ai-toolkit-rules
Mandatory engineering, security, testing, git, performance, quality, and response rules.…
Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
$ npx -y skills add softspark/ai-toolkit --skill pr --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/prContext preview
The summary Claude sees to decide when to auto-load this skill.
Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge.
name: pr description: "Creates GitHub PR after pre-flight checks (lint/typecheck/tests), structured summary from commits. Triggers: pr, pull request, create PR, ready to merge." effort: medium disable-model-invocation: true argument-hint: "[title or branch]" allowed-tools: Bash, Read, Grep
$ARGUMENTS
Create or update the task's GitHub pull request after project-specific checks. When called by `/autonomous-dev`, preserve its run ID, branch, PR identity, approval history and evidence. This skill publishes the PR; the calling process owns subsequent review, QA and required-CI completion.
an existing PR first, then project configuration or the remote default branch. Do not assume a branch named `main` exists.
/pr [title]
Generate a structured PR summary from the commit history before writing the PR description:
python3 ${CLAUDE_SKILL_DIR}/scripts/pr-summary.py [base_branch]
# Pass the resolved PR base explicitly, for example develop.The script outputs JSON with:
Use the output to populate the PR template fields below.
---
Read the project's instructions, CI configuration and package/Make scripts. For an autonomous run, use the commands frozen in its plan from `.ai-toolkit/autonomous.json`. Run the actual lint, typecheck, test and build commands applicable to that project; a Python command is not a universal gate. Inspect every result and preserve evidence of the tested commit. Missing runtime services or failed commands are blockers, never successful checks.
Verify that the authorized changes are committed, the intended base exists, and the diff contains only the task's work. Use the resolved base with a triple-dot diff for PR scope. Preserve unrelated dirty work and report it.
Verify the repository and active account. Search for an existing PR from the exact head branch before creation, including after an interrupted publication. Update that PR when it represents this task. Never open a duplicate merely because a previous assistant message omitted its URL.
Use the repository's template and write the exact body with an editing tool to an absolute temporary file outside the checkout. Pass it through a structured connector argument or `gh --body-file`, preserving real newlines. For example, with actual repository/branch values and the prepared body file:
gh pr create --base develop --head feat/csv-export --title "feat: export filtered orders" --body-file /absolute/run/pr-body.md
Publishing must already be authorized by the task and allowed by the current host. A missing permission leaves a prepared, reviewable result and a concrete blocker. Creating a PR does not authorize merging it. Record the returned URL immediately in the autonomous run before continuing.
## Summary <1-3 bullet points describing changes> ## Changes - [ ] Feature implementation - [ ] Tests added/updated - [ ] Documentation updated ## Test plan - [ ] CI checks pass (lint, typecheck, tests) - [ ] Manual testing completed - [ ] No regressions ## Screenshots <if applicable>
Before creating PR:
# View PR gh pr view # Check PR status gh pr checks # Inspect the current head and review state gh pr view --json url,headRefOid,baseRefName,reviewDecision,mergeStateStatus
Report pending conditions; `/autonomous-dev` waits for them before completion.
substituting a hardcoded branch name.
AI coding toolkit with machine-enforced safety, 116 skills, 44 agents, lifecycle hooks, persona presets, opt-in plugin packs, and benchmark tooling.
Repo: softspark/ai-toolkit
Mandatory engineering, security, testing, git, performance, quality, and response rules.…
Searches past coding sessions for observations, decisions, context. Triggers: mem-search,…
Accessibility validator: WCAG 2.1 AA, EN 301 549, EAA. Triggers: a11y, accessibility, WCAG,…
Creates new specialized agents with frontmatter, tools, delegation. Triggers: new agent,…
Analyzes code quality, complexity, patterns across codebase. Triggers: quality report,…
API design: naming, versioning, pagination, idempotency, OpenAPI, error contracts and safe…