New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Counterfact PR Creation

by counterfact in counterfact/api-simulator

Create Counterfact pull requests with the required agent-authored acceptance and repository-learning notes; do not use to review another PR.

MITAuto-check passedDevelopment

Install Counterfact PR Creation

skills CLI
$ npx skills add counterfact/api-simulator --skill counterfact-pr-creation -a claude-code

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

GitHub CLI
$ gh skill install counterfact/api-simulator counterfact-pr-creation --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/counterfact/api-simulator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/counterfact-pr-creation .claude/skills/counterfact-pr-creation && 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
counterfact-pr-creation
GitHub stars
170
Token cost
~918 tokens
SKILL.md length
436 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Create Counterfact pull requests with the required agent-authored acceptance and repository-learning notes; do not use to review another PR.

  • Review another PR
  • SKILL.md covers When to use this skill, Agent-owned PR sections, Manual acceptance tests and Repository learning check
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve Pull requests

What it does

Counterfact PR Creation is an agent skill from counterfact/api-simulator. Create Counterfact pull requests with the required agent-authored acceptance and repository-learning notes; do not use to review another PR.

Its SKILL.md is about 920 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 Development, covering Pull requests and OpenAPI specifications. It works with OpenAPI. The repository describes itself as: Turn an OpenAPI spec into a local API in one command. Build and test your frontend with custom responses, shared state, and simulated failures, without waiting for the backend. The licence is MIT.

When your agent uses it

  • Review another PR
  • Tasks that involve Pull requests
  • Tasks that involve OpenAPI specifications

Example prompts

  • “/counterfact-pr-creation”

What it can do on your machine

Read from SKILL.md and the folder at commit fc1c7f8. 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 (its code samples are markdown).

    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

Counterfact PR Creation loads about 918 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 436 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~918

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 counterfact/api-simulator at commit fc1c7f8, republished under its MIT licence (© counterfact). 436 words, ~918 tokens.

Download SKILL.mdSave it as .claude/skills/counterfact-pr-creation/SKILL.md (or your agent's skills folder).
name
counterfact-pr-creation
description
Create Counterfact pull requests with the required agent-authored acceptance and repository-learning notes; do not use to review another PR.
applyTo
.github/pull_request_template.md, .github/skills/**/*.md, AGENTS.md

Counterfact PR Creation Skill

When to use this skill

Use this skill when an agent creates or opens a Counterfact pull request. Do not use it as a review checklist.

Agent-owned PR sections

Writing ## Manual acceptance tests and ## Repository learning check is the responsibility of the agent that creates the PR, not of a reviewing agent. Completing manual acceptance and checking its boxes is the human reviewer's responsibility. A reviewing agent must not look for either section or treat its absence as a PR deficiency. Their absence most likely means the PR was not opened by an agent.

Manual acceptance tests

Every agent-created PR description must include a section titled exactly ## Manual acceptance tests with 3–6 checklist items that start unchecked. Each checklist item must describe an observable behavior, not an implementation detail. A human performs manual acceptance and checks the boxes before merge.

  • Agents create the boxes and leave them unchecked. Never check manual acceptance boxes yourself, including after running tests or exercising the behavior yourself.

  • Report agent-run verification separately from human manual acceptance. Passing automated checks or agent-run verification does not establish human acceptance.

  • When editing an existing PR description, preserve boxes checked by a human; do not infer human acceptance from test results or change unchecked boxes to checked.

  • Cover the main success path, at least one edge case, and one regression check where applicable.

  • A PR that only adds files under .github/issue-proposals/ may omit this section.

  • The repository workflow validates this section for applicable PRs. A failing check while human acceptance is pending is expected; report it as awaiting human acceptance instead of checking boxes to make the workflow pass.

Show full SKILL.md (162 more words)Show less

Repository learning check

For every non-trivial agent-created PR, include this section in the PR description:

markdown
## Repository learning check

- Learning found: Yes/No
- Guidance updated: Yes/No
- Updated file(s): N/A or list files
- Rationale: one sentence explaining why the repository guidance did or did not need to change

If Learning found: Yes, update the most relevant repository guidance in the same PR.

Use the following decision tree:

  • Runtime behavior, REPL behavior, request handling, context usage, server lifecycle, or application architecture → update the appropriate SKILL.md
  • Generator behavior, code generation patterns, route generation, OpenAPI processing, overlays, or specification handling → update the appropriate SKILL.md
  • Build, test, release, CI/CD, dependency management, repository maintenance, or contributor workflow → update the appropriate SKILL.md
  • Cross-cutting conventions that apply throughout the repository → update AGENTS.md

A durable learning is a reusable rule, pattern, validation step, compatibility concern, testing strategy, architectural constraint, or repository-specific convention that helps future contributors avoid mistakes or work more effectively.

Do not create guidance for one-off implementation details, temporary workarounds, PR-specific decisions, historical commentary, or task summaries. If no durable learning was discovered, explicitly record Learning found: No and do not create or modify guidance files solely to satisfy this requirement.

© counterfact, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/counterfact-pr-creation of counterfact/api-simulator.

Open the folder on GitHubat commit fc1c7f8

Compare with similar skills

Counterfact PR Creation 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.

Counterfact PR Creation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Counterfact PR Creation this skillcounterfact/api-simulator170—~918Automated safety check: PassMIT
PR Reviewconfluentinc/mcp-confluent167—~4.6kAutomated safety check: NotesMIT
B24phpsdk Maintainerbitrix24/b24phpsdk102—~10kAutomated safety check: NotesMIT
Apm Spec Guardianmicrosoft/apm4k—~4.9kAutomated safety check: PassMIT
Guidesmicronaut-projects/micronaut-openapi114—~1.9kAutomated safety check: NotesApache-2.0
Ramp CI Integrationjeremylongshore/tons-of-skills-marketplace2.8k—~1.3kAutomated safety check: PassMIT

Similar skills

  • PR Review

    confluentinc/mcp-confluent

    Reviews pull requests for the Confluent MCP server. An agent skill from confluentinc/mcp-confluent.

    167 GitHub stars~4.6k tokensUpdated today
    DevelopmentAuto-check: notes

  • B24phpsdk Maintainer

    bitrix24/b24phpsdk

    A skill your agent uses whenever working with GitHub issues in the bitrix24/b24phpsdk repository: creating new issues, reading existing ones, planning implementation from an issue, referencing an…

    102 GitHub stars~10k tokensUpdated 10 days ago
    Backend & APIsAuto-check: notes

  • Apm Spec Guardian

    microsoft/apm

    Official

    A skill your agent uses to run a four-panel adversarial advisory review on any pull request that touches the OpenAPM specification artifact (docs/src/content/docs/specs/openapm-.md), its inline /…

    4k GitHub stars~4.9k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Guides

    micronaut-projects/micronaut-openapi

    Create or update standalone Micronaut Guides in micronaut-projects/micronaut-guides, including topic discovery, guide authoring, validation, PDF export, and pull request handoff.

    114 GitHub stars~1.9k tokensUpdated yesterday
    Backend & APIsAuto-check: notes

  • Ramp CI Integration

    jeremylongshore/tons-of-skills-marketplace

    Build deterministic CI gates for a Ramp integration using the official OpenAPI contract, local fixtures, and explicitly approved sandbox probes.

    2.8k GitHub stars~1.3k tokensUpdated yesterday
    Backend & APIsAuto-check passed

  • Datadog Data Source Generator

    DataDog/terraform-provider-datadog

    Official

    Generates a Datadog Terraform provider data source from an OpenAPI operation with tfgen and opens a review-ready GitHub PR with a risk scan and testing guide.

    468 GitHub stars~2.7k tokensUpdated yesterday
    DevOps & CloudAuto-check passed

More from counterfact/api-simulator

All 12 skills in this repo

  • Counterfact Repl

    counterfact/api-simulator

    Interact with Counterfact mock API server programmatically. An agent skill from counterfact/api-simulator.

    170 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed

  • Build Simulation

    counterfact/api-simulator

    Build a fully simulated API from an OpenAPI spec using Counterfact.

    170 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed

  • Counterfact Maintenance

    counterfact/api-simulator

    Keep contributor changes aligned with repository test patterns, diagnostics, black-box test boundaries, release/versioning workflow, documentation requirements, and compatibility.

    170 GitHub stars~3.1k tokensUpdated yesterday
    Auto-check passed

  • Counterfact Repo Basics

    counterfact/api-simulator

    Provide Counterfact repository orientation, high-level architecture, and the canonical command reference for install/build/test/lint workflows.

    170 GitHub stars~868 tokensUpdated yesterday
    Auto-check passed

  • Route

    counterfact/api-simulator

    Edit Counterfact route files to add endpoint behavior while keeping handlers thin and delegating business logic to context classes.

    170 GitHub stars~341 tokensUpdated yesterday
    Auto-check passed

  • Scenario

    counterfact/api-simulator

    Create and update Counterfact scenario modules that seed or mutate context state through reusable scenario functions.

    170 GitHub stars~356 tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Counterfact PR Creation

What does Counterfact PR Creation do?

Create Counterfact pull requests with the required agent-authored acceptance and repository-learning notes; do not use to review another PR. Counterfact PR Creation is an agent skill from counterfact/api-simulator. Create Counterfact pull requests with the required agent-authored acceptance and repository-learning notes; do not use to review another PR.

When should I use Counterfact PR Creation?

Counterfact PR Creation fits situations like: review another PR; tasks that involve Pull requests; tasks that involve OpenAPI specifications.

How do I install Counterfact PR Creation in Claude Code?

Run `npx skills add counterfact/api-simulator --skill counterfact-pr-creation -a claude-code`. Or copy the skill folder (.github/skills/counterfact-pr-creation in counterfact/api-simulator) into .claude/skills/counterfact-pr-creation in your project. Claude Code loads it when a task matches its description.

How do I install Counterfact PR Creation in Codex?

Run `npx skills add counterfact/api-simulator --skill counterfact-pr-creation -a codex`. Or copy the skill folder (.github/skills/counterfact-pr-creation in counterfact/api-simulator) into .agents/skills/counterfact-pr-creation in your project. Codex loads it when a task matches its description.

Can I use Counterfact PR Creation 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 counterfact/api-simulator --skill counterfact-pr-creation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/counterfact-pr-creation, .gemini/skills/counterfact-pr-creation, .github/skills/counterfact-pr-creation and .opencode/skills/counterfact-pr-creation in your project.

What does Counterfact PR Creation need to run?

SKILL.md names no scripts, command-line tools or credentials: Counterfact PR Creation is instructions for the agent only.

Does Counterfact PR Creation 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 Counterfact PR Creation 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 Counterfact PR Creation use?

Counterfact PR Creation 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 Counterfact PR Creation use?

About 918 tokens (SKILL.md is roughly 3.7k 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 Counterfact PR Creation?

Skills that share tags, products or a category with Counterfact PR Creation: PR Review (confluentinc/mcp-confluent, 167 stars), B24phpsdk Maintainer (bitrix24/b24phpsdk, 102 stars), Apm Spec Guardian (microsoft/apm, 4k stars) and Guides (micronaut-projects/micronaut-openapi, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Counterfact PR Creation?

counterfact (a GitHub organization) maintains it in counterfact/api-simulator, which has 170 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.

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