本文へ移動
cccskills
無料GitHub で公開

pr

Push committed changes and create a draft PR on GitHub. Use when you have staged changes ready to push and want to open a draft PR for early feedback or documentation.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md5.2 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

PR

Quickly push changes and open a draft pull request on GitHub.

When to Use

  • You have staged changes ready to push and want to create a draft PR
  • Early feedback needed on work-in-progress
  • Want to document and track changes before final review
  • Need to open a PR for discussion or CI validation

Instructions

Step 1: Verify Staged Changes

Check what will be committed:

git status

Ensure all changes you want are staged with:

git add <files>

Or add everything:

git add .

Step 2: Create Commit Message

Write a clear, conventional commit message. Use the format:

<type>(<scope>): <description>

<optional body with details>

Types: feat, fix, chore, refactor, docs, test, etc.

Examples:

  • feat(registry): add new skill category
  • fix(cli): resolve version mismatch
  • chore: regenerate artifacts

Step 3: Commit Changes

git commit -m "your commit message here"

Step 5: Push to Remote

git push -u origin <branch-name>

If you're on main or pushing to an existing branch:

git push

Step 6: Create Draft PR

gh pr create --draft

This will prompt you for:

  • Title — auto-filled from commit, edit as needed
  • Body — add context, description, or leave blank
  • Assignees — optional
  • Labels — apply by judgement; see Step 7

For multiline descriptions, use a body file with real newlines. Do not pass literal \\n sequences or rely on shell $'...' quoting; malformed quoting can make GitHub display \\n (and sometimes a stray $).

cat > /tmp/pr-body.md <<'EOF'
## Summary

Describe the change here.
EOF
gh pr create --draft --title "Your PR Title" --body-file /tmp/pr-body.md

After creating or editing the PR, verify the stored body:

gh pr view <number> --json body --jq .body

Or specify details inline for a one-line body:

gh pr create --draft --title "Your PR Title" --body "Description here"

Step 7: Apply Labels by Judgement

Labels are how humans and automation triage the PR queue, so choose them deliberately — but never hardcode a fixed label list. Repos define their own labels and rename or retire them over time; a memorized set rots and won't transfer across repos. Instead, read the live set and reason about fit each time.

  1. Read the repo's actual labels (names and descriptions — the description tells you the intended use):

    gh label list --limit 200 --json name,description --jq '.[] | "\(.name) — \(.description)"'
    
  2. Pick the smallest set that is actually true of this PR. Match the diff's substance against label descriptions:

    • What kind of change is it? (bug fix, enhancement, refactor, docs, dependency bump …)
    • What area does it touch? (frontend, backend, CLI, schema, CI …)
    • Does a cross-cutting label genuinely apply? (performance, security, tech-debt …) — only if the PR materially does that, not aspirationally.
    • Is there a state/process label the repo uses for triage or gating? (needs-review, awaiting-assets, blocked …) Apply one only if it reflects reality.
  3. Prefer precision over coverage. Two labels that are exactly right beat five that are loosely related. If nothing fits, apply nothing — a wrong label misroutes triage worse than a missing one.

  4. Skip labels you can't justify. Roadmap/sprint/phase tags, auto-merge eligibility, ownership cosign labels, etc. usually require context the PR author must supply — don't guess them. If a required-by-process label is missing (e.g. the repo gates on a scope or migration-notes label) and you can't satisfy it, say so rather than applying it falsely.

  5. Apply, then confirm:

    gh pr edit <number> --add-label "<label-1>" --add-label "<label-2>"
    gh pr view <number> --json labels --jq '.labels[].name'
    

State briefly why each label was chosen (and note any you deliberately skipped) so the reasoning is auditable.

Tips

  • Accidental staging leakage: if a PR contains unrelated staging changes, do not force-push blindly. Start a clean branch from current origin/main, apply only the intended files, verify git diff --stat origin/main...HEAD, then push and create a replacement draft PR. Close the contaminated PR and cross-reference the replacement in a comment.
  • Draft PRs show as "Draft" and won't trigger auto-merge workflows
  • Rebase before final PR — git rebase -i origin/main to clean up commits
  • Ready to review? — Use gh pr ready to convert from draft to ready-for-review
  • Add more commits — Just push again with git push, the PR updates automatically

Troubleshooting

"fatal: The current branch has no upstream branch"

  • Use git push -u origin <branch-name> on first push

"Permission denied" when pushing

  • Check your git credentials: gh auth status
  • Re-authenticate if needed: gh auth login

PR creation fails

  • Ensure you're in a git repository: git rev-parse --show-toplevel
  • Check GitHub CLI is installed: gh version

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

ci-churn

無料

Measure CI churn cost for a pull request: how many commits and how many CI-compute seconds were burned on avoidable "fix the CI" push rounds. Use when you want to understand the efficiency cost of a PR's iteration cycle, get actionable pre-push check suggestions, or include a churn summary in a pipeline report. Triggers: "ci churn", "how much CI did we burn", "avoidable commits", "ci efficiency", "wasted CI time", "churn report", "/ci-churn". Called automatically by /fp-drift at pipeline close.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

Produce the rendered evidence a human-gated frontend PR owes its reviewer: capture each changed surface (plus the before state for anything modified, plus mobile width), then generate one self-contained local HTML page the founder can open and review without checking anything out. Use when a PR is gated by the "Frontend changes are HUMAN-GATED" section of CLAUDE.md, or when the user says "/design-gate", "screenshot evidence for this PR", "prep this for founder review", "build the design evidence page", "what does this look like before and after". The page comes from a template script, not hand-written markup. Output is session-local and never committed. Do NOT use for non-gated changes: typo/grammar/factual fixes in an unchanged block, dead link targets, alt/ARIA fixes with no visual change, cache-bust bumps, or refactors with no rendered diff.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

One-fix-at-a-time, approval-gated design fix recovery. Given a checklist of fixes (handover doc, CHECKLIST.md, or inline list), applies each individually, presents a diff, and waits for an explicit APPROVE / REJECT / NO CHANGES decision before committing. Trigger phrases: /design-iteration, "go through the checklist one by one", "fix these one at a time", "bucket recovery", "design fix pass".

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

Playbook for correcting a named skill's star level to match its computed Trust Magnitude grade, with an independent post-calibration verification pass and a CLI-logged timeline event (never hand-written). Use when: recalibrating a skill's level, fixing a stale or drifted star rating, running a batch of `gaia dev calibrate` corrections, or confirming a past calibration actually landed. Triggers: "calibrate <skill>", "recalibrate the trust magnitude backlog", "promote/demote <skill> to N stars", "why is <skill> still N stars", "verify a calibration actually landed", "Hall of Heroes ranking is wrong".

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

Close out a completed EPIC / sprint end-to-end: author a fact-verified meta-post announcing what shipped, archive the EPIC's handovers, snapshot orchestrator memory, gate the integration→main merge on CI-green + explicit human go, drive the version bump (merge-commit conventions that auto-sync classifies), and verify the release reached the registry/PyPI. Use when the user says "close out EPIC <n>", "wrap up the sprint", "ship the meta shift", "/epic-close", or asks to finalize an integration branch that is ready to merge to main. Generalizes the EPIC 1002 (Yggdrasil II) close-out. This skill orchestrates — it authors founder docs directly (superadmin) and delegates code/regen to workers; it NEVER merges to main without the human gate.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

Run this skill for Phase 3 of the evidence verification pipeline — the adversarial audit step. Use when you need to check the evidence data lake for bad data before ingestion: dead links, wrong URL formats (tree/ vs blob/), subjective wording ("elite", "high-quality"), stale migration notes, benchmark catalog misuse/vendor-claim leakage, or skills whose star evidence conflicts with classified evidence level. Triggers on phrases like: "audit the data lake", "adversarial check", "ev-adversarial-audit", "check for noise in evidence", "flag bad evidence", "run the audit phase", "quality check the by-type files", or any reference to Phase 3 of the pipeline.

日本語の概要は準備中です。原文の説明を表示しています。

gaia-research/gaia-skill-tree232026年10月13日 更新

gaia-research のスキルをすべて見る

このスキルの問題を報告する