Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/soia-team/soia-open-skillsnpx agentmods add skills/soia-team/soia-open-skills/soia-meta-find-skillWrote 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/soia-team/soia-open-skills/soia-meta-find-skill)<a href="https://agentmods.dev/skills/soia-team/soia-open-skills/soia-meta-find-skill"><img src="https://agentmods.dev/badge/skills/soia-team/soia-open-skills/soia-meta-find-skill/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/soia-team/soia-open-skills/soia-meta-find-skill"><img src="https://agentmods.dev/badge/skills/soia-team/soia-open-skills/soia-meta-find-skill.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 | $0.00048 | $0.01762 |
| Opus 5 | $0.00024 | $0.00881 |
| Sonnet 5 | $0.00010 | $0.00352 |
| Haiku 4.5 | $0.00005 | $0.00176 |
Grade A, and why
soia-meta-find-skill 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 3d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
soia-meta-find-skill
按自然语言需求发现最匹配的 SOIA 技能，优先识别当前项目已安装的技能；未安装时只收集安装选择，不安装、不同步、不发布。
客户可读说明
这个技能可以做什么
- 在项目
.agents/skills、用户全局真源或公开生态目录中发现候选技能。 - 识别代码审查、架构评审、调用链、数据流、模块边界等中文意图。
- 返回“项目/全局、目标 Agent、单技能/整域/全量”选择意图，交给安装或同步技能执行。
客户如何使用
先从当前项目查找；若当前目录不能确定项目，脚本不会暗自扫描全局目录，而会让 Agent 向客户确认范围。
python3 scripts/find_skill.py --query <关键词> [--project <项目路径>] [--scope auto|project|global|both] [--agent <Agent>]
从仓库源码调用：
python3 skills/soia-meta-find-skill/scripts/find_skill.py --query <关键词> --project <项目路径> --agent claude --agent codex
--agent 可重复，仅保留客户的目标 Agent 选择，不猜测任何宿主目录。--scope auto 仅扫描可确定的当前项目；project、global、both 是显式范围。--skills-dir 与 --directory 保留给旧离线调用和测试。
依赖与安装
运行时只依赖 Python 3 标准库。本路由技能可随 soia-meta 领域插件提供给 Claude Code 或 Codex：
claude plugin marketplace add soia-team/soia-open-skills && claude plugin install soia-meta@soia
codex plugin marketplace add soia-team/soia-open-skills && codex plugin add soia-meta@soia
WorkBuddy 以角色化专家装载，见 docs/install/workbuddy.md。
本技能不会默认生成 -g -a '*' 命令。未安装候选必须先让客户确认：安装到项目还是全局、哪些 Agent、单技能/整域/全量；默认是单技能，绝不默认全量。确认后把结构化选择交给安装或同步技能；发布流程也不得顺带安装，除非客户另行选择。仅选择字段齐全不等于写入批准；只有已展示影响并获客户明确批准、且包含 source、具体 target、action 以及删除/替换影响的完整计划，才可由下游复用而不重复询问。计划字段变化时重新确认受影响部分。
npx skills add 仍是单技能安装路线，但它的具体参数只能由安装 owner 在客户确认选择后生成；本 finder 不构造或执行该命令。
仅为旧消费者提供 --legacy-install-cmd：它会额外输出标为 deprecated 的旧全局全 Agent 命令，不能用于新流程。
私密信息与中间数据
- 只读取候选
SKILL.md的 frontmatter 与随技能发布的公开目录、同义词参考；不读私有配置、凭据或客户文件。 - 查询结果只输出 stdout，不写缓存、日志或运行时状态。
- 路径仅用于当前宿主读取
SKILL.md；回执不复制私有路径。
日志与完成回执
回执说明查询词、扫描范围、项目/全局命中、候选数、选择依据，以及是否仍需客户选择安装范围。没有候选时明确返回空列表，不猜造技能名。
完成：已为“<需求>”定位 <技能名>。
日志摘要：项目/全局/生态目录命中 <数量> 个；选择依据为 <关键词或领域>。
下一步：已读取 <SKILL.md 路径> / 等待客户确认 <project|global>、<agents>、<skill|domain|all>。
检索与加载契约
- 从客户需求提取 1–3 个高区分度词；可直接使用中文短语。词组与同义词由 references/query-hints.json 维护。
auto范围下，若--project或当前工作目录可确定项目，扫描<project>/.agents/skills；否则只检索公开目录，并标记selection_required。global或both只在显式请求时扫描用户全局真源。项目与全局同时命中同一技能时按 realpath + skill name 去重，项目优先。- 本地与公开目录候选一起排序；本地匹配不再短路隐藏其他高相关候选。
- 只对已安装候选返回优先
path；以installed_scopes、source_scope表示来源。实际读取该SKILL.md后才算加载。 - 未安装候选返回
source和install_selection。如果scope或agents未选，Agent 必须问客户；不能执行安装、同步或发布。只有完整计划已展示影响并获客户明确写入批准，才可传递给下游 owner 而不重复询问；仅有选择信息时仍进入安装确认门。 install_selection.target.kind默认skill，同时声明客户可选的domain和all。全量仅在客户明确选择后交给对应 owner 处理。
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.
- 3d ago Changed · +14 tokens per session bdc16cd8549a
- 7d ago Changed · +10 lines · -49 tokens per session ab98bd359d6d
- 12d ago First seen · 114 lines · 83 tokens per session scan A 26eeca4b4247
soia-meta-find-skill is a skill published in the GitHub repository soia-team/soia-open-skills (5 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,762 once invoked, about $0.0002 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
validate
Check that an Open Knowledge Format (OKF) bundle is conformant with the v0.2 spec (§11). Use when asked to validate, lint, or check an OKF bundle, or before committing changes to one. Runs a deterministic Python checker — not an eyeball pass. Also migrates a v0.1 bundle to v0.2 in place with --migrate.
memex-sync
Sync Zettelkasten cards across devices via git.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
raytsystem-watch
Inspect video, audio, or supplied transcripts through raytsystem Tool Hub and return evidence-bound speech, visual, OCR, action, transition, and timeline findings. Use for /watch, a YouTube/Loom/public Zoom/direct media URL, a local video or audio file, a transcript, or requests such as "watch this video", "analyze…
research-workflow-orchestrator
Run a resumable end-to-end research workflow that automates low-risk work, pauses at explicit human decision gates, records provenance, and routes each stage to the appropriate research-hub skill or MCP tool.
literature-triage-matrix
Turn a list of papers (Zotero collection, Obsidian cluster, manual list) into a compact comparison matrix written to .research/literaturematrix.md, instead of generic per-paper summaries. Use when the user asks to "make a literature matrix", "compare these papers by method/data/limitations", or "decide which papers…