speckit-resume
Resume an interrupted session by detecting feature state and suggesting the next command
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Resume an interrupted session by detecting feature state and suggesting the next command
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Autonomous SpecKit workflow executor. Reads a populated workflow file and executes all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "execute workflow", "autonomous speckit", or has a workflow file ready for execution.
Autonomous SpecKit workflow executor. Reads a populated workflow file and runs all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "execute workflow", "autonomous speckit", "autonomous execution", "kick off autopilot", "start the autonomous pipeline", "drive it through all the SDD phases", "run the whole thing autonomously", "full end-to-end speckit run", or hands over a populated SPEC-NNN-workflow.md file for end-to-end execution. Requires SpecKit CLI installed, constitution created, and a populated workflow file. Not for SDD methodology questions ($speckit-coach), pre-spec scoping ($grill-me), new-spec setup ($speckit-scaffold-spec), status checks ($speckit-status), or PR comment resolution ($speckit-resolve-pr).
Autonomous SpecKit workflow executor. Reads a populated workflow file and runs all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "execute workflow", "autonomous speckit", "autonomous execution", "kick off autopilot", "start the autonomous pipeline", "drive it through all the SDD phases", "run the whole thing autonomously", "full end-to-end speckit run", or hands over a populated SPEC-NNN-workflow.md file for end-to-end execution. Requires SpecKit CLI installed, constitution created, and a populated workflow file. Not for SDD methodology questions ($speckit-coach), pre-spec scoping ($grill-me), new-spec setup ($speckit-scaffold-spec), status checks ($speckit-status), or PR comment resolution ($speckit-resolve-pr).
Autonomous SpecKit workflow executor. Reads a populated workflow file and executes all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "execute workflow", "autonomous speckit", or has a workflow file ready for execution.
Archive a merged SpecKit spec and clean active workflow residue after the implementation PR has merged. Use after confirming merge provenance, when the user asks for post-merge SpecKit archive hygiene, cleanup hygiene, or removal of completed specs from active specs.
Archive a merged SpecKit spec, remove completed active specs, refresh roadmap and project-memory state, and prepare the cleanup PR after merge.
| name | speckit-resume |
| description | Resume an interrupted session by detecting feature state and suggesting the next command |
| compatibility | Requires spec-kit project structure with .specify/ directory |
| metadata | {"author":"github-spec-kit","source":"speckit-utils:commands/resume.md"} |
$ARGUMENTS
Resume an interrupted SDD session by scanning the project for active features, detecting their completion state, and generating a prompt to continue work.
Locate the .specify/ directory to identify the project root. If not found, error: "No spec-kit project found. Run specify init first."
Scan the specs/ directory for feature directories (numbered directories like 001-auth, 002-dashboard).
For each feature directory, detect state by checking for these files:
spec.md - specification exists and is non-emptyplan.md - implementation plan exists and is non-emptytasks.md - task breakdown existschecklists/ - quality checklists existIf tasks.md exists, parse checkbox items:
- [x] or - [X] = completed- [ ] = remainingCount total tasks, completed tasks, and extract remaining task descriptions.
| Condition | Phase | Next Command |
|---|---|---|
No spec.md or empty | specify | /speckit.specify |
spec.md exists, no plan.md | plan | /speckit.plan |
plan.md exists, no tasks.md | tasks | /speckit.tasks |
tasks.md exists, some incomplete | implement | /speckit.implement |
| All tasks complete | complete | Review and finalize |
If $ARGUMENTS specifies a feature name or number (e.g., 001-auth or auth), filter to that feature only.
For each active (non-complete) feature, output:
Feature: {name}
Status: {spec ✓/✗} {plan ✓/✗} {tasks ✓/✗}
Phase: {phase}
Progress: {completed}/{total} tasks complete
Next step: Run `/{next_command}`
If tasks remain, list the first 3 remaining tasks:
Remaining tasks:
1. {task description}
2. {task description}
3. {task description}
If all features are complete:
All features are complete. Review and finalize the project.
Output the resume prompt. If --copy was passed as an argument, mention that the prompt can be copied to clipboard.