeting or disqualify the role:
- People-management scope — "lead a team of PMs" vs. an IC/individual-contributor framing
- Seniority or title — Director vs. Senior PM vs. Principal
- Location and work model — onsite/hybrid/remote, and which office
- Compensation band — especially where a pay-transparency disclosure appears only on the canonical post
- Hard requirements — degree filters, years of experience, clearance, work authorization
- Required application materials — essays, work samples, portfolios, take-homes that aggregators drop entirely
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.
- 10d ago First seen · 139 lines · 71 tokens per session scan A 682ed06345ae
tailor-resume is a skill published in the GitHub repository tmargolis/career-navigator (13 stars, last pushed 11d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,725 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…