Pipeline
Orchestration pattern for sequential, dependent tasks. When work must flow through stages where each stage depends on the previous (design → implement → test → review), structure as a pipeline with explicit handoffs. Each stage completes before the next begins.
Install
npx skills add ElliotJLT/Claude-Skill-Potions --skill pipelinegit clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/pipeline ~/.claude/skills/pipelinePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Pipeline
<purpose>
Some tasks are inherently sequential - you can't test what isn't built, can't
build what isn't designed, can't review what isn't complete. This elixir
enforces pipeline discipline: define stages, ensure clean handoffs, and never
skip ahead.
</purpose>
## When To Activate
Trigger when:
- Task has natural phases that must happen in order
- Output of one stage is input to the next
- Skipping stages would cause problems
- User describes multi-phase work ("first X, then Y, then Z")
- Work involves: plan → implement → verify pattern
Do NOT trigger for:
- Independent tasks (use fan-out instead)
- Single-stage work
- Exploratory work with no clear sequence
## The Pattern
```
[Input] → [Stage 1] → [Handoff] → [Stage 2] → [Handoff] → [Stage 3] → [Output]
│ │ │
└── Checkpoint ──────────┴── Checkpoint ──────────┘
```
## Instructions
### Step 1: Define the Pipeline
Map out all stages:
```
Pipeline: [Task Name]
Stages:
1. [Stage Name] - [What happens] - [Output artifact]
2. [Stage Name] - [What happens] - [Output artifact]
3. [Stage Name] - [What happens] - [Output artifact]
Dependencies:
- Stage 2 requires: [Stage 1 output]
- Stage 3 requires: [Stage 2 output]
```
### Step 2: Define Checkpoints
Each stage needs exit criteria:Details
- Skill name
pipeline- Repository
- ElliotJLT/Claude-Skill-Potions
- Path
skills/pipeline/SKILL.md- License
- MIT
- Repo updated
- 12 February 2026
FAQ
What does the Pipeline skill do?
Orchestration pattern for sequential, dependent tasks. When work must flow through stages where each stage depends on the previous (design → implement → test → review), structure as a pipeline with explicit handoffs. Each stage completes before the next begins.
How do I install the Pipeline skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill pipeline. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Pipeline popular?
It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.
Related skills
Agent Audit
62ElliotJLT/Claude-Skill-Potions
When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.
Battle Plan
62ElliotJLT/Claude-Skill-Potions
Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.
Breadcrumbs
62ElliotJLT/Claude-Skill-Potions
Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.
Power Calculations
36dariia-m/my_claude_skills
Power, minimum detectable effect (MDE) and sample-size calculations in R for randomized experiments and survey experiments - two-arm and multi-arm designs with a shared control, ANCOVA vs change-score vs post-only, binary outcomes, within-subject differences, interactions/heterogeneity, clustered assignment, attrition and exclusions, and multiple-testing adjustment (per-test, Bonferroni bound, Holm/Romano-Wolf). Combines closed-form MDEs with Monte Carlo simulation of the exact pre-registered regression, including size checks. Use whenever the user asks for power calculations, an MDE table, "h
Loose Ends
62ElliotJLT/Claude-Skill-Potions
Before declaring work complete, checks for loose ends: unused imports, TODO comments created, missing tests, stale references, incomplete error handling. Activates after implementing features or fixes. The cleanup that always gets skipped.
Prove It
62ElliotJLT/Claude-Skill-Potions
Before declaring any task complete, actually verify the outcome. Run the code. Test the fix. Check the output. Claude's training optimizes for plausible-looking output, not verified-correct output. This skill forces the verification step that doesn't come naturally. No victory laps without proof.
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.