workflow-patterns
Agent workflowswshobson/agentsskills.sh ↗
Installs
9,358
deduplicated, at the last sync
Since we started
+1.1%
40 readings, about 2 hours apart. Not a live curve.
Our category
Agent workflows
ours
Last read
Sep 3, 2026
from the directory
Our brief
oursThis skill guides users through a structured 11-step Test-Driven Development (TDD) workflow for implementing tasks. It provides detailed patterns for managing task lifecycles, including writing failing tests (RED), implementing minimum code (GREEN), refactoring, and verifying test coverage. The process also includes steps for documenting deviations and creating focused git commits.
- Focused git commit
- Updated plan files
- Working code base
- Test reports
- Project plan file (plan.md)
- Code repository
- Testing framework/tools
not detected
The evidence provides no information regarding required payment status for using the skill.
not detected
The evidence provides no information regarding required user registration for using the skill.
The skill cannot verify if a task meets external business requirements or decide if all necessary dependencies have been accounted for outside of updating tech-stack.md and plan.md.
Evidenceplugins/conductor/skills/workflow-patterns/references/details.md:1-108plugins/conductor/skills/workflow-patterns/SKILL.md:1-39
# workflow-patterns — detailed patterns and worked examples
## TDD Task Lifecycle
Follow these 11 steps for each task:
### Step 1: Select Next Task
Read plan.md and identify the next pending `[ ]` task. Select tasks in order within the current phase. Do not skip ahead to later phases.
### Step 2: Mark as In Progress
Update plan.md to mark the task as `[~]`:
```markdown
- [~] **Task 2.1**: Implement user validation
```
Commit this status change separately from implementation.
### Step 3: RED - Write Failing Tests
Write tests that define the expected behavior before writing implementation:
- Create test file if needed
- Write test cases covering happy path
- Write test cases covering edge cases
- Write test cases covering error conditions
- Run tests - they should FAIL
Example:
```python
def test_validate_user_email_valid():
user = User(email="test@example.com")
assert user.validate_email() is True
def test_validate_user_email_invalid():
user = User(email="invalid")
assert user.validate_email() is False
```
### Step 4: GREEN - Implement Minimum Code
Write the minimum code necessary to make tests pass:
- Focus on making tests green, not perfection
- Av--- name: workflow-patterns description: Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol. version: 1.0.0 --- # Workflow Patterns Guide for implementing tasks using Conductor's TDD workflow, managing phase checkpoints, handling git commits, and executing the verification protocol that ensures quality throughout implementation. ## When to Use This Skill - Implementing tasks from a track's plan.md - Following TDD red-green-refactor cycle - Completing phase checkpoints - Managing git commits and notes - Understanding quality assurance gates - Handling verification protocols - Recording progress in plan files ## Detailed patterns and worked examples Detailed pattern documentation lives in `references/details.md`. Read that file when the navigation tier above is insufficient. ## Best Practices 1. **Never skip RED**: Always write failing tests first 2. **Small commits**: One logical change per commit 3. **Immediate updates**: Update plan.md right after task completion 4. **Wait for approval**: Never skip checkpoint verification 5. **Rich git notes**:
Read 2 of 2 text files in the skill.
Installfrom the directory
npx skills add https://github.com/wshobson/agentsInstalling happens there, not here. We are an index with an opinion, not a mirror.
What is inside itfrom the directory
2 files — names only. The directory does not report sizes.
What the auditors foundfrom the directory
A skill is instructions your agent will follow and scripts it may run, so who checked it matters as much as how many people installed it.
Installs, reading by readingours
Axis starts at 9.3k, not zero — the range is 9.3k to 9.4k.
Asked out loudspoken, not typed
The same skill in the words people use speaking to an assistant rather than typing into a box. Each one carries the situation it came from, and each answer says only what the skill's own files support.
You should first read `plan.md` to identify the next pending task, selecting tasks in order within the current phase. Then, you must update `plan.md` to mark that task as in progress.
Yes, the workflow requires that you always write tests that define expected behavior and ensure they fail first. This is a core best practice of the TDD cycle.