sdlc-handoff SKILL.md skillA

sdlc-handoff from tscarpe/claude-sdlc-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tscarpe/claude-sdlc-skills/sdlc-handoff@git:20261104.17dcf12

Pins git:20261104.17dcf12 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tscarpe/claude-sdlc-skills
Path
skills/sdlc-handoff/SKILL.md
Versions recorded
2
Latest version
git:20261104.17dcf12, committed Nov 4, 2026
First version recorded
Nov 4, 2026
Size
7,655 bytes
Repository stars
66
License
MIT

Session handoff and takeover that works with any coding agent. 会话交接与会话接手:旧会话上下文将满、或任务要换会话/换机器/换 agent 继续时,把当前任务压缩成一张自足的交接卡(write);新会话读取交接卡并直接继续(resume),覆盖开发、排查、梳理、调研、文档等任意任务。Use when 交接、接手、继续上次的工作、上下文满了、换个会话做、上次做到哪了、pick up where I left off, handoff, resume previous work, context is full. 用法:/sdlc-handoff write|resume|list.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 交接(sdlc-handoff)

> **定位**:上下文将满、或要换会话/换机器/换 agent 时,把「任务做到哪」压成一张**自足的交接卡**;新会话凭卡直接继续,不必重述背景。覆盖开发、排查、梳理、调研、文档任意任务——不限于 SDLC 某一阶段。

**路径基准**:文中 `scripts/...`、`references/...` 一律相对本文件所在目录(技能根目录)解析。

**平台无关**:本 skill 不依赖任何具体 agent 的目录、环境变量、工具名或斜杠行为。脚本无法执行时,按 [manual-collect.md](references/manual-collect.md) 用现有工具采集同样字段;会话记录读不到时,靠交接卡本身继续。

## 三种动作

| 用户意图 | 动作 |
|---|---|
| 「交接一下」「上下文满了」「换个会话做」「换 agent 继续」 | write |
| 「接手」「继续上次」「上次做到哪了」「按这张卡继续」 | resume |
| 「有哪些交接卡」「列一下交接」 | list |
| 同一会话内只是历史太长、任务仍在推进 | 不做交接,用 agent 自带的上下文压缩 |

无参数时给出三选一,不要猜;同时说明「同一会话内只是历史太长」可以不走交接。**list** 即执行 resume 第 1 步的扫描与展示(时间 / 任务 / `status` / `next`)后结束,不进入接手。

长任务不必等上下文将满:每完成一个里程碑都可主动 write 一张存档卡(`status` 按实际填,`prev` 指向上一张)——越接近上下文上限,压缩质量越差。

## write:产出交接卡

1. **空会话不产卡**:本会话无实质工作(无文件改动、无工具调用记录)时直接说明,建议开新会话即可。
2. **采集硬事实**:执行 `bash <技能根>/scripts/collect.sh`。脚本不可执行或环境不支持时,按 [manual-collect.md](references/manual-collect.md) 逐项采集。
3. **补会话外状态**:若工具集提供后台进程/长任务列表,记录仍在运行的项;否则在卡里写明「未检查」。
4. **写卡**:按 [handoff-template.md](references/handoff-template.md) 的 8 段结构落盘到「落盘与命名」约定的位置。collect 输出的 handoffs 段有同任务存续卡时,填 `prev` 并继承其「背景与目标」与未结待办,按现状改写、不凭记忆重写。
5. **自检**(逐条过,不通过就改):
   - 8 段齐全,`next` 是单条可直接执行的下一步
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tscarpe/claude-sdlc-skills/sdlc-handoff@sha256:da06a3c24a7d7c2b

The line at the top of this page pins the label git:20261104.17dcf12, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_4rnvm5shf7zlr2bt.svg)](https://markdownregistry.com/a/art_4rnvm5shf7zlr2bt)

0 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, all committed on Nov 4, 2026.

versioncommittedcommitsizeaudit
git:20261104.17dcf12 latest2026-11-04 17dcf12 7,655 BA view · diff
git:20261104.bf292622026-11-04 bf29262 6,484 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (7655 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

tscarpe/claude-sdlc-skills · 66 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_4rnvm5shf7zlr2bt
GET https://markdownregistry.com/api/v1/resolve?ref=tscarpe/claude-sdlc-skills/sdlc-handoff
GET https://markdownregistry.com/api/v1/blob/da06a3c24a7d7c2b6248803d7600116047f0ef338354ca54f4b5f00e66f6ece4

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from tscarpe/claude-sdlc-skills

CLAUDE.md CLAUDE.md file
tscarpe/claude-sdlc-skills · CLAUDE.md
git:20261104.bf29262 · audit A · 66 stars
sdlc-design SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-design/SKILL.md · Produces the technical design document (design.md) from the confirmed requirement digest: solution alternatives, data…
git:20261105.93b60b6 · audit A · 66 stars
sdlc-doubt SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-doubt/SKILL.md · Adversarially re-checks a non-trivial technical decision in a fresh context by stripping the conclusion and asking an…
git:20261018.62c92c0 · audit A · 66 stars
sdlc-gate SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-gate/SKILL.md · Runs the mandatory risk-tiered review gate after technical design and test cases are finalized: adversarial review by…
git:20261105.93b60b6 · audit A · 66 stars
sdlc-guardrails SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-guardrails/SKILL.md · Deterministic guardrail engine that enforces "write-it-and-it's-wrong" red-lines at write time - a PostToolUse hook…
git:20261018.62c92c0 · audit A · 66 stars
sdlc-intent SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-intent/SKILL.md · Digests and health-checks product requirement documents (PRD). Stage 1 produces a structured digest (roles, concepts…
git:20261104.2dd86a9 · audit A · 66 stars
sdlc-release-check SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-release-check/SKILL.md · Scans the Java + SQL diff between current and baseline branches (master/main), extracting release-time manual actions…
git:20261020.e73c079 · audit A · 66 stars
sdlc-sync SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-sync/SKILL.md · Syncs SDLC artifacts between local markdown workspace and the authoritative web platform: pulls platform…
git:20261105.2f7edc1 · audit B · 66 stars
sdlc-test SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-test/SKILL.md · Orchestrates AI testing: dev-complete verification (health probe + smoke against an externally supplied service), case…
git:20261105.93b60b6 · audit A · 66 stars
sdlc-ui-visual SKILL.md skill
tscarpe/claude-sdlc-skills · skills/sdlc-ui-visual/SKILL.md · Design-to-code visual restoration loop: diffs the running page against a Figma link or baseline image via real…
git:20261018.3265427 · audit A · 66 stars

Every file in tscarpe/claude-sdlc-skills

Browse by kind, by grade A, or by owner.