An end-of-session ritual tool that closes tasks, verifies work, and prepares the repository for the next contributor.
Install
mkdir -p .claude/skills/landing && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/9525" && unzip -o skill.zip -d .claude/skills/landing && rm skill.zipInstalls to .claude/skills/landing
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.Key capabilities
- →Verify code quality and tests
- →Group commits logically
- →File follow-up tasks
- →Push code to remote repository
How it works
The tool executes a final verification, commits changes, and pushes to the repository to ensure a clean, deployable state for future work.
Inputs & outputs
When to use landing
- →Closing finished tasks at the end of a session
- →Running final verification before pushing code
- →Grouping commits logically for better history
- →Filing new follow-up tasks for the next session
About this skill
Use the verbatim prompt at .flywheel/prompts/landing.md.
Checklist:
- New beads filed in
.beads/beads.jsonlfor every thread of follow-up work. -
verifyskill passes (format, lint, typecheck, build, tests). - Closed beads updated with a one-line
closed_reason. - Commits are logically grouped with detailed messages, each
referencing bead ids (
fg-12: ...). - No ephemeral files committed.
-
git pull --rebase && git push;git statusclean. - One-line session report: beads closed, beads opened, test count delta, next-session kick-off hint.
Success = a future swarm can pick up the project using only
.beads/beads.jsonl, AGENTS.md, and FLYWHEEL.md.
When not to use it
- →When the work session is not finished
Prerequisites
Limitations
- →Work is not considered complete until git push succeeds
How it compares
It enforces a formal end-of-session ritual that guarantees the repository is left in a state ready for the next agent swarm.
Compared to similar skills
landing side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| landing (this skill) | 0 | 3mo | No flags | Beginner |
| jira | 11 | 6mo | No flags | Beginner |
| triaging-issues | 5 | 2mo | Review | Intermediate |
| ck | 0 | 1mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by hoangsonww
View all by hoangsonww →You might also like
jira
davila7
Use when the user mentions Jira issues (e.g., "PROJ-123"), asks about tickets, wants to create/view/update issues, check sprint status, or manage their Jira workflow. Triggers on keywords like "jira", "issue", "ticket", "sprint", "backlog", or issue key patterns.
triaging-issues
pytorch
Triages GitHub issues by routing to oncall teams, applying labels, and closing questions. Use when processing new PyTorch issues or when asked to triage an issue.
ck
wanzicong
Claude Code 的每个项目持久化记忆。在会话启动时自动加载项目上下文，通过 git 活动追踪会话，并写入原生记忆。命令运行确定性的 Node.js 脚本——行为在不同模型版本间保持一致。
issue
siculo
>
project-state-init
luck7x
初始化 Codex 项目“项目记忆/状态管理”套件到当前项目根目录：复制 `AGENTS.md` 与 `.codex/skills/*`（handoff / handoff-resume / ops-sync 等）并可选生成 `.codex/state` 骨架。用于新项目快速启用长期项目工作流（ops-sync、handoff、审计）。
gsd-ns-manage
rafaelribeiro96
config workspace | workstreams thread update ship inbox