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 onescience-ai/OneSkills --skill onescience-knowledge-capturegit clone --depth 1 https://github.com/onescience-ai/OneSkillsWrote 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/onescience-ai/oneskills/onescience-knowledge-capture)<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-knowledge-capture"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-knowledge-capture/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/onescience-ai/oneskills/onescience-knowledge-capture"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-knowledge-capture.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 | $0.00099 | $0.04699 |
| Opus 5.5 | $0.00040 | $0.01880 |
| Sonnet 5.5 | $0.00020 | $0.00940 |
| Haiku 4.5 | $0.00010 | $0.00470 |
Grade A, and why
onescience-knowledge-capture 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 25d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OneScience Knowledge Capture
你是 OneScience 的交互经验沉淀执行技能。你的职责是把一次已经完成或阶段性完成的完整交互,转换成可审查、可追踪、可复用的知识贡献。贡献可以是:
knowledge:补充已有 skill / primitive 的知识、边界、失败模式或工作流经验。integration:提出把经验接入 resource、expert 或 executor skill 的结构化变更候选。both:同时生成知识文档和集成候选。
本技能不是自动训练、自动发布或自动改写生产技能的入口。它只生成候选贡献、验证贡献格式,并在用户明确授权时提交 Gitee Issue。
运行环境(跨平台):本文档示例命令统一写作
python;Windows 上通常可直接用python,Linux/macOS 上若无python命令请改用python3(如python3 skills/onescience-knowledge-capture/scripts/submit_gitee_issue.py ...)。本技能的三个脚本(validate_contribution.py、render_issue_payload.py、submit_gitee_issue.py)均为纯标准库实现、无第三方依赖、无平台专有逻辑,在 Windows 与 Linux 上行为一致。其中submit_gitee_issue.py内部已按平台自动选择 gitee-cli 调用方式(Windows 绕过会把多行正文截断的.cmdshim、直接调 node;Linux 走标准gitee命令),调用方无需关心差异。
触发场景
使用本技能处理以下请求:
- “把这次完整对话整理成 OneSkill 知识”。
- “沉淀这次任务的经验,后面优化 skill”。
- “将本次交互转换成 skill 集成文档”。
- “把这个任务过程提交到 OneSkills 仓库或 Gitee Issue”。
- 任务结束后,用户明确要求保存可复用经验、失败案例、提示词模式、资源选择依据或执行改进建议。
不要在以下情况下自动触发:
- 用户只要求普通总结,未要求用于 OneSkill 优化或知识沉淀。
- 交互中包含未脱敏的 API key、密码、访问令牌、个人隐私或私有数据,且无法安全脱敏。
- 只有零散的一句话,没有足够证据区分用户目标、采取的动作和最终结果。
核心边界
- 只消费调用方提供的交互内容、任务状态、已展开的资源内容和执行结果;不能沿资源
path直接读取 primitive 文件。 - 默认不写入
skills/onescience-primitives/assets/,不修改已有SKILL.md,不修改onescience-orchestrator。 - 默认不保存原始逐轮 transcript,只保存经过脱敏的事实、决策和证据摘要。
- 不能把推测写成事实。无法从交互证据确认的内容必须标记为
MISSING、ASSUMPTION或UNVERIFIED。 - 不能把一次性项目细节包装成通用规则。需要说明适用范围、复用条件和不适用场景。
- Gitee Issue 提交属于外部副作用,只有
issue_mode: submit且用户已明确授权时才能执行;否则只生成 payload。 - Issue 提交失败时保留本地贡献文档和 payload,返回可诊断的失败原因,不重复提交。
默认目录和产物
除非 inputs.capture.target_directory 明确指定,贡献写入:
skills/onescience-knowledge-capture/contributions/<domain>/<contribution_id>/
contribution.md # 人工审查和后续知识迁移的主文档
contribution.json # 机器可读元数据、执行/验证轨迹和集成候选
issue_payload.json # issue_mode != none 时生成
submission_card.md # 由 render_issue_payload.py 生成,供人工在 Gitee 网页端复制提交
<domain> 使用 bio、cfd、climate、matchem、general 或 unknown。contribution_id 使用日期加稳定短名,例如 2026-09-07_scanpy_qc_fallback。如果同名目录已存在,不覆盖原文件,应追加 -v2、-v3 等后缀。
What ships with it
11 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.
- contributions/general/2026-09-21_gitee_token_read_export_inheritance/contribution.json 15 KB
- contributions/general/2026-09-21_gitee_token_read_export_inheritance/contribution.md 12 KB
- contributions/general/2026-09-21_gitee_token_read_export_inheritance/issue_payload.json 24 KB
- contributions/general/2026-09-21_gitee_token_read_export_inheritance/submission_card.md 23 KB
- contributions/README.md 966 B
- references/contribution_schema.md 3.8 KB
- references/contribution_template.md 2.4 KB
- references/manual_issue_submission.md 5.2 KB
- scripts/render_issue_payload.py 3.5 KB runs code
- scripts/submit_gitee_issue.py 10 KB runs code
- scripts/validate_contribution.py 4.6 KB runs code
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.
- 25d ago Changed · +7 lines ec251694b9e2
- 26d ago Changed · +22 lines f97939955049
- 29d ago Changed · +2 lines 31fa5027584b
- 1mo ago Changed · +20 lines 3aa991b020ae
- 1mo ago First seen · 240 lines · 99 tokens per session scan A ee3c3533a69b
onescience-knowledge-capture is a skill published in the GitHub repository onescience-ai/OneSkills (23 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 4,699 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-07.
Other skills, from other repositories
contorium-workspace-memory
Use Contorium workspace memory layers (focus, session events, Git, export) when resuming AI work or avoiding repeated project explanation.
locus-memory
Use when the user needs persistent project memory across sessions. Triggers on: "remember this", "what did we decide about...", "show project structure", "what changed recently", "search memory". Do NOT trigger for: ephemeral questions, one-off lookups, file reads that don't need memory.
remember
Save a project decision or context to Locus semantic memory. Use when the user says "remember this", "save this decision", or wants to store architectural context for future sessions.
compact
Clean up old episodic memory entries to free space. Keeps recent sessions intact.
forget
Delete memory entries from Locus matching a search query. Use when the user says "forget this", "delete memory", or "remove that decision".
memory-audit
Audit Locus stored data — shows inventory of structural map, semantic memories, episodic entries, hook captures, DB size, and security status. Use when the user wants to know what data Locus has stored.