本文へ移動
cccskills
無料GitHub で公開

gate-push

Single-verb branch-to-PR quality gate pipeline. Use when the user wants to gate, push, and open a PR for a branch in one command.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.4 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。

Load dh:dh-cli-usage before using <sam_cli/> or <dh_scripts/>.

Gate Push

Run /dh:gate-push <branch-name> to resolve branch context into a /dh:complete-implementation input and execute that quality-gate pipeline.

Required input

  • branch_name = $ARGUMENTS (must be non-empty)

If empty: stop with:

COMPLETION BLOCKED — Missing required argument <branch-name>.

Then re-run:
/dh:gate-push <branch-name>

Branch → backlog lookup algorithm

  1. Normalize branch_name into a lookup slug:
    • Strip leading branch type prefix when present (feature/, fix/, chore/, etc.) by removing only the prefix up to and including the first / character
    • Then replace any remaining /, _, and - with spaces (for example feature/auth/login-fix → auth login fix)
    • Trim whitespace
    • Store the result as normalized_slug
    • Expected pattern is type/slug (e.g., feature/foo-bar); multi-segment branches (type/segment1/segment2) are supported and normalize with the same replacement rule
  2. Strategy 1 (title match):
    • <sam_cli/> backlog list --title "<normalized_slug>"
  3. Strategy 2 (topic match fallback, only if Strategy 1 has zero results):
    • <sam_cli/> backlog list --topic "<normalized_slug>"
  4. If exactly one item is returned, use it as match.
  5. If multiple items are returned, do not guess — stop and follow the No-match / unresolved fallback procedure below.

Resolve complete-implementation input

From match, resolve in this order:

  1. If match.issue exists (issue number field from backlog output) → target = #<match.issue>
  2. Else if match.plan exists and non-empty → target = <match.plan> (use the backlog item's plan field directly)
  3. Else no resolvable target

Execute gate pipeline

If target is resolved:

Skill(skill: "dh:complete-implementation", args: "<target>")

/dh:complete-implementation is the source of truth for the quality-gate phases and final push/PR behavior. Do not duplicate its gate logic here.

No-match / unresolved fallback

If no backlog match is found, a match exists but has neither issue nor plan, or multiple matches are found:

  • Do not prompt mid-loop.
  • Stop with:
COMPLETION BLOCKED — Branch cannot be resolved to a single backlog issue/plan.

Required precondition:
- Ensure branch-to-backlog mapping is decided at workflow start (for example via `/dh:work-backlog-item --auto ...`) or at the start of `/dh:implement-feature`.
- Ensure the matched backlog item has either an issue number or a linked plan.

Then re-run:
/dh:gate-push <branch-name>

Success check

After successful completion, verify PR visibility for the branch.

GitHub backend only — this step requires a GitHub remote configured with the gh CLI. For beads and other non-GitHub backends, skip this step and verify via your backend's native tooling (e.g., bd show <issue-id> for merge-request state).

if gh repo view --json name >/dev/null 2>&1; then
  gh pr list --head <branch-name>
else
  echo "Remote is not a GitHub repository — PR visibility check not applicable for this backend."
fi

Use the original input branch (branch_name), not normalized_slug, for --head.

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

Add automated documentation updater to any Claude skill. Creates a Python sync script that downloads upstream docs, processes markdown for AI consumption, and maintains local cache with configurable refresh. Collects template variables, then delegates implementation through 5-phase workflow. Use when adding auto-updating reference documentation to plugins or skills.

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。

Jamie-BitFlight/claude_skills672026年10月12日 更新

SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feature, or convert an idea into an executable SAM plan.

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。

Jamie-BitFlight/claude_skills672026年10月12日 更新

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

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。

Jamie-BitFlight/claude_skills672026年10月12日 更新

Browser automation for AI agents using the agent-browser CLI and Playwright. Use when navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, logging into sites, or automating any browser task. Triggers on "open a website", "fill out a form", "click a button", "scrape data", "test this web app", "automate browser actions", or any programmatic web interaction request.

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。

Jamie-BitFlight/claude_skills672026年10月12日 更新

Runs the description-drift experiment — spawns all Claude Code agents simultaneously to collect self-reported capabilities, then compares them against static frontmatter descriptions to reveal how reliable orchestrator routing based on descriptions actually is. Use when measuring description drift across the agent fleet, re-running the capability collection experiment, analyzing a specific agent's self-reported capabilities, or auditing whether frontmatter descriptions accurately reflect agent behavior.

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。

Jamie-BitFlight/claude_skills672026年10月12日 更新

Create or adapt Claude Code agent definitions. Use when creating an agent, changing subagent configuration, selecting agent scope, or designing a specialized delegation role.

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。

Jamie-BitFlight/claude_skills672026年10月12日 更新

Jamie-BitFlight のスキルをすべて見る

このスキルの問題を報告する