Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Inspect and optionally remove completed Doradb task worktrees and their local branches with deterministic safety checks.
Install Task Prune
$ npx skills add jiangzhe/doradb --skill task-prune -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jiangzhe/doradb task-prune --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jiangzhe/doradb.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/task-prune .claude/skills/task-prune && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "task-prune" agent skill from https://github.com/jiangzhe/doradb/tree/main/.agents/skills/task-prune into .claude/skills/task-prune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-prune", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jiangzhe/doradb/tree/main/.agents/skills/task-pruneType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jiangzhe/doradb --skill task-prune -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jiangzhe/doradb task-prune --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiangzhe/doradb.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/task-prune .agents/skills/task-prune && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "task-prune" agent skill from https://github.com/jiangzhe/doradb/tree/main/.agents/skills/task-prune into .agents/skills/task-prune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-prune", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jiangzhe/doradb --skill task-prune -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jiangzhe/doradb task-prune --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiangzhe/doradb.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/task-prune .cursor/skills/task-prune && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "task-prune" agent skill from https://github.com/jiangzhe/doradb/tree/main/.agents/skills/task-prune into .cursor/skills/task-prune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-prune", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jiangzhe/doradb.git --path .agents/skills/task-prune--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jiangzhe/doradb --skill task-prune -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jiangzhe/doradb task-prune --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiangzhe/doradb.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/task-prune .gemini/skills/task-prune && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "task-prune" agent skill from https://github.com/jiangzhe/doradb/tree/main/.agents/skills/task-prune into .gemini/skills/task-prune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-prune", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jiangzhe/doradb task-pruneInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jiangzhe/doradb --skill task-prune -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jiangzhe/doradb.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/task-prune .github/skills/task-prune && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "task-prune" agent skill from https://github.com/jiangzhe/doradb/tree/main/.agents/skills/task-prune into .github/skills/task-prune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-prune", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jiangzhe/doradb --skill task-prune -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jiangzhe/doradb task-prune --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jiangzhe/doradb.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/task-prune .opencode/skills/task-prune && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "task-prune" agent skill from https://github.com/jiangzhe/doradb/tree/main/.agents/skills/task-prune into .opencode/skills/task-prune/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-prune", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
task-prune- GitHub stars
- 121
- Token cost
- ~551 tokens
- SKILL.md length
- 235 words
- Files
- 2
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Inspect and optionally remove completed Doradb task worktrees and their local branches with deterministic safety checks.
- Works in 7 steps: Start with a dry run → Require the output to list all worktrees… → Exclude the main worktree with reason… → …
- Listing cleanup candidates
- SKILL.md covers Required Flow and Removal Boundary
- Calls git
What it does
Task Prune is an agent skill from jiangzhe/doradb. Inspect and optionally remove completed Doradb task worktrees and their local branches with deterministic safety checks. Use when listing cleanup candidates or pruning clean task worktrees marked implemented both locally and on origin/main, from the main dispatch checkout; never delete remote branches.
Its SKILL.md is about 550 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Development, covering Git worktrees. The repository describes itself as: DoraDB - Async Rust storage engine. The licence is Apache-2.0.
When your agent uses it
- Listing cleanup candidates
- Pruning clean task worktrees marked implemented both locally and on origin/main
- From the main dispatch checkout
- Never delete remote branches
Example prompts
- “/task-prune”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Start with a dry run
- Require the output to list all worktrees before any removal decision.
- Exclude the main worktree with reason main_dispatch_branch.
- Inspect every non-main worktree under .worktrees/ whose basename is a
- Mark a worktree safe only when all conditions hold
- Report candidates under safe_to_purge, unfinished, and excluded, with
- Apply removal only after explicit user intent
What it can do on your machine
Read from SKILL.md and the folder at commit 3291b68. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Task Prune loads about 551 tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 235 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jiangzhe/doradb at commit 3291b68, republished under its Apache-2.0 licence (© jiangzhe). 235 words, ~551 tokens.
Download SKILL.mdSave it as
.claude/skills/task-prune/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- task-prune
- description
- Inspect and optionally remove completed Doradb task worktrees and their local branches with deterministic safety checks. Use when listing cleanup candidates or pruning clean task worktrees marked implemented both locally and on origin/main, from the main dispatch checkout; never delete remote branches.
Task Prune Workflow
Use this skill only from the main dispatch worktree. The underlying tool calls
this operation purge-worktrees; keep that command name unchanged.
Required Flow
- Start with a dry run:
tools/task.rs purge-worktrees- Require the output to list all worktrees before any removal decision.
- Exclude the
mainworktree with reasonmain_dispatch_branch. - Inspect every non-main worktree under
.worktrees/whose basename is a six-digit task id, using that worktree's owndocs/tasks/<task-id>-*.mddocument. - Mark a worktree safe only when all conditions hold:
- its matching task document has
status: implemented; - the worktree is clean;
- exactly one matching
docs/tasks/<task-id>-*.mddocument onorigin/mainhasstatus: implemented; - it contains no other registered worktree.
The task document on
origin/mainis the completion authority; neither a same-name remote task branch nor local-tip ancestry is required. Apply mode refreshesoriginbefore checking eligibility; dry runs use locally available refs.
- its matching task document has
- Report candidates under
safe_to_purge,unfinished, andexcluded, with reasons for every non-safe worktree. - Apply removal only after explicit user intent:
tools/task.rs purge-worktrees --applyRemoval Boundary
Apply mode may act only on direct children of the dispatch root matching
.worktrees/<six-digit-task-id>. It may remove only:
- the local worktree via
git worktree remove; - the local branch via
git branch -D.
Never delete a remote branch. Treat missing task documents, non-implemented
status, dirty worktrees, missing origin/main, missing or ambiguous task documents
on origin/main, non-implemented status on origin/main, or nested registered
worktrees as hard reasons to retain the worktree.
© jiangzhe, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .agents/skills/task-prune of jiangzhe/doradb.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 3291b68
Compare with similar skills
Task Prune next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Task Prune this skilljiangzhe/doradb | 121 | — | ~551 | Automated safety check: Pass | Apache-2.0 | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Migrate Core Code to Submodulestinyhumansai/openhuman | 42k | — | ~2.6k | Automated safety check: Pass | GPL-3.0 | |
| Finishing A Development Branchfarm-fe/farm | 5.6k | 34 repos | ~1.8k | Automated safety check: Pass | MIT | |
| Git Worktree Cleanuplobehub/lobehub | 83k | — | ~2.8k | Automated safety check: Pass | Custom licence | |
| Keep Codex Fastvibeforge1111/keep-codex-fast | 1.6k | — | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
Finishing A Development Branch
farm-fe/farm
A skill your agent uses when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for…
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
Keep Codex Fast
vibeforge1111/keep-codex-fast
A skill your agent uses when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state.
Pre-Release PR Triage
jamiepine/voicebox
Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.
More from jiangzhe/doradb
All 10 skills in this repoBacklog
jiangzhe/doradb
Manage backlog todo documents in docs/backlogs with deterministic tooling.
Issue Rfc
jiangzhe/doradb
Create and list GitHub Issues for Doradb RFC documents with deterministic scripts.
Issue Task
jiangzhe/doradb
Create and list GitHub Issues for Doradb task documents with deterministic scripts.
Rfc Create
jiangzhe/doradb
Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals.
Rfc Resolve
jiangzhe/doradb
Resolve completed or superseded Doradb RFC programs after implementation tasks, tests, review, and verification are complete.
Style Audit
jiangzhe/doradb
Audit branch-diff Rust files, or explicitly requested file/directory Rust targets, for Doradb coding style using deterministic tooling and concise read-only review.
Related
Categories
Questions about Task Prune
What does Task Prune do?
Inspect and optionally remove completed Doradb task worktrees and their local branches with deterministic safety checks. Task Prune is an agent skill from jiangzhe/doradb. Inspect and optionally remove completed Doradb task worktrees and their local branches with deterministic safety checks.
When should I use Task Prune?
Task Prune fits situations like: listing cleanup candidates; pruning clean task worktrees marked implemented both locally and on origin/main; from the main dispatch checkout; never delete remote branches.
How do I install Task Prune in Claude Code?
Run `npx skills add jiangzhe/doradb --skill task-prune -a claude-code`. Or copy the skill folder (.agents/skills/task-prune in jiangzhe/doradb) into .claude/skills/task-prune in your project. Claude Code loads it when a task matches its description.
How do I install Task Prune in Codex?
Run `npx skills add jiangzhe/doradb --skill task-prune -a codex`. Or copy the skill folder (.agents/skills/task-prune in jiangzhe/doradb) into .agents/skills/task-prune in your project. Codex loads it when a task matches its description.
Can I use Task Prune in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jiangzhe/doradb --skill task-prune -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-prune, .gemini/skills/task-prune, .github/skills/task-prune and .opencode/skills/task-prune in your project.
What does Task Prune need to run?
Going by SKILL.md and its folder, Task Prune needs the command-line tools its instructions call (git).
Does Task Prune access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Task Prune safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Task Prune use?
Task Prune is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Task Prune use?
About 551 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Task Prune?
Skills that share tags, products or a category with Task Prune: Finishing a Development Branch (obra/superpowers, 296k stars), Migrate Core Code to Submodules (tinyhumansai/openhuman, 42k stars), Finishing A Development Branch (farm-fe/farm, 5.6k stars) and Git Worktree Cleanup (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Task Prune?
jiangzhe (a GitHub user) maintains it in jiangzhe/doradb, which has 121 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 5, 2026.
Source: jiangzhe/doradb on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.