Agent skill

PR Plots

A skill your agent uses when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body.

MITAuto-check passedAgent Workflows

Install PR Plots

skills CLI

$ npx skills add RussellSB/pytrendy --skill pr-plots -a claude-code

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

GitHub CLI

$ gh skill install RussellSB/pytrendy pr-plots --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/RussellSB/pytrendy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.opencode/skills/pr-plots .claude/skills/pr-plots && 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/

Paste into Claude Code

Install the "pr-plots" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/pr-plots into .claude/skills/pr-plots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-plots", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/pr-plots

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add RussellSB/pytrendy --skill pr-plots -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install RussellSB/pytrendy pr-plots --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.opencode/skills/pr-plots .agents/skills/pr-plots && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "pr-plots" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/pr-plots into .agents/skills/pr-plots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-plots", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add RussellSB/pytrendy --skill pr-plots -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install RussellSB/pytrendy pr-plots --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.opencode/skills/pr-plots .cursor/skills/pr-plots && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "pr-plots" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/pr-plots into .cursor/skills/pr-plots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-plots", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/RussellSB/pytrendy.git --path .opencode/skills/pr-plots

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add RussellSB/pytrendy --skill pr-plots -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install RussellSB/pytrendy pr-plots --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.opencode/skills/pr-plots .gemini/skills/pr-plots && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "pr-plots" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/pr-plots into .gemini/skills/pr-plots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-plots", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install RussellSB/pytrendy pr-plots

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add RussellSB/pytrendy --skill pr-plots -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .github/skills && cp -r skills-src/.opencode/skills/pr-plots .github/skills/pr-plots && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "pr-plots" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/pr-plots into .github/skills/pr-plots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-plots", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add RussellSB/pytrendy --skill pr-plots -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install RussellSB/pytrendy pr-plots --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/RussellSB/pytrendy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.opencode/skills/pr-plots .opencode/skills/pr-plots && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "pr-plots" agent skill from https://github.com/RussellSB/pytrendy/tree/main/.opencode/skills/pr-plots into .opencode/skills/pr-plots/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pr-plots", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: pr-plots
GitHub stars: 106
Token cost: ~1.2k tokens
SKILL.md length: 572 words
Files: 1
Skills in repo: 5
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body.

Works in 6 steps: Find the PR's first commit: gh pr view… → Find its parent: git fetch origin && git… → Checkout parent commit (detached HEAD):… → …
Preparing a fix
SKILL.md covers When to generate, Generating "before" plots…, Generating "after" plots… and Updating PR body, plus 3 more sections
Calls git, gh and python

What it does

PR Plots is an agent skill from RussellSB/pytrendy. Use when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body. Covers generating pre-fix and post-fix plots via detecttrends(plot=True), updating the PR body with image placeholders via gh CLI, the human-in-the-loop image upload to user-attachments, and cleanup. Never commits plot files or temp scripts.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Pull requests and Human-in-the-loop approvals. It works with Git. The repository describes itself as: Trend Detection in Python. Applicable for real-world industry use cases in time series. The licence is MIT.

When your agent uses it

Preparing a fix
Feature PR for review and adding before/after plot evidence to the PR body

Example prompts

“/pr-plots”

Requirements

Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Find the PR's first commit: gh pr view --json commits -q '.commits[0].oid' or GitHub MCP get_commits.
Find its parent: git fetch origin && git rev-parse ^.
Checkout parent commit (detached HEAD): git checkout .
If test fixture data doesn't exist at that commit, extract from the target branch: git show origin/develop:path/to/fixture.csv >…
Write a temp Python script that
Run the script: python _gen_before_plots.py.

What it can do on your machine

Read from SKILL.md and the folder at commit 0d6d5bb. 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
Shell commands in SKILL.md call:
- git
- gh
- python
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git and gh, which can reach the network depending on how they are called.
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

PR Plots loads about 1.2k tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 572 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~89
When it runs · the whole SKILL.md, loaded when a task matches: ~1.2k

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 RussellSB/pytrendy at commit 0d6d5bb, republished under its MIT licence (© RussellSB). 572 words, ~1,235 tokens.

Download SKILL.mdSave it as .claude/skills/pr-plots/SKILL.md (or your agent's skills folder).

name: pr-plots
description: Use when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body. Covers generating pre-fix and post-fix plots via detect_trends(plot=True), updating the PR body with image placeholders via gh CLI, the human-in-the-loop image upload to user-attachments, and cleanup. Never commits plot files or temp scripts.

Before/After plots for PR body

When a fix or feature PR is ready for review, generate visual evidence showing the change's effect and add it to the PR description. This is a human-in-the-loop process: the agent generates plots and writes the PR body with <img> placeholders; the user pastes images into GitHub's editor to get user-attachments/assets/ URLs.

When to generate

PR type	Plots	Notes
Fix PR	Before + After for the main bug	Show the bug behavior (pre-fix) and the corrected behavior (post-fix)
Feature PR	After only (usually)	If there's a prior behavior to compare, include Before; otherwise just show the new behavior
Guard rail	After only	When a fix introduces a workaround or edge-case suppression, add a complementary plot showing that other scenarios still work correctly

Guard rail plots

When a fix introduces a workaround (e.g. suppressing noise on a zero-baseline leading edge), add a guard rail plot to verify the fix doesn't break another scenario. Use a single "after" plot (not before/after) — the point is confirming no regression. Label the section "Guard rail" and explain in the text why it was added.

Generating "before" plots (pre-fix state)

Find the PR's first commit: gh pr view <N> --json commits -q '.commits[0].oid' or GitHub MCP get_commits.
Find its parent: git fetch origin <sha> && git rev-parse <sha>^.
Checkout parent commit (detached HEAD): git checkout <parent-sha>.
If test fixture data doesn't exist at that commit, extract from the target branch: git show origin/develop:path/to/fixture.csv > /tmp/fixture.csv.
Write a temp Python script that:
- Sets matplotlib to Agg backend: matplotlib.use('Agg')
- Loads the fixture data (from /tmp/ if extracted, or from the repo if it exists at that commit)
- Runs detect_trends(plot=True) with the same params as the test
- Saves the plot: plt.savefig('before_<scenario>.png', dpi=150, bbox_inches='tight')
- Closes the figure: plt.close()
Run the script: python _gen_before_plots.py.

Generating "after" plots (post-fix state)

Checkout the working branch (develop or feature branch).
Run the same script with output filenames changed to after_<scenario>.png.

Show full SKILL.md (255 more words)Show less

Updating PR body

Write the PR body markdown to /tmp/pr_body.md with <img> placeholder tags (empty src="").

Update via gh CLI REST API (the GitHub MCP token lacks PR write permission):

bash

gh api repos/OWNER/REPO/pulls/N --method PATCH --field body="$(cat /tmp/pr_body.md)"

Never git add, git commit, or git push plot files or temp scripts. Plots stay local only.
User pastes each image into the GitHub PR editor (edit PR → paste image into body) to get user-attachments/assets/ URLs.
User provides URLs → agent updates the PR body with real image URLs (same gh api PATCH call).

PR body structure template

markdown

## Before / After — `test_<name>`

The core fix: <one-line description>

**Before fix** — <description of the bug behavior>:

<img width="1990" height="478" alt="<description>" src="" />

**After fix** — <description of the fixed behavior>:

<img width="1990" height="478" alt="<description>" src="" />

## Guard rail — `test_<name>`

Added to verify the fix doesn't break <scenario>. Confirmed working post-fix:

<img width="1990" height="478" alt="<description>" src="" />

Cleanup

After the user has pasted the images and confirmed the PR body looks good:

Delete temp plot files (*.png) from the repo working directory
Delete temp Python scripts (_gen_*.py)
Delete temp CSV fixtures from /tmp/
Delete temp branch if one was created (git branch -D <temp-branch>)
Switch back to the original working branch
Do NOT leave any untracked files in the repo

Constraints

Zero commits: Never git add or git commit plot files, temp scripts, or temp fixtures. These are ephemeral.
MCP token limitation: The GitHub MCP token does not have PR write permission. Use gh api (REST) or gh pr edit (if it works) with the user's local PAT instead.
Image hosting: GitHub has no API for uploading images to user-attachments/assets/. This is a web-editor-only feature. The human-in-the-loop step is mandatory.
matplotlib backend: Always use matplotlib.use('Agg') in temp scripts to avoid interactive display warnings and ensure PNGs save correctly in non-interactive environments.

Files

Just SKILL.md in .opencode/skills/pr-plots of RussellSB/pytrendy.

Open the folder on GitHubat commit 0d6d5bb

Compare with similar skills

PR Plots 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.

PR Plots compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
PR Plots this skillRussellSB/pytrendy	106	—	~1.2k	Automated safety check: Pass	MIT	yesterday
Code ReviewerCaoMeiYouRen/caomei-auth	220	—	~1.5k	Automated safety check: Pass	MIT	8 days ago
Repo Context Ledgergviiisen/repo-context-ledger	105	—	~2.8k	Automated safety check: Pass	MIT	1 mo ago
PRP Workstream OrchestratorWirasm/prp	2.3k	—	~3.5k	Automated safety check: Pass	MIT	7 days ago
Walkthroughsmallnest/goal-workflow	290	—	~4.7k	Automated safety check: Notes	MIT	26 days ago
Cline Pilotsickn33/agentic-awesome-skills	47k	1 repos	~4.6k	Automated safety check: Pass	MIT	today

Similar skills

Code Reviewer
CaoMeiYouRen/caomei-auth
审查当前 git 变更、PR、提交范围、技能定义文件、架构调整或安全敏感代码时使用。输出结构化 Review Gate 结论（Pass/Reject）、问题分级（blocker/warning/suggest）、最低验证矩阵、证据链与复查基线。覆盖正确性、安全、架构、SOLID、可删除代码、性能、异常处理与测试风险；默认只输出 review，不直接修改代码。用户提到 review、code…
220 GitHub stars~1.5k tokensUpdated 8 days ago
DevelopmentAuto-check passed
Repo Context Ledger
gviiisen/repo-context-ledger
Record every behavior-changing feature addition, fix, and adjustment as durable, evidence-based repository knowledge, then use that ledger to continue accurately across AI windows, tools, Git…
105 GitHub stars~2.8k tokensUpdated 1 mo ago
Agent WorkflowsAuto-check passed
PRP Workstream Orchestrator
Wirasm/prp
Coordinates several PRP workstreams in isolated Git worktrees from one session, verifying proof, holding merge gates and sequencing the merges.
2.3k GitHub stars~3.5k tokensUpdated 7 days ago
Agent WorkflowsAuto-check passed
Walkthrough
smallnest/goal-workflow
Generate a Phase-2 Walkthrough artifact (walkthrough.md) once implementation and verification are complete.
290 GitHub stars~4.7k tokensUpdated 26 days ago
Testing & QAAuto-check: notes
Cline Pilot
sickn33/agentic-awesome-skills
Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.
47k GitHub starsUsed in 1 repo~4.6k tokens
Agent WorkflowsAuto-check passed
Gh Issues
trpc-group/trpc-agent-go
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments.
1.9k GitHub starsUsed in 8 repos~8.7k tokens
Agent WorkflowsAuto-check passed

Questions about PR Plots

What does PR Plots do?

A skill your agent uses when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body. PR Plots is an agent skill from RussellSB/pytrendy. Use when preparing a fix or feature PR for review and adding before/after plot evidence to the PR body.

When should I use PR Plots?

PR Plots fits situations like: preparing a fix; feature PR for review and adding before/after plot evidence to the PR body.

How do I install PR Plots in Claude Code?

Run `npx skills add RussellSB/pytrendy --skill pr-plots -a claude-code`. Or copy the skill folder (.opencode/skills/pr-plots in RussellSB/pytrendy) into .claude/skills/pr-plots in your project. Claude Code loads it when a task matches its description.

How do I install PR Plots in Codex?

Run `npx skills add RussellSB/pytrendy --skill pr-plots -a codex`. Or copy the skill folder (.opencode/skills/pr-plots in RussellSB/pytrendy) into .agents/skills/pr-plots in your project. Codex loads it when a task matches its description.

Can I use PR Plots 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 RussellSB/pytrendy --skill pr-plots -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pr-plots, .gemini/skills/pr-plots, .github/skills/pr-plots and .opencode/skills/pr-plots in your project.

What does PR Plots need to run?

Going by SKILL.md and its folder, PR Plots needs the command-line tools its instructions call (git, gh and python). Our summary lists: Python 3.

Does PR Plots access the network?

SKILL.md contains no URLs. Its commands use git and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is PR Plots 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 PR Plots use?

PR Plots is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PR Plots use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 PR Plots?

Skills that share tags, products or a category with PR Plots: Code Reviewer (CaoMeiYouRen/caomei-auth, 220 stars), Repo Context Ledger (gviiisen/repo-context-ledger, 105 stars), PRP Workstream Orchestrator (Wirasm/prp, 2.3k stars) and Walkthrough (smallnest/goal-workflow, 290 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PR Plots?

RussellSB (a GitHub user) maintains it in RussellSB/pytrendy, which has 106 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 8, 2026.

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

Install PR Plots

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Before/After plots for PR body

When to generate

Guard rail plots

Generating "before" plots (pre-fix state)

Generating "after" plots (post-fix state)

Updating PR body

PR body structure template

Cleanup

Constraints

Files

Compare with similar skills

Similar skills

More from RussellSB/pytrendy

Related

Questions about PR Plots