resume
Resume a PM-managed project from git, the approval record, the story Execution blocks and the decision log, then continue.
- License 许可
- GPL-3.0
- 所属仓库
- bendusz/bstack
- 最近更新
- 2026-11-15
- Stars
- ★ 3
- Forks
- 1
01 前言 Front Matter
- name
- resume
- description
- Resume a PM-managed project from git, the approval record, the story Execution blocks and the decision log, then continue.
03 SKILL.md 正文
If you were dispatched as a child agent (your task begins 'You are a bstack … child'), do not use this skill.
references/… below means ${CLAUDE_PLUGIN_ROOT}/skills/project-manager/references/…, and
<plugin> in any reference means ${CLAUDE_PLUGIN_ROOT}. Neither is a shell variable: write the
path out in every command.
Run the bstack:project-manager skill's procedure (load that skill first) to resume this project.
Probe the host first; without T3 Code, say so and stop. Then load references/state.md and follow
## Resume: read docs/handoff.md if present, then the approval record, the integration branch's first-parent history, every
story's pm-exec, the worktree list, each recorded thread that is not merged, and the last ~20
lines of docs/log.md, in that order.
Git and the pm-exec lines win over the log.
Summarise where things stand in a few lines: the approval status, the sprint, each claimed story
with its status, rounds, thread, branch and worktree, any Tests: line, any blocker, and the
next step. Present a blocked story to the user before anything else, except one with a
Replaced by: line: that is history, not a blocker. Then continue from each story's status as
## Resume says.
If docs/approval.json is absent, the project has not been planned: say so and start planning
(references/planning.md).
04 同仓库更多 Skills
why
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
unslop
Cut AI tells from any writing. Must always apply.
typescript-best-practices
TypeScript best practices. Use when reading or editing any .ts or .tsx file.
technical-writing
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /poteto:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
teach
Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
reflect
Spawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.