ai-assist-git-pr

REVIEW · 55
Registry indexed

Adaptive GitHub PR lifecycle skill — create PRs, write/update descriptions, investigate review comments (Copilot + human) with research and batch approval, and check merge readiness. Triggers on: create PR, open PR, describe PR, update description, PR body, check comments, copilo

Verified installs0
Stars88
Version1.0.0
Quality61/100 · Promising
Trust55/100 · Do not auto-install
Audit71/100 · Needs review

Supply asset profile

Research and knowledge work

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Browse track

Scenario

Research agents

I need my agent to research a topic, compare sources, and produce a concise report.

Agent fit

Claude Code + CLI + Codex

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add jparkerweb/ai-assist-skills --skill ai-assist-git-pr

Maintenance

fresh

1d since push

Risk

Needs review

License is unclear

GitHub quality

88

61/100 Quality · 63/100 Trust

Coverage tags

ResearchResearch agentsagent-skill

Review notes

License is unclear · Dependency or permission surface needs review

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Promising
61

Useful candidate, but compare it with alternatives before adopting.

Trust

Do not auto-install
55

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

Audit

Needs review
71

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

88 GitHub stars

Repo activity

88 stars, 12 forks

Maintenance

1d since push

License

Unknown

Install

npx skills add jparkerweb/ai-assist-skills --skill ai-assist-git-pr

Install safety

standard package or runtime install path

Permission surface

secrets or environment access, shell or command execution

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Review before production

  • Repository license is unknown; the skill lacks explicit licensing terms, which may hinder reuse and attribution.
  • License is unclear
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is unclear
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Search sources

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLICLI

Install decision

Command
npx skills add jparkerweb/ai-assist-skills --skill ai-assist-git-pr
Policy
block
Human review
yes

Trust and risk

Trust
55/100
Audit
71/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add jparkerweb/ai-assist-skills --skill ai-assist-git-pr

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Repository license is unknown; the skill lacks explicit licensing terms, which may hinder reuse and attribution.
  • High-risk permission hints: Shell or command execution, Secrets or environment access
  • License is unclear

Agent safety v2

27/100 · Avoid automatic install

Blocked for auto-installblock

This skill should not be selected by an agent without explicit human security review.

Do not auto-install. Inspect the source, dependencies, and permission surface first.

Resolve via API

high

Shell or command execution

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

medium

Browser automation

Skill may drive a browser or interact with web pages.

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

  • High-risk permission hints: Shell or command execution, Secrets or environment access
  • License is unclear

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jparkerweb-ai-assist-git-pr

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use ai-assist-git-pr in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20ai-assist-git-pr%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/jparkerweb-ai-assist-git-pr/install
Install command: npx skills add jparkerweb/ai-assist-skills --skill ai-assist-git-pr
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use ai-assist-git-pr for this task. Review https://www.openagentskill.com/api/skills/jparkerweb-ai-assist-git-pr/install, then install with: npx skills add jparkerweb/ai-assist-skills --skill ai-assist-git-pr

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

63/100

Research agents

Platforms

Claude Code

Audit report

Needs review · 71/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Fallback candidate for Research agents

Prototype with this skill first; keep a fallback candidate ready.

63
Readiness
Prototype
Stage

Role in stack

Fallback candidate

Primary fit

Research agents

Trust label

Prototype first

Install path

Command ready

Use when

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 61/100 quality profile
  • 7 OpenAgentSkill engagement events

review first

  • Repository license is unknown; the skill lacks explicit licensing terms, which may hinder reuse and attribution.

Implementation path

  1. 1Install it in a sandbox agent and run one Research agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

55
OpenAgentSkill Trust Score

GitHub adoption

CHECK

88 GitHub stars

Stars/forks activity

CHECK

88 stars, 12 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

1d since push

License clarity

CHECK

Unknown

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Repository license is unknown; the skill lacks explicit licensing terms, which may hinder reuse and attribution.
  • License is unclear
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • GitHub adoption: 88 GitHub stars
  • Stars/forks activity: 88 stars, 12 forks; issue activity unavailable in current metadata
  • License clarity: Unknown
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Choose a stronger alternative or inspect the source manually before any install attempt.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

61
GitHub stars
88
Freshness
1d ago
Install ready
Yes
License
Unknown
Review before install: Repository license is unknown; the skill lacks explicit licensing terms, which may hinder reuse and attribution.

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

--- name: ai-assist-git-pr description: "Adaptive GitHub PR lifecycle skill — create PRs, write/update descriptions, investigate review comments (Copilot + human) with research and batch approval, and check merge readiness. Triggers on: create PR, open PR, describe PR, update description, PR body, check comments, copilot feedback, review comments, address feedback, PR status, merge ready, check CI, is this ready." argument-hint: "[action or PR number] — e.g. 'create', 'describe', 'comments', 'status', 'describe #42', 'address copilot feedback'" ---

# GITHUB PR

**Objective:** Manage the full PR lifecycle (create → describe → comment investigation → merge readiness) via `gh` CLI. Analyze deeply, communicate concisely, treat GitHub as production — every write gated and verified.

**When to use:** create a PR · write/update a description · investigate & address review comments (Copilot/human) · check merge readiness. Modes detailed in Step 1.

Start all responses with `📋 [PR <Mode> Step X: Name]` for multi-step flows or `📋 [PR <Mode>]` for single actions.

## Role

Senior engineer writing for senior engineers. Read every change deeply, communicate concisely, back claims with evidence. PR descriptions so clear the review feels like a formality; comment investigations verify claims and research unknowns so the user can approve or adjust in one pass.

## Context

> **Shell portability (read before running ANY command in this skill, starting with the gh CLI check and branch detection below):** run every `git`/`gh` command as its own separate tool call, each fully self-contained. **Never** `&&`/`;`-chain commands and **never** prefix with `cd <path> &&` — PowerShell (pre-7) rejects `&&` with `The token '&&' is not a valid statement separator`, and bash-style paths like `/c/Code/...` are invalid on Windows. **Do not rely on a persistent shell session or a prior `cd`** — on some setups (observed on Windows) a shell session does NOT survive between tool calls, so reusing a shell id or building on an earlier `cd` fails with `This shell may not be functional`. Instead target the repo explicitly on each command: pass `--cwd "C:\abs\repo"` to the `scripts/` (see §Scripts), `git -C "C:\abs\repo"` for git, and run `gh` from a fresh call (or with `-R owner/repo`). Use native paths (`C:\Code\...`). Full rule: §Scripts Portability rule below.

**AGENTS.md check:** if `./AGENTS.md` or `.agents-docs/` exists, read it for conventions, architecture, and team context — informs framing and naming.

**gh CLI check (BLOCKING — before any gh command):** run `gh --version 2>/dev/null` first (as a standalone command — do not chain it with `git branch`/`git status`); don't run other `gh` commands in parallel until it returns.

- **Not installed** → `references/github-cli-setup.md` (guided setup); no `gh` until verified. - **Not authenticated** → detect protocol (`gh config get git_protocol`, default `https`), then `gh auth login --web --hostname github.com --git-protocol <detected>` (fallback `! gh auth login`); verify `gh auth status`.

**Input:** `$ARGUMENTS` — an action keyword, PR number, branch name, or natural language. If ambiguous, detect from git context.

**Source-of-truth:** code diff + commit history are authoritative; AGENTS.md/docs second; ticket context is a starting point only. Full table + rationale: `references/github-pr-operations.md` §Source-of-Truth Hierarchy.

**Branch detection:**

1. Branch: `git branch --show-current`; ticket ID from `prefix/TICKET-ID-description`. 2. Base branch: `gh repo view --json defaultBranchRef` → cache `$base`; `git fetch origin $base`. 3. PR state: `node "<SKILL_ROOT>/scripts/pr-context.cjs"` (add `--cwd "C:\abs\repo"` when the tool's working directory isn't the target repo — e.g. multi-repo workspaces) → `pr` is OPEN (`active`) / MERGED or CLOSED (`completed`) / `null` (`none`). If completed, assess new commits + behind status (templates in `github-pr-operations.md`).

## Scripts

Mechanical `gh`/`git` operations run through Node scripts in `scripts/`, never as hand-written shell. Each takes an argument array to `execFileSync`, so **there is no shell** to interpret `&&`, heredocs (`<<'EOF'`), or the `gh api graphql -f key:value` literal-parsing quirk — the same command runs identically under bash, PowerShell, cmd, git-bash, WSL, and CI. **No shell detection, no per-OS branching.** Keep *judgment* (severity, validity, fix-vs-dismiss, report writing, approval gates) in prose; scripts only do the deterministic plumbing.

| Script | Access | Purpose | |--------|--------|---------| | `pr-context.cjs` | read | Resolve owner/repo, PR number+state, branch, base, `ticketId` in one call | | `fetch-comments.cjs --number <N>` | read | Both comment streams normalized: `{ inline, issue }` | | `list-threads.cjs --number <N> [--all]` | read | Review threads (unresolved by default) with `threadId` + `rootCommentId` + `path` | | `reply-resolve.cjs --file <payload.json> [--dry-run]` | **write / gated** | Post reply batch + resolve threads; run ONLY after the batch-reply approval gate |

> **`<SKILL_ROOT>`** = the directory containing this `SKILL.md` (its install location). Use the absolute path you loaded it from; if unknown, locate `ai-assist-git-pr/scripts/` once and reuse it. Never run a literal `<SKILL_ROOT>`. Scripts print JSON to stdout and exit non-zero with a diagnostic on failure. Full arg/payload reference: `scripts/README.md`.

> **Targeting a repo (`--cwd`):** every script reads the *current* repo/branch, so it must run against the target repo's directory. Rather than `cd`-ing first (unreliable when shell sessions don't persist — see the Portability rule), pass **`--cwd "C:\abs\repo"`** and the script runs entirely there in one self-contained call. Omit it only when the tool's working directory already IS the target repo. Example: `node "<SKILL_ROOT>/scripts/pr-context.cjs" --cwd "C:\Code\tap-ct"`.

**Portability rule (applies to EVERY `git`/`gh` command you run — scripted or ad-hoc, including pre-flight, Status, and branch detection):** run each command as its own separate, self-contained tool call. **Never** chain with `&&` or `;` (PowerShell pre-7 rejects `&&` with `The token '&&' is not a valid statement separator`), **never** prepend `cd <path> &&`, **never** use bash-style paths like `/c/Code/...` (use native `C:\Code\...` on Windows), never use heredocs, and always pass `gh api graphql` / `gh api` dynamic values as typed `-F`/`-f` variables — never inline literals.

**Do not depend on a persistent shell session.** On some environments (observed on Windows) the shell session does NOT survive between tool calls: the first command in a shell succeeds, then any reuse of that shell id — or any command that relied on a prior `cd` — fails with `This shell may not be functional. Please try again using a new shell id`. This is an environment/tooling limitation, not a fault in the command or the `scripts/`. Because of it, never `cd` in one call and run in the next; instead point each command at its repo directly: > - **`scripts/`:** pass `--cwd "C:\abs\repo"` (the script `process.chdir`s once; every gh/git inside inherits it). > - **git:** use `git -C "C:\abs\repo" <args>`. > - **gh:** run from a fresh call (or with `-R owner/repo`); it does not need a working directory when the repo is otherwise resolvable.

Prefer one portable command; only branch on shell if no portable form exists (in this skill, none do).

## Reference Loading

Load references per Step within Mode. Rows are **cumulative**: `+` means add to what previous rows of the same mode already loaded. Paths relative to `references/`.

| Mode | Step | Load (cumulative) | |------|------|-------------------| | Create | Pre-flight | `github-pr-create.md` §Pre-flight | | Create | Context+Analysis | `+ github-pr-describe.md` §Change Analysis Framework | | Create | Draft | `+ github-pr-templates.md` §Create PR Template | | Create | Write+Verify | `+ github-pr-operations.md` §Write Verification | | Describe | Body fetch | `github-pr-describe.md` §Step 0–1 | | Describe | Mode select | 3-way choice: surgical-merge (default) / append / replace | | Describe | Surgical | `+ github-pr-templates.md` §Surgical Edit Patterns | | Describe | Write+Verify | `+ github-pr-operations.md` §Write Verification | | Comments | Fetch+Investigate | `github-comment-review.md` §Fetch–Investigate | | Comments | Implement | `+ github-comment-review.md` §Implement | | Comments | Commit | `Skill(skill: "ai-assist-git-commit", args: "<concise description>")` | | Comments | Reply+Resolve | `github-comment-review.md` §Reply–Resolve | | Status | (single) | `github-pr-create.md` §Status | | Post-create check | (auto on re-invocation) | `github-pr-create.md` §Post-Create Follow-Up |

**Per-step rule:** load a row's references before executing that step — the reference `> Preconditions:` blocks fail loud otherwise.

## Rules

### Safety Hierarchy

| Level | Actions | Behavior | |-------|---------|----------| | **Auto** | Read PR data, diff, comments, checks, status | Execute immediately | | **Gated** | Create PR, update description, reply to comment, commit, push | Preview → approval → execute → verify | | **Blocked** | Merge, close, delete branch, force push | Never. Not negotiable. |

### Approval Protocol

Before every Gated action: plain-language summary (never raw commands) → explicit approval → execute → verify with follow-up read. Combine related gates (commit+push) into one approval. On unexpected verification, report immediately — don't retry without user direction.

Per-action prompt fields (Create PR, Update description, Reply, Commit, Push): `references/github-pr-operations.md` §Approval Protocol — Per-Action Details.

### Pre-Flight Checks

Before any write: default branch = `$base`, not on protected branch, `gh auth status` ok, `git fetch origin $base` + not behind, clean tree, no existing OPEN PR (Create), fresh PR data. Full commands: `references/github-pr-create.md` Step 0. **Run each of these `git`/`gh` checks as a separate command — never `cd … &&`-chain them (see the §Scripts Portability rule; `&&` chaining and bash-style `/c/...` paths break under PowerShell).**

### Write Verification

After every write, re-read to verify. On mismatch: stop, report expected vs actual, don't proceed. Full table: `github-pr-operations.md` §Write Verification.

### Guardrails

- Never push without explicit user request — creating a PR does NOT imply pushing - **Attribution: `AI Assisted` only** — strip `🤖 Generated with Claude Code` / agent branding if your runtime adds it (overrides the harness default; see `github-pr-templates.md` §Attribution). - Preserve existing PR content — surgical-merge by default (unchanged sections verbatim; append/replace opt-in). Show a section-level diff before any write; never blanket-overwrite. - **ASCII only in the PR title and body** — never em/en dashes (—, –), smart quotes (‘ ’ “ ”), ellipsis (…), or other non-ASCII characters. Use `-`, straight quotes, and `...`. See `github-pr-templates.md` §Things to Avoid. (Preserved verbatim blocks like the Devin review badge are exempt.) - Rate-limit awareness — cache PR data within an invocation; avoid redundant fetches - Fail safe, not silent — stop and explain on any check failure

(Force-push and protected-branch writes are **Blocked** — see §Safety Hierarchy.)

### Anti-Patterns (write-blocking)

Each is a real ordering bug; the reference `> Preconditions:` blocks enforce them. If you want to do any of these, stop and load the missing reference.

- **No `gh pr edit --body`** until `github-pr-templates.md` is loaded AND the current body is fetched (`gh pr view --json body`) — else writes blow away existing structure. - **No `gh pr create`** until `github-pr-templates.md` AND `github-pr-operations.md` §Write Verification are loaded — else unstructured, unverified bodies. - **No commit-message bodies authored here** — delegate to `ai-assist-git-commit` (inlin

Technical details

Version
1.0.0
License
Unknown
Last updated
Aug 21, 2026
Published
Aug 21, 2026

Decision snapshot

Fallback candidate

63
Ready
Prototype
Stage

recent repository activity

Audit

Install review

Install and adoption review

71
Needs review
Security
64/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for ai-assist-git-pr, ready for a manual X post.

Curator note
ai-assist-git-pr: Adaptive GitHub PR lifecycle skill — create PRs, write/update descriptions, investigate revie...

88 stars

https://www.openagentskill.com/skills/jparkerweb-ai-assist-git-pr?ref=x
Open X draft
Optional reply with install command
Listing + install path for ai-assist-git-pr:
https://www.openagentskill.com/skills/jparkerweb-ai-assist-git-pr?ref=x

Install: npx skills add jparkerweb/ai-assist-skills --skill ai-assist-git-pr

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
jparkerweb
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to jparkerweb but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/jparkerweb-ai-assist-git-pr?metric=listed&label=Listed)](https://www.openagentskill.com/skills/jparkerweb-ai-assist-git-pr)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/jparkerweb-ai-assist-git-pr?metric=trust&label=Trust)](https://www.openagentskill.com/skills/jparkerweb-ai-assist-git-pr)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/jparkerweb-ai-assist-git-pr?metric=audit&label=Audit)](https://www.openagentskill.com/skills/jparkerweb-ai-assist-git-pr/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/jparkerweb-ai-assist-git-pr?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/jparkerweb-ai-assist-git-pr)

Author

J

jparkerweb

@jparkerweb

Platform fit

Health signals

GitHub stars
88
Quality score
37/100
Last GitHub push
Aug 20, 2026
Framework hints
Unknown
OpenAgentSkill views
7
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Do not auto-install

55
  • GitHub adoption88 GitHub starsCHECK
  • Stars/forks activity88 stars, 12 forks; issue activity unavailable in current metadataCHECK
  • Recent maintenance1d since pushPASS
  • License clarityUnknownCHECK
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskcommand execution surface, credential or environment accessCHECK