Automated summary
Automates the wrap-up of an expedition by chaining tests, commit, push, pull request creation and kanban status update.
Strengths
- Sequences end-of-task steps safely: tests run before the commit and a failure stops the workflow.
- Built-in traceability: the expedition ID shows up in the commit message, the PR body and the kanban move.
- Updates the status (review or done) so other agents can see the work is ready.
- Finishes by suggesting the next ready items via `yurtle-kanban list --status ready`.
Limitations
- Model invocation is disabled (`disable-model-invocation: true`), so the command must be triggered explicitly.
- Tightly coupled to the `yurtle-kanban` tool, expedition branches and a `brain/`-style test layout.
- Does not handle rebases, merge conflicts or push failures, which require manual intervention.
Use it when an expedition is finished and you want tests, commit, push, PR and kanban update handled in one command.
Avoid it on a repo without yurtle-kanban or expedition conventions, or while untested changes still need manual rework.
Security analysis
CautionThe skill uses powerful tools (git, gh) for legitimate development workflow purposes but includes commands that push to remote and create PRs, which can affect shared infrastructure. No destructive or exfiltrating commands are present, but the broad git add -A and direct push warrant caution.
- •Uses git push and gh pr create, which modify remote repositories and could publish unintended changes if not reviewed.
- •git add -A stages all changes without specifying files, risking accidental inclusion of sensitive or unrelated files.
- •Automates commit and push operations that could propagate mistakes to shared branches.
Examples
/done EXP-042Finish the current expedition: run the relevant tests, commit with the expedition reference, push, open the PR, and move EXP-017 to review./done — the change is fully tested and self-contained, so move the expedition straight to done and show me the next three ready items.name: done description: Complete current expedition - run tests, commit, push, and update kanban status disable-model-invocation: true allowed-tools: Bash(yurtle-kanban *), Bash(git *), Bash(pytest *), Bash(python3 *), Bash(gh *) argument-hint: "[EXP-XXX]"
Complete Work
Finish the current expedition: run tests, commit changes, push to remote, and update kanban status.
Steps
1. Identify Current Work
# Check current branch
git branch --show-current
# Check in-progress items
yurtle-kanban list --status in_progress
If $ARGUMENTS provided, use that expedition. Otherwise, infer from branch name or ask.
2. Run Tests
Run appropriate tests based on what was changed:
# Unit tests for modified modules
pytest brain/MODULE/tests/ -v
# Integration tests if applicable
pytest brain/tests/ -v -k "integration"
# Live being tests if applicable (CLI-first)
pytest live-being-tests/test_*.py -v
Report test results. If tests fail, DO NOT proceed - fix issues first.
3. Commit Changes
# Check what's changed
git status
git diff --stat
# Stage and commit with expedition reference
git add -A
git commit -m "feat(exp-XXX): Brief description
- What was implemented
- Key changes
Co-Authored-By: Claude <noreply@anthropic.com>"
4. Push to Remote
git push origin HEAD
4b. Version Check (for significant changes)
If this work adds features or fixes bugs, consider bumping the version:
# Check current version
grep version pyproject.toml | head -1
# For bug fixes: bump patch (1.1.0 → 1.1.1)
# For new features: bump minor (1.1.0 → 1.2.0)
# For breaking changes: bump major (1.1.0 → 2.0.0)
If version bump is appropriate, use /release patch after merging to main.
5. Create PR (required for expedition branches)
Create PR so other agents can see the work is ready for review:
gh pr create --title "feat(exp-XXX): Title" --body "## Summary
- What this PR does
## Test Plan
- How it was tested
## Expedition
EXP-XXX: [Title]"
6. Update Kanban Status
IMPORTANT: This makes the work visible to other agents (e.g., Agent A checking for reviews):
# Move to review (for changes needing review)
yurtle-kanban move EXP-XXX review
# Or if self-contained, fully tested, and ready to merge:
yurtle-kanban move EXP-XXX done
7. Show Next Work
yurtle-kanban list --status ready --limit 3
Suggest the next highest-priority item.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/complete-current-expedition-mmh8qqz9/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/complete-current-expedition-mmh8qqz9' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/complete-current-expedition-mmh8qqz9/download' --output '.skill-downloads/complete-current-expedition-mmh8qqz9/SKILL.md.part' && mv '.skill-downloads/complete-current-expedition-mmh8qqz9/SKILL.md.part' '.skill-downloads/complete-current-expedition-mmh8qqz9/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
Tools declared by the author (check availability in your agent): Bash(yurtle-kanban *), Bash(git *), Bash(pytest *), Bash(python3 *), Bash(gh *)
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/complete-current-expedition-mmh8qqz9/SKILL.md' && test -s '.skill-downloads/complete-current-expedition-mmh8qqz9/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/done' && cp -R '.skill-downloads/complete-current-expedition-mmh8qqz9' '.claude/skills/done'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/complete-current-expedition-mmh8qqz9'openskills read 'complete-current-expedition-mmh8qqz9'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/complete-current-expedition-mmh8qqz9/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.