WI

windsurf-core-workflow-b

Automates development tasks using Windsurf workflows and memories.

Install

mkdir -p .claude/skills/windsurf-core-workflow-b && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/6878" && unzip -o skill.zip -d .claude/skills/windsurf-core-workflow-b && rm skill.zip

Installs to .claude/skills/windsurf-core-workflow-b

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Execute Windsurf''s secondary workflow: Workflows, Memories, and reusable
73 charsno explicit “when” trigger
Intermediate

Key capabilities

  • →Create reusable multi-step automation sequences
  • →Define custom slash commands for Cascade
  • →Store persistent facts across sessions
  • →Chain multiple workflows together

How it works

Workflows are markdown files in `.windsurf/workflows/` that become slash commands, and memories are persistent facts stored locally.

Inputs & outputs

You give it
Markdown files defining workflows and user prompts for memories
You get back
Executable slash commands, persistent facts, and automated task execution

When to use windsurf-core-workflow-b

  • →Automating feature scaffolding
  • →Storing persistent project context
  • →Creating custom editor slash commands
  • →Standardizing repetitive coding steps

About this skill

Devin Desktop Customizations

Overview

Devin Desktop is the current name for Windsurf. Select the smallest customization that matches the task instead of treating Workflows and Memories as interchangeable automation.

Prerequisites

  • Devin Desktop with Cascade enabled
  • A version-controlled workspace for shared customizations
  • A concrete behavior or procedure to encode

Authentication

Rules, AGENTS.md, Workflows, and Skills require no separate authentication. MCP-backed steps use provider OAuth or environment-backed secrets; never embed tokens in customization files.

Tool Use

  • Use Read to inspect only the repository files and configuration needed for the request.
  • Use Grep to locate relevant settings, rules, logs, or code without broad collection.
  • Use Write only for a new artifact the user requested; never write credentials or unreviewed production configuration.
  • Use Edit for bounded, reviewable changes and preserve unrelated user work.
  • Use only the command-scoped Bash entries declared in frontmatter, with non-destructive checks before mutations.

Instructions

Step 1: Choose the mechanism

MechanismActivationUse for
Rulealways_on, glob, model_decision, or manualShort behavioral constraints
AGENTS.mdRoot always-on; subdirectory location-scopedRepository conventions without frontmatter
WorkflowManual only through /workflow-nameRepeatable prompt sequences
SkillDynamic model invocation or @mentionMulti-step procedures with supporting files
MemoryAutomatic local retrievalEphemeral facts; not durable team knowledge

Prefer .devin/rules/*.md for Rules. Legacy .windsurf/rules/ remains a fallback. Keep durable team knowledge in version control rather than relying on local auto-generated Memories.

Step 2: Create a Rule or AGENTS.md

Use a Rule for controlled activation:

---
trigger: glob
globs: "src/api/**/*.ts"
---

# API constraints
- Validate external input at the route boundary.
- Return the repository's standard error envelope.

Use a root or directory-level AGENTS.md when location alone should determine scope.

Step 3: Create a Workflow

Save manual procedures under .windsurf/workflows/<name>.md, within the documented 12,000-character limit:

# Review current pull request

1. Read the diff against the target branch.
2. Run the repository's required tests.
3. Report correctness, security, and regression findings with file locations.
4. Stop and ask for clarification when a finding cannot be resolved safely.

Invoke it explicitly as /review-current-pr. Workflows are Cascade-specific and are not automatically selected.

Step 4: Create a Skill

Use .windsurf/skills/<name>/SKILL.md when the procedure needs scripts, templates, or reference files. Devin Desktop also discovers cross-agent skills under .agents/skills/; use that location when portability is intentional.

Step 5: Verify activation

Test one matching and one non-matching request. Confirm a Rule's trigger, a Workflow's slash command, or a Skill's dynamic/explicit invocation. Record the file location and visible outcome.

Output

Create the selected customization in its documented location, explain why it is a Rule, AGENTS.md, Workflow, Skill, or Memory, state its activation behavior and scope, and provide matching and non-matching verification evidence.

Error Handling

IssueResponse
Workflow is not listedConfirm .windsurf/workflows/*.md, discovery scope, and character limit
Skill is not invokedImprove name/description, then test with @mention
Rule applies too broadlyReplace always_on with a narrower glob, model decision, or AGENTS.md scope
Memory is staleRemove it through Customizations and encode durable knowledge as a Rule

Examples

"Use a Workflow for a release checklist that a human must start; use a Skill for test-and-fix guidance Cascade should select automatically with bundled scripts."

Resources

Related Skill

Use windsurf-policy-guardrails when the customization must be enforced through Hooks, CI, repository protection, or an organization-wide administrative policy.

Prerequisites

Windsurf with Cascade enabledUnderstanding of `windsurf-core-workflow-a` (Write mode)`.windsurfrules` configured

Limitations

  • →Workflows can exceed context limits if too long
  • →Memories may not be recalled if relevance score is low
  • →Slash commands require files to be in `.windsurf/workflows/`

How it compares

This skill allows defining and executing custom, multi-step automation sequences and persistent facts, unlike manual, one-off command execution.

Compared to similar skills

windsurf-core-workflow-b side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
windsurf-core-workflow-b (this skill)12moReviewIntermediate
changelog-automation84moReviewIntermediate
configured-agent510moReviewBeginner
plugin-settings27moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

More by jeremylongshore

View all by jeremylongshore →

analyzing-logs

jeremylongshore

Analyze application logs to detect performance issues, identify error patterns, and improve stability by extracting key insights.

14123

ollama-setup

jeremylongshore

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

1167

backtesting-trading-strategies

jeremylongshore

Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".

1071

generating-database-seed-data

jeremylongshore

Process this skill enables AI assistant to generate realistic test data and database seed scripts for development and testing environments. it uses faker libraries to create realistic data, maintains relational integrity, and allows configurable data volumes. u... Use when working with databases or data models. Trigger with phrases like 'database', 'query', or 'schema'.

1033

cursor-codebase-indexing

jeremylongshore

Execute set up and optimize Cursor codebase indexing. Triggers on "cursor index setup", "codebase indexing", "index codebase", "cursor semantic search". Use when working with cursor codebase indexing functionality. Trigger with phrases like "cursor codebase indexing", "cursor indexing", "cursor".

885

testing-mobile-apps

jeremylongshore

Execute mobile app testing on iOS and Android devices/simulators. Use when performing specialized testing. Trigger with phrases like "test mobile app", "run iOS tests", or "validate Android functionality".

810

You might also like

changelog-automation

wshobson

Automate changelog generation from commits, PRs, and releases following Keep a Changelog format. Use when setting up release workflows, generating release notes, or standardizing commit conventions.

885

configured-agent

anthropics

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.

585

plugin-settings

anthropics

This skill should be used when the user asks about "plugin settings", "store plugin configuration", "user-configurable plugin", ".local.md files", "plugin state files", "read YAML frontmatter", "per-project plugin settings", or wants to make plugin behavior configurable. Documents the .claude/plugin-name.local.md pattern for storing plugin-specific configuration with YAML frontmatter and markdown content.

217

skill-builder

ruvnet

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the Claude Skills specification.

45

skill-creator-doctor

ananddtyagi

Create, repair, maintain, and consolidate skills. This skill should be used when users want to create new skills, fix broken skills that won't load, diagnose skill system issues, maintain skill health, or consolidate duplicate/obsolete skills. Automatically detects and repairs common skill loading problems including missing registry entries, metadata format issues, and structural problems. Provides comprehensive skill ecosystem management including duplicate detection, merge workflows, and archival processes.

17

slash-command-creator

greatSumini

Guide for creating Claude Code slash commands. Use when the user wants to create a new slash command, update an existing slash command, or asks about slash command syntax, frontmatter options, or best practices.

15

Search skills

Search the agent skills registry