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 agentsope/career-skills --skill career-bullet-buildergit clone --depth 1 https://github.com/agentsope/career-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/agentsope/career-skills/career-bullet-builder)<a href="https://agentmods.dev/skills/agentsope/career-skills/career-bullet-builder"><img src="https://agentmods.dev/badge/skills/agentsope/career-skills/career-bullet-builder/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/agentsope/career-skills/career-bullet-builder"><img src="https://agentmods.dev/badge/skills/agentsope/career-skills/career-bullet-builder.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 | $0.00275 | $0.03366 |
| Opus 5 | $0.00138 | $0.01683 |
| Sonnet 5 | $0.00055 | $0.00673 |
| Haiku 4.5 | $0.00028 | $0.00337 |
Grade A, and why
career-bullet-builder 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 12d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Career Bullet Builder · 简历条目打磨器
把"我负责数据整理""参与了一个小组项目""跟教程做了个模型"这种粗糙素材,打磨成简历上一行就让 HR 停一下、且完全属实的中文条目(bullet)。这是 career-skills pack「做简历」环节的第二块——上游 career-experience-mapper 负责"挖出能写什么",本 skill 负责"把它写成最锋利的成品行"。
核心原则 / Core principle:Polish, never inflate. 只打磨表达,不抬高事实。证据不足就用保守动词或留缺口,绝不替用户编数字、成果或头衔。每个写进简历的数字,用户都要能在面试里讲清来源。
Activation Rules
触发(do):
- "帮我把这段经历写成简历条目 / bullet。"
- "这句简历怎么改得更有力 / 更专业?"
- "我简历这条太弱 / 太平,帮我润色。"
- "这条经历怎么量化?没有数字怎么办?"
- 承接
career-experience-mapper的产出,要写成成稿 bullet。
不触发(don't — 交给别的 skill):
- "我不知道这段经历能写什么 / 体现什么能力" →
career-experience-mapper(先挖能力)。 - "整份简历怎么排版 / 投这个岗位怎么调 / 简历该多长" →
career-resume-tailor。 - "有哪些岗位适合我 / 帮我看这份 JD" →
career-role-finder/career-jd-analyzer。 - cover letter、面试故事 → 对应 skill。
Agentic Protocol
按顺序执行;每步有可验证产出。涉及方法细节时按需 Read 对应 reference,不要把整份贴给用户。
Step 1 — 接素材 (Intake · B1). 取得三种之一:(a) experience-mapper 的 handoff 块;(b) 用户已有的简历句;(c) 一句话口语经历。识别:动作 / 对象 / 方法·工具 / 产出 / 已有数字 / 目标岗位关键词(若有)。口语和模糊处先如实标记,不脑补。
→ 产出:归一化的"待打磨素材"清单。
Step 2 — 选公式 (Formula · B2). Read references/bullet-formulas.md。默认 PAR(情境-行动-结果);有真实数字用 XYZ(成果+量化+方法);技术项目用 CAR(挑战-行动-结果)。一条经历可给 1-2 个公式版本。
→ 产出:每条素材选定的公式。
Step 3 — 强动词 + 诚实量化 (Verb & Quantify · B3). Read references/action-verbs.md,把弱开头(负责 / 参与 / 帮忙)换成精确强动词,按 evidence 档位选词(贡献小别用"主导")。Read references/quantification.md:有真实数字就量化;没有走 fallback(规模 / 频率 / 周期 / 技术细节),绝不编数字。
→ 产出:每条的强动词版 + 量化或缺口标记。
Step 4 — 成品优化 (Optimize · B4). Read references/ats-optimization.md。控长度(每条 1-2 行)、统一时态 / 句式、多条之间动词去重与排比、嵌入岗位关键词、按影响力排序。
→ 产出:打磨后的成品 bullet(可多变体)。
Step 5 — 诚信闸门 (Integrity Gate · B5). Read references/no-fabrication.md,逐条过:有没有编数字 / 成果 / 头衔?团队成果标了个人范围吗?动词层级配得上真实贡献吗?继承上游 gaps / integrity_flags,绝不用编造去填缺口;拿不准直接问用户。
→ 产出:通过 / 标记项 + 待补充清单。
Step 6 — 输出 (Output). 按下方 Output 结构给成品 bullet(每条标公式 / 缺口),提示哪些补真实数字会更强,并说明下一步可交给 career-resume-tailor 排进整份简历。
Core Operation Models
| # | 模型 Model | When to use | Key action |
|---|---|---|---|
| B1 | Intake 素材接入 | 拿到 handoff / 已有 bullet / 口语经历 | 抽 动作/对象/方法/产出/数字/关键词,不脑补 |
| B2 | Formula Selection 选公式 | 定一条怎么搭骨架 | PAR(默认)/ XYZ(有数字)/ CAR(技术项目) |
| B3 | Verb & Quantify 动词与量化 | 升级表达 | 弱→强动词(按 evidence 档)+ 诚实量化 / fallback |
| B4 | Bullet Optimization 成品优化 | 出可投递成品 | 长度/时态/排比/去重/关键词/排序/多变体 |
| B5 | Integrity Gate 诚信闸门(红线) | 贯穿,输出前必过 | 不编数字/成果/头衔;继承 gaps;拿不准就问 |
What ships with it
8 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.
- 12d ago First seen · 169 lines · 275 tokens per session scan A feedcba1716f
career-bullet-builder is a skill published in the GitHub repository agentsope/career-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 275 tokens to every session and 3,366 once invoked, about $0.0014 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 2026-08-31.
Other skills, from other repositories
ats-latex-cv
Build ATS-optimised, human-sounding CVs in LaTeX (Overleaf-ready code). Trigger this skill whenever a user asks to create, rewrite, reconstruct, or improve a CV, resume, or job application document — including when they upload an existing CV, paste raw experience, or describe a target role. Also trigger when the user…
Academic CV Builder
Format CVs for academic positions with publications, grants, and teaching.
vitaecontext-wiki-maintenance
Maintainer-only skill for refreshing VitaeContext wiki knowledge from official sources. Use only from a local repository clone when a maintainer asks to refresh one module, audit all module wiki entries, or audit module source lists.
vitaecontext-vitaegraph
Build, deepen, validate, index, and maintain a private hierarchical career knowledge graph from supplied career materials. Use when the user asks to create or update a VitaeGraph, model education with nested courses or thesis work, enrich projects from Git repositories, or supply deep selected career context to…
vitaecontext-build
Build, normalize, and maintain the user's Career Context file so downstream platform outputs stay factual and consistent. Use when the user wants an agent to consolidate CV data, LinkedIn exports, GitHub history, project summaries, bio facts, achievements, or positioning into one professional source of truth before…
vitaecontext-cv
Optimize CV and resume content for recruiter readability and parser-safe ATS handling without making unsupported claims about exact vendor scoring. Use when the user asks about resumes, CVs, ATS formatting, keyword strategy, bullets, section order, achievement metrics, or job-targeted resume tailoring.