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 bleakbelladonnals/asr-transcription-skills --skill srt-to-review-blueprintgit clone --depth 1 https://github.com/bleakbelladonnals/asr-transcription-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/bleakbelladonnals/asr-transcription-skills/srt-to-review-blueprint)<a href="https://agentmods.dev/skills/bleakbelladonnals/asr-transcription-skills/srt-to-review-blueprint"><img src="https://agentmods.dev/badge/skills/bleakbelladonnals/asr-transcription-skills/srt-to-review-blueprint/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/bleakbelladonnals/asr-transcription-skills/srt-to-review-blueprint"><img src="https://agentmods.dev/badge/skills/bleakbelladonnals/asr-transcription-skills/srt-to-review-blueprint.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 | $0.00119 | $0.04053 |
| Opus 5.5 | $0.00048 | $0.01621 |
| Sonnet 5.5 | $0.00024 | $0.00811 |
| Haiku 4.5 | $0.00012 | $0.00405 |
Grade A, and why
srt-to-review-blueprint 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 1mo 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
录音转蓝本（SRT → 课后复习蓝本）
何时使用
- 用户有一批按时间顺序命名的课程/会议录音转写 SRT，转写质量差（同音错字、碎片块、无标点、无说话人）
- 用户同时有课堂笔记（结构化骨架）和/或面试旁听笔记（点评要点），要求纠错并整理成可复习、可补笔记的蓝本
- 交付物：一份"整体复习版" + 一份"笔记补丁版"，绝不修改任何原文件
输入与输出
- 输入：N 个 SRT（按文件名时间顺序）+ 课堂笔记.md +（可选）旁听笔记.md
- 输出目录：
<日期>-蓝本/，内含：整体蓝本.md：按课堂议程组织的完整复习文档笔记补丁.md：可粘贴进课堂笔记对应小节的增量片段面试旁听补充.md（仅当有面试录音段）：对旁听笔记的增量补充存疑清单.md：所有未决项，不确认完不算交付完成
核心流程
Step 0 预处理（脚本，不用 LLM）
运行 scripts/preprocess_srt.py：
python3 scripts/preprocess_srt.py "08-06 morning.srt" "08-06 afternoon1.srt" "08-06 afternong2.srt" -o 清洗后语料.md
- 剥掉文本行首内嵌时间戳（转写工具残留，如
00:00:01,080细节） - 去空块/纯序号块；合并碎片块（≤8 字且与前块时间重叠或间隙 ≤1.5s 的并入前块）
- 每行一个合并块，行首锚点
【morning#123】（文件名+原始块号），供存疑清单精确定位 - 检查统计：微块占比应大幅下降（典型：53% → <15%），否则调合并参数
- ⚠️ SRT 时间轴常互相重叠（同一语音流反复切分），顺序以文件内块序和文件名为准，不要按时间轴重排
Step 0.5 转写来源格式变体（先识别再清洗，2026-08 实测）
- 飞书妙记：标准 SRT，无说话人标记 → 直接可用
- 钉钉听记：文本行首带内嵌时间戳（
00:00:02,760推动），清洗正则re.sub(r'^\d{2}:\d{2}:\d{2},\d{3}\s*', '', line) - 通义听悟：导出是纯文本段落，无任何时间戳 → 无法时间轴定位，锚点退化为段落序号
- 讯飞听见：不支持 OGG；普通会员不能上传音频文件 → 录音豆/录音卡的 ogg 素材走不通
- ⚠️ 同一时段多设备录音的时间轴不可互相对齐：实测同时段两录音前段错位 4~5 分钟、后段对齐（启动差异/智能暂停），跨文件定位用内容锚点（独特短语）+ 文件名块序，不要用时间戳
- 转写来源质量怎么选/怎么比：见
transcription-quality-evaluation技能
Step 1 建权威骨架
- 从课堂笔记提取标题树 → 每个骨架节点标注"录音定位关键词"（如 Step3 算成本 ↔ 录音中"拉候选池"段）
- 从旁听笔记提取点评要点清单 → 锚定面试录音的点评段
- ⚠️ 笔记也可能带错（如模型名拼写），笔记是锚点不是唯一事实源；录音与笔记冲突时标出冲突，交用户裁决
Step 2 分块
- 先用关键词扫描定位主题边界（候选池/评测/成本/文章/作业…首现位置），结合笔记骨架节点切分清洗后语料
- 每批 2000~3000 字（质量最优粒度；4 万字一次处理必漏错），超 4000 字的主题段再拆
- 切块前检查重复转写：同一段话常被转写两遍（如 morning #110
112 与 #126128），合并去重后再切 - 每块 = 原文片段 + 对应笔记小节 + 按块定制的术语表 + 输出模板 + 纠错规则，封装成独立任务；错词模式与实测术语表见
references/转写纠错模式与术语表.md - 试点切块表与实测错词表见
references/pilot-morning-2026-08-06.md
Step 3 subagent 分发（减少主上下文负担）
- 主会话只做编排：预处理 → 切块 → 分发 → 收集 → 校验，原文 8 万字不进主上下文
delegate_task并行分发，每 subagent 只处理自己的块（leaf 角色），context 必须显式包含：- 本块原文（带锚点）
- 对应笔记小节全文
- 术语表
- 输出模板（见 templates/subagent-task.md）
- 纠错规则 + 闲聊界定 checklist
- 并行上限 3，块数多于 3 时分轮
- 主会话校验（subagent 自报不可全信）：术语表 grep（未纠错术语残留检查）、数字抽查、骨架对账
- 增量保存纪律：每批结果一到就写盘（分章节稿-部分.md / 章节-N.md），不要等全部回收再拼；subagent 散落文件统一移入
<蓝本>/subagent暂存/，核对内容与已存结果冗余后再删
What ships with it
5 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.
- 1mo ago First seen · 151 lines · 119 tokens per session scan A e54d4f8738c3
srt-to-review-blueprint is a skill published in the GitHub repository bleakbelladonnals/asr-transcription-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 119 tokens to every session and 4,053 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.