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 ssmurfgg04-gif/context-m --skill job-intent-trackergit clone --depth 1 https://github.com/ssmurfgg04-gif/context-mWrote 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/ssmurfgg04-gif/context-m/job-intent-tracker)<a href="https://agentmods.dev/skills/ssmurfgg04-gif/context-m/job-intent-tracker"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/job-intent-tracker/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/ssmurfgg04-gif/context-m/job-intent-tracker"><img src="https://agentmods.dev/badge/skills/ssmurfgg04-gif/context-m/job-intent-tracker.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 | $0.00161 | $0.01885 |
| Opus 5 | $0.00081 | $0.00942 |
| Sonnet 5 | $0.00032 | $0.00377 |
| Haiku 4.5 | $0.00016 | $0.00188 |
Grade A, and why
job-intent-tracker 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 7d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Job Intent Tracker(求职意向 + 岗位追踪)
这个 skill 解决"求职启动期"的三个核心问题:
- 我适合投什么岗? —— 从用户背景里抽取信号,反推 2~3 个目标方向
- 目标岗位长什么样? —— 为每个方向生成"岗位画像 / Target Profile"
- 投了哪些、进度如何? —— 维护一份结构化追踪表(Excel / Markdown 表)
不要把这个 skill 用成"简历改写"或"面试题生成"——那是 resume-builder / jd-resume-tailor / interview-prep 的事。本 skill 只关心"方向"和"管理"。
何时触发本 skill
强信号(基本必须用):
- "我想换工作 / 想跳槽 / 想找下一份工作"
- "帮我看看我适合什么岗位"
- "帮我管理投递进度 / 跟踪一下我投的公司"
- "我有 X 年 Y 经验,下一步该往哪走"
- "我投了好多家但忘了进度"
弱信号(先确认再用):
- 用户只丢了一份简历,没说目的 → 先问"你是想梳理方向、改简历,还是准备面试?"
- 用户说"想找工作"但很模糊 → 先问"你心里有目标方向吗?还是想让我帮你判断方向?"
工作流程
按这个顺序走,一步都不要跳:
Step 1: 自我盘点(Background Intake)
用 AskUserQuestion(或在没有该工具时直接问)收集以下信息。不要一次问完,分 23 轮,每轮 23 个问题,否则用户会被"问卷感"劝退。
第一轮(必问):
- 当前 / 最近一份工作的岗位、公司类型、年限
- 核心技能 3~5 个(关键词即可)
- 目标行业 / 目标方向(如果用户有)—— 没有也没关系,跳到 Step 2
第二轮(看情况问):
- 期望薪资 range(用户不愿意说就跳过)
- 城市偏好 / 是否接受 remote
- 排除项("不想做销售 / 不想加班 / 不接受出差"等)
第三轮(深度信号,仅在前两轮信息不足以画像时问):
- 最有成就感的 1~2 个项目
- 最不喜欢做的事
- 5 年后的画面
如果用户上传了简历 .pdf / .docx,先调用 pdf 或 docx skill 解析出文本,再从中抽取以上信息,避免用户重复打字。
Step 2: 推荐求职方向
基于 Step 1 的信息,生成 2~3 个候选方向。每个方向都要写清楚:
方向 N:<岗位名>(如:互联网产品经理 / 数据分析师 / 量化研究员)
- 匹配度:高 / 中 / 低(高=核心技能直接命中;中=需补 1~2 个关键技能;低=需要转岗叙事)
- 匹配理由:基于用户的 ___ 经验和 ___ 技能
- 缺口:用户还需要补 ___ 才能成为强候选人
- 典型雇主:<3~5 个具体公司或公司类型>
- 薪资带(仅供参考):__k - __k(注明"市场行情,仅供参考,建议用户自行通过职级查询")
重要:不要只推荐"安全"的方向。 如果用户技能允许,至少给一个"跳一跳能够到"的方向,并诚实标注缺口。
Step 3: 生成岗位画像(Target Profile)
为用户最终选定的 1~2 个方向(让用户主动选),生成详细画像。模板在 references/target_profile_template.md,需要读取这个文件后再填充。
画像要包含:岗位职责典型描述、技能要求 must-have / nice-to-have、面试流程预期、对标公司列表(按 tier 分层)。
读取行业关键词库决定 must-have / nice-to-have:
- 互联网产品 / 运营 / PM →
references/keywords_internet.md - 技术 / 研发 / 数据 →
references/keywords_tech.md - 金融 / 咨询 / 商科 →
references/keywords_finance.md - 通用 / 跨行业 →
references/keywords_general.md
Step 4: 创建投递追踪表
调用 scripts/init_tracker.py 生成初始追踪表。脚本支持两种格式:
python scripts/init_tracker.py --format xlsx --output /path/to/tracker.xlsx
# 或
python scripts/init_tracker.py --format md --output /path/to/tracker.md
What ships with it
7 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.
- 7d ago First seen · 137 lines · 161 tokens per session scan A cc01edc2deb4
job-intent-tracker is a skill published in the GitHub repository ssmurfgg04-gif/context-m (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 161 tokens to every session and 1,885 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
test-plan
Build a test plan when a new Epic is created. Pulls epic details and linked stories from Jira, analyzes scope, and produces a test plan covering strategy, automation gap analysis, success criteria, environment needs, and risks. Output goes to Confluence and local test knowledge base. Use when: "test plan", "plan tests…
review-ticket
Review a Jira ticket during backlog grooming or refinement. Audits the ticket for testability, AC completeness, missing edge cases, and potential blockers. Outputs a structured review the SDT can bring to the grooming session. Use when: "review this ticket", "check ACs", "testability review", "grooming". Do NOT use…
setup
First-run configuration wizard for QABuddy. Sets up context source (Jira, spec docs, chat, custom), team mode (solo vs PR-based), and project preferences. Writes .qabuddy.json to the project root. Optionally wires QABuddy to run on pull requests (the reusable PR-coverage workflow). Re-run to reconfigure. Use when…
digest
NOTE: this skill requires connected chat / email / project-tracker / docs MCPs, which are typically only present in Cowork — the Code variant exists for parity but most users will want the Cowork variant. Cross-tool rollup of what's pending, what shipped, and what's blocked across chat / email / project tracker /…
roadmap
Render a per-project feature roadmap — a Band×Status grid (Shipped/Current/Next/Later × done/in-progress/blocked/buildable) synthesized from CLAUDE.md + PROGRESS.md, persisted to a committed ROADMAP.md with staleness-aware refresh. Modes: '/roadmap' (nearest project), '/roadmap ' (a projectslist tag), '/roadmap…
stitch
Build or verify cross-repo STITCH.md linking backend + frontends in a product group. Modes: create, verify, diff, section. Uses CODEMAPs as drift source by default. Trigger: '/stitch create ', '/stitch diff '.