Agent skill

Deliver Pull Request

by shm11C3 in shm11C3/HardwareVisualizer

Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion.

GPL-3.0Auto-check passedDevelopment

Install Deliver Pull Request

skills CLI
$ npx skills add shm11C3/HardwareVisualizer --skill deliver-pull-request -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install shm11C3/HardwareVisualizer deliver-pull-request --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/shm11C3/HardwareVisualizer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deliver-pull-request .claude/skills/deliver-pull-request && rm -rf skills-src

Use ~/.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/

Facts

Skill name
deliver-pull-request
GitHub stars
183
Token cost
~1.9k tokens
SKILL.md length
1,093 words
Files
2
Skills in repo
6
Repo updated
First seen
Licence
GPL-3.0

At a glance

Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion.

  • Works in 4 steps: Confirm The Boundary → Keep The Change Focused → Publish The Pull Request → …
  • The user explicitly asks to create
  • SKILL.md covers 1. Confirm The Boundary, 2. Keep The Change Focused, 3. Publish The Pull Request and 4. Finish CI And Review, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deliver Pull Request is an agent skill from shm11C3/HardwareVisualizer. Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion. Use when the user explicitly asks to create or publish a PR, or to finish an existing PR.

Its SKILL.md is about 1.9k 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 Pull requests. The repository describes itself as: A cross-platform hardware monitor with real-time metrics, local history, and customizable dashboards. The licence is GPL-3.0.

When your agent uses it

  • The user explicitly asks to create
  • Finish an existing PR

Example prompts

  • “/deliver-pull-request”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Confirm The Boundary
  2. Keep The Change Focused
  3. Publish The Pull Request
  4. Finish CI And Review

What it can do on your machine

Read from SKILL.md and the folder at commit fc54f73. 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

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    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

Deliver Pull Request loads about 1.9k tokens when it runs. Until then it costs about 57 tokens; SKILL.md has 1,093 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~57
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 shm11C3/HardwareVisualizer at commit fc54f73, republished under its GPL-3.0 licence (© shm11C3). 1,093 words, ~1,940 tokens.

Download SKILL.mdSave it as .claude/skills/deliver-pull-request/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
deliver-pull-request
description
Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion. Use when the user explicitly asks to create or publish a PR, or to finish an existing PR.

Deliver Pull Request

Publish one coherent change and finish the CI and review work that belongs to it. This workflow ends at an approved PR; merging is a separate request.

1. Confirm The Boundary

A request to create or publish a PR authorizes the branch, commit, push, PR, review replies, and thread resolution needed to deliver that change. It does not authorize merge, destructive Git operations, or unrelated changes. It also authorizes a separate Issue only for a verified merge-blocking finding discovered during review that does not belong to the PR's requirement. Follow SECURITY.md instead of creating a public Issue for a vulnerability.

Before editing, apply AGENTS.md and be able to explain:

  • why the change is needed now;
  • what must change;
  • how the smallest coherent solution works; and
  • why plausible alternatives are unnecessary or worse for this requirement.

Do not create mandatory decision paperwork. Preserve a non-obvious decision only at the smallest durable owner that will need it.

2. Keep The Change Focused

  • Inspect the current branch, worktree, base, and associated PR.
  • Reuse only an open PR whose head repository and branch, intended base, and represented requirement match the current change. Stop when the target is missing or ambiguous instead of creating or updating a different PR.
  • Preserve an existing PR's Draft or Ready state. If pushing or changing that state can enable repository automation to merge without merge authorization, stop before the mutation.
  • Preserve unrelated user changes. Use an isolated worktree when necessary.
  • Implement only the current requirement. Keep adjacent findings separate.
  • Add a focused regression test when it can prove the changed contract.
  • Allow complexity only when the current requirement or an established ownership boundary requires it.

3. Publish The Pull Request

Read and use change-kind-naming. Follow CONTRIBUTING.md and the PR template.

  1. Confirm the branch contains only the intended change.
  2. Run focused checks, then broader checks only when the blast radius requires them.
  3. Review the complete diff and stage only intended paths.
  4. Create a Conventional Commit and push the project-prefixed branch.
  5. Create or update the PR in the Ready or Draft state requested by the user.
  6. Report the PR URL, scope, validation, and any preserved unrelated work.

Prefer an available GitHub connector. The gh CLI cannot complete GitHub operations inside the project sandbox; when it is needed, run the explicit operation in the permitted environment with the required approval.

4. Finish CI And Review

Separate discovery from verification so review converges on approval.

Primary Review
  1. Let the configured automatic reviewers perform one primary review of the published change.
  2. Collect automatic and human feedback before editing and keep a working record of each claim, evidence, decision, and owning boundary.
  3. Triage all accepted findings together and make one focused correction batch.

The primary review is the only broad review. Do not request another full review after corrections.

For review feedback, read and use gh-ai-review-triage:

  • Treat a comment as evidence of a possible problem, not as a prescribed patch.
  • Implement a suggestion only when all of these are true: the problem is supported by code, tests, CI, or a canonical decision; it breaks the current requirement's correctness or security, or makes the changed boundary unclear or brittle for a presently required case; the PR owns that boundary; and a smallest coherent fix is identified.
  • Decline when the claim is false, stale, duplicate, outside the current requirement without affecting its contract, or owned by another boundary that this requirement does not need to change. Reply with the verified evidence, scope decision, and responsible boundary.
  • Do not use low implementation cost, reviewer preference, or possible future value to justify implementation.
  • If the evidence is insufficient, or a verified risk is real but outside the current PR's responsibility, do not guess, dismiss it, or add a defensive patch. Ask the maintainer for a decision.
  • Keep accepted corrections narrow, run the relevant checks, reply with the decision and evidence, and resolve the thread.
  • Never request a Codex review manually. Codex decides when to review.
Show full SKILL.md (425 more words)Show less
Verification Reviews

After the correction batch:

  1. Run focused checks, then commit and push the complete correction batch.
  2. Let CodeRabbit's automatic incremental review and relevant CI inspect that push.
  3. Treat the incremental review as verification of the primary-review decisions and the correction diff, not as a new broad review.
  4. Accept a later finding in this PR when it proves that a primary finding remains unresolved, that the correction introduced a regression, or that a newly discovered merge-blocking problem belongs to the current requirement and changed boundary. A merge-blocking problem requires concrete evidence of a security or soundness failure, data loss or corruption, build/release/runtime failure on a supported path, or a serious violation of the current requirement or public contract.
  5. Reply and defer later findings that are style or naming preferences, speculative fallbacks, future-facing abstractions, minor maintainability improvements, or otherwise non-blocking. They do not justify another push.
  6. For a verified merge-blocking finding outside the PR's requirement, create a separate Issue with the evidence, impact, and owning boundary, then link it from the review reply. Do not expand this PR. For a vulnerability, follow SECURITY.md and do not create a public Issue.
  7. If another correction is required, batch it and let the next push receive automatic incremental review. If automatic review was paused or skipped, request one with @coderabbitai review. Never use @coderabbitai full review.
  8. Once threads are resolved and CI passes, use @coderabbitai approve when needed and confirm GitHub records approval.

If two consecutive verification reviews fail to reach approval without a new in-scope merge-blocking finding, stop automatic correction. An in-scope merge-blocking finding may receive a focused fix, but if the same critical problem does not converge after two corrections, report the unresolved evidence to the maintainer instead of adding another speculative patch.

For a failing check, inspect the failing leaf job and exact error before editing. Separate product regressions from test and environment failures, and fix only an in-scope cause.

Completion Gate

Stop when:

  • the requested change is complete and contains no unrelated work;
  • relevant local checks and CI pass;
  • primary-review feedback is fixed or declined with evidence, and its threads are resolved;
  • GitHub has no outstanding change request and records approval from the approval-capable reviewer; and
  • the PR is in the requested publication state and GitHub reports it mergeable.

Do not seek more findings merely for additional certainty. A verification review does not reopen broad discovery. If permission, approval, a required gate, or an external service prevents completion, report the concrete blocker and the evidence already completed.

© shm11C3, GPL-3.0. 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/deliver-pull-request of shm11C3/HardwareVisualizer.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit fc54f73

Compare with similar skills

Deliver Pull Request 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.

Deliver Pull Request compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deliver Pull Request this skillshm11C3/HardwareVisualizer183—~1.9kAutomated safety check: PassGPL-3.0
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Check PRonyx-dot-app/onyx32k2 repos~2.3kAutomated safety check: PassMIT
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT
PR Design DocOpenHands/OpenHands90k—~2.4kAutomated safety check: PassMIT

Similar skills

  • 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.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Check PR

    onyx-dot-app/onyx

    Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.

    32k GitHub starsUsed in 2 repos~2.3k tokens
    DevelopmentAuto-check passed
  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed
  • PR Design Doc

    OpenHands/OpenHands

    For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…

    90k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed

More from shm11C3/HardwareVisualizer

  • Capture Project Learning

    shm11C3/HardwareVisualizer

    Turn a HardwareVisualizer maintainer correction, repeated failure, surprising invariant, or costly investigation into an evidence-backed learning record and the right durable guardrail.

    183 GitHub stars~858 tokensUpdated today
    Auto-check passed
  • Change Kind Naming

    shm11C3/HardwareVisualizer

    Decide the correct change kind and semantically align branch names, PR titles, commit prefixes, and PR template types.

    183 GitHub stars~994 tokensUpdated today
    Auto-check passed
  • Gh AI Review Triage

    shm11C3/HardwareVisualizer

    Triage and optionally address AI-generated GitHub PR review feedback from Copilot, CodeRabbit, or similar bots.

    183 GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Hardwarevisualizer Design Review

    shm11C3/HardwareVisualizer

    Review or shape HardwareVisualizer product and architecture changes against the maintainer's design principles.

    183 GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Verify Identity Contracts

    shm11C3/HardwareVisualizer

    Verify the id/key contract between backend producers and frontend consumers before implementing any change that joins, selects, persists, or attributes entities keyed by backend-produced ids (GPUs…

    183 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Categories

Questions about Deliver Pull Request

What does Deliver Pull Request do?

Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion. Deliver Pull Request is an agent skill from shm11C3/HardwareVisualizer. Deliver a focused HardwareVisualizer change as a pull request, then address its CI and review feedback to completion.

When should I use Deliver Pull Request?

Deliver Pull Request fits situations like: the user explicitly asks to create; finish an existing PR.

How do I install Deliver Pull Request in Claude Code?

Run `npx skills add shm11C3/HardwareVisualizer --skill deliver-pull-request -a claude-code`. Or copy the skill folder (.agents/skills/deliver-pull-request in shm11C3/HardwareVisualizer) into .claude/skills/deliver-pull-request in your project. Claude Code loads it when a task matches its description.

How do I install Deliver Pull Request in Codex?

Run `npx skills add shm11C3/HardwareVisualizer --skill deliver-pull-request -a codex`. Or copy the skill folder (.agents/skills/deliver-pull-request in shm11C3/HardwareVisualizer) into .agents/skills/deliver-pull-request in your project. Codex loads it when a task matches its description.

Can I use Deliver Pull Request 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 shm11C3/HardwareVisualizer --skill deliver-pull-request -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deliver-pull-request, .gemini/skills/deliver-pull-request, .github/skills/deliver-pull-request and .opencode/skills/deliver-pull-request in your project.

What does Deliver Pull Request need to run?

SKILL.md names no scripts, command-line tools or credentials: Deliver Pull Request is instructions for the agent only.

Does Deliver Pull Request access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deliver Pull Request 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 Deliver Pull Request use?

Deliver Pull Request is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deliver Pull Request use?

About 1.9k tokens (SKILL.md is roughly 7.8k 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 Deliver Pull Request?

Skills that share tags, products or a category with Deliver Pull Request: Finishing a Development Branch (obra/superpowers, 296k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 86k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deliver Pull Request?

shm11C3 (a GitHub user) maintains it in shm11C3/HardwareVisualizer, which has 183 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 8, 2026.

Source: shm11C3/HardwareVisualizer on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.