paper-making

Handcraft paper from plant fibres — fibre harvesting, pulping, sheet forming with a mould and deckle, pressing, and drying. Covers fibre sources (cotton, kozo, abaca, recycled paper), beating methods, sizing, and decorative techniques. Use when making handmade paper for art, stationery, or bookbinding, when creating unique textured or embedded paper for special projects, or when learning traditional paper making as a craft practice.

9 stars

Best use case

paper-making is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Handcraft paper from plant fibres — fibre harvesting, pulping, sheet forming with a mould and deckle, pressing, and drying. Covers fibre sources (cotton, kozo, abaca, recycled paper), beating methods, sizing, and decorative techniques. Use when making handmade paper for art, stationery, or bookbinding, when creating unique textured or embedded paper for special projects, or when learning traditional paper making as a craft practice.

Teams using paper-making should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/paper-making/SKILL.md --create-dirs "https://raw.githubusercontent.com/pjt222/agent-almanac/main/i18n/caveman-lite/skills/paper-making/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/paper-making/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How paper-making Compares

Feature / Agentpaper-makingStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Handcraft paper from plant fibres — fibre harvesting, pulping, sheet forming with a mould and deckle, pressing, and drying. Covers fibre sources (cotton, kozo, abaca, recycled paper), beating methods, sizing, and decorative techniques. Use when making handmade paper for art, stationery, or bookbinding, when creating unique textured or embedded paper for special projects, or when learning traditional paper making as a craft practice.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Paper Making

Handcraft paper from plant fibres using traditional mould and deckle sheet-forming techniques.

## When to Use

- You want to make handmade paper for art, stationery, or bookbinding
- You have plant fibres (cotton linters, kozo bark, recycled paper) to process
- You want to create unique textured or embedded paper for special projects
- You are teaching or learning traditional paper making as a craft practice

## Inputs

- **Required**: Fibre source (cotton linters, recycled paper, kozo bark, or plant stalks)
- **Required**: Mould and deckle (a flat screen frame with a removable top frame)
- **Required**: Vat or tub large enough to submerge the mould (basin, plastic tub)
- **Required**: Water (generous amounts)
- **Optional**: Blender for pulping (dedicated to paper making — not for food afterward)
- **Optional**: Pressing boards and felt sheets (couching felts)
- **Optional**: Sizing agent (gelatin, methylcellulose, or rice starch)
- **Optional**: Additives: flower petals, threads, pigments, plant material for embedding

## Procedure

### Step 1: Prepare the Fibre

Different fibre sources require different preparation.

```
Fibre Sources and Preparation:

RECYCLED PAPER (easiest — start here):
1. Tear paper into 1-inch squares (avoid glossy or heavily printed paper)
2. Soak in water for 2-4 hours (overnight is better)
3. Blend in small batches: handful of soaked paper + 2 cups water
4. Blend until smooth with no visible paper chunks (30-60 seconds)

COTTON LINTERS (archival quality):
1. Tear cotton linter sheets into small pieces
2. Soak overnight in warm water
3. Blend to desired consistency:
   - Short blend (15s) = textured, chunky paper
   - Long blend (60s) = smooth, fine paper

KOZO (Japanese paper — strong, translucent):
1. Strip bark from kozo (paper mulberry) branches
2. Soak in water, then cook in alkaline solution
   (wood ash lye or soda ash) for 2-3 hours until soft
3. Rinse thoroughly to remove alkali
4. Beat by hand with a wooden mallet on a flat stone
   until fibres separate (do not blend — hand beating
   preserves long fibres that give kozo its strength)

PLANT STALKS (experimental — iris, daylily, corn husk):
1. Harvest fibrous stalks after growing season
2. Ret (soak) for 1-2 weeks to soften
3. Cook in alkaline solution for 2-3 hours
4. Rinse and beat by hand
5. Results vary — experiment with fibre length and beating time
```

**Got:** A slurry of prepared fibre (pulp) with the consistency of thin oatmeal.

**If fail:** If the pulp is too chunky, blend longer. If too thin and watery, add more fibre. The consistency should coat the back of a spoon lightly.

### Step 2: Prepare the Vat

Set up the sheet-forming station.

```
Vat Setup:
1. Fill a vat (plastic tub, basin) with water — deep enough to
   fully submerge the mould (at least 4 inches of water)
2. Add prepared pulp to the vat
3. Stir thoroughly — fibres must be evenly suspended, not clumped
4. Pulp-to-water ratio: approximately 1 part pulp to 10-20 parts water
   - More pulp = thicker paper
   - Less pulp = thinner, more translucent paper
5. Stir before EVERY sheet — fibres settle quickly

Test: dip your hand in the vat. The water should be milky/cloudy
with evenly suspended fibres. If you can see clumps, stir more.
```

**Got:** A vat of evenly suspended pulp ready for sheet forming.

**If fail:** If fibres clump despite stirring, the fibre may be too long. Blend briefly to shorten the fibres, then re-suspend.

### Step 3: Form the Sheet

The mould and deckle technique is the heart of paper making.

```
Sheet Forming Protocol:

THE TOOLS:
- Mould: a flat frame with a fine screen (window screen or brass mesh)
- Deckle: a second frame that sits on top of the mould (acts as an edge)
- Together they create a shallow tray that holds the pulp

FORMING:
1. Stir the vat thoroughly
2. Hold the mould screen-side up with the deckle on top, gripping both
3. Dip the mould+deckle into the vat at an angle (far edge first)
4. Level the mould underwater, then lift straight up in one smooth motion
5. As the mould clears the water, shake gently side-to-side and
   front-to-back (2-3 shakes each direction) — this interlocks the fibres
6. Hold level and let water drain through the screen (30-60 seconds)
7. Remove the deckle carefully — lift straight up so water does not
   drip onto the formed sheet

THE SHAKE:
- The side-to-side and front-to-back shakes are critical
- They interlock fibres in both directions, creating strength
- Without shaking, the sheet tears easily in one direction
- Practice on scrap pulp — the shake is the skill that takes longest to learn

THICKNESS CONTROL:
- Thin paper: less pulp in the vat, faster pull-through
- Thick paper: more pulp, slower pull-through
- Even thickness comes from pulling the mould through the vat
  smoothly and leveling before lifting
```

**Got:** A wet sheet of paper sitting evenly on the mould screen with consistent thickness and no thin spots or holes.

**If fail:** If the sheet has thin spots, the mould was not level during the lift. If the sheet is thick on one side, the mould was tilted during draining. Practice the lift motion: smooth, level, and confident.

### Step 4: Couch, Press, and Dry

Transfer the wet sheet and remove water.

```
COUCHING (transferring the sheet):
1. Place a damp felt or blanket on a flat surface
2. In one smooth motion, flip the mould face-down onto the felt
3. Press the back of the screen gently with a sponge to release the sheet
4. Lift the mould straight up — the sheet should stay on the felt
5. Place another damp felt on top of the sheet
6. Repeat: form sheet → couch onto felt → cover with felt → form next sheet

Couching stack: felt / sheet / felt / sheet / felt / sheet / felt

PRESSING:
1. Place the couching stack between pressing boards
2. Apply even pressure:
   - Screw press (ideal)
   - Weight (heavy books, concrete blocks — 20+ kg)
   - Stand on it (place boards on floor, step on carefully)
3. Press for 15-30 minutes — water should squeeze out from the sides
4. Replace wet felts with dry ones and press again for best results

DRYING:
Option A — Air dry on boards:
1. Carefully peel each sheet from its felt
2. Place on a smooth board (glass, formica, or MDF)
3. Smooth gently with a damp sponge to remove wrinkles
4. Sheets will dry flat against the board (12-24 hours)
5. Peel gently when dry — edges release first

Option B — Hang dry:
1. Peel sheets from felts and hang on a clothesline with clips
2. Faster drying but produces a wavy, textured surface
3. Suitable for art paper where texture is desired

Option C — Iron dry (fast):
1. Place damp sheet between clean cotton cloths
2. Iron on medium heat until dry (5-10 minutes)
3. Produces a smooth, flat sheet quickly
```

**Got:** Finished sheets of handmade paper — dry, flat (if board-dried), with deckled edges and visible fibre texture.

**If fail:** If sheets tear during couching, the mould was lifted before enough water drained. Let the mould drain longer before flipping. If sheets wrinkle during drying, they were not pressed firmly enough or the drying surface was not smooth.

## Validation

- [ ] Fibre was prepared to an even, lump-free pulp
- [ ] Pulp was evenly suspended in the vat before each sheet
- [ ] Sheet forming included the interlocking shake in both directions
- [ ] Sheets have consistent thickness without thin spots or holes
- [ ] Pressing removed sufficient water before drying
- [ ] Finished sheets are dry, intact, and suitable for their intended use

## Pitfalls

- **Not stirring before each sheet**: Fibres settle in seconds. Every sheet needs a fresh stir or the last sheets will be thin and sparse
- **Tearing during couching**: Too much water still on the mould, or the couching motion was too slow. Drain longer and flip in one confident motion
- **Uneven thickness**: The mould was not level during the lift and drain. Practice the motion slowly, focusing on keeping the frame horizontal
- **Paper too fragile**: The fibres may not be beaten enough (too long, too stiff) or the sheet may be too thin. Beat longer or use more pulp
- **Mould warps when wet**: Wooden moulds can warp. Use marine-grade wood or seal with waterproofing. Aluminium frames avoid this issue entirely

## Related Skills

- `forage-plants` — fibre plants can be foraged in the wild; understanding plant anatomy helps identify suitable fibre sources

Related Skills

skill-name-here

9
from pjt222/agent-almanac

One to three sentences describing what this skill accomplishes, followed by key activation triggers. This field is the primary mechanism agents use to decide whether to activate the skill — it is read during discovery before the full body is loaded. Start with a verb. Include the most important "when to use" conditions inline. Max 1024 characters.

write-vignette

9
from pjt222/agent-almanac

Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.

write-validation-documentation

9
from pjt222/agent-almanac

Write IQ/OQ/PQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.

write-testthat-tests

9
from pjt222/agent-almanac

Write comprehensive testthat (edition 3) tests for R package functions. Covers test organization, expectations, fixtures, mocking, snapshot tests, parameterized tests, and achieving high coverage. Use when adding tests for new package functions, increasing test coverage for existing code, writing regression tests for bug fixes, or setting up test infrastructure for a package that lacks it.

write-standard-operating-procedure

9
from pjt222/agent-almanac

Write a GxP-compliant Standard Operating Procedure (SOP). Covers regulatory SOP template structure (purpose, scope, definitions, responsibilities, procedure, references, revision history), approval workflow design, periodic review scheduling, and operational procedures for system use. Use when a new validated system requires operational procedures, when existing informal procedures need formalisation, when an audit finding cites missing procedures, when a change control triggers SOP updates, or when periodic review identifies outdated procedural content.

write-roxygen-docs

9
from pjt222/agent-almanac

Write roxygen2 documentation for R package functions, datasets, and classes. Covers all standard tags, cross-references, examples, and generating NAMESPACE entries. Follows tidyverse documentation style. Use when adding documentation to new exported functions, documenting internal helpers or datasets, documenting S3/S4/R6 classes and methods, or fixing documentation-related R CMD check notes.

write-incident-runbook

9
from pjt222/agent-almanac

Create structured incident runbooks with diagnostic steps, resolution procedures, escalation paths, and communication templates for effective incident response. Use when documenting response procedures for recurring alerts, standardizing incident response across an on-call rotation, reducing MTTR with clear diagnostic steps, creating training materials for new team members, or linking alert annotations directly to resolution procedures.

write-helm-chart

9
from pjt222/agent-almanac

Create production-ready Helm charts for Kubernetes application deployment with templating, values management, chart dependencies, hooks, and testing. Covers chart structure, Go template syntax, values.yaml design, chart repositories, versioning, and best practices for maintainable and reusable charts. Use when packaging a Kubernetes application for repeatable deployments, parameterizing manifests for multiple environments, managing complex multi-component applications with dependencies, or standardizing deployment practices with versioned rollback capability across teams.

write-continue-here

9
from pjt222/agent-almanac

Write a CONTINUE_HERE.md file capturing current session state so a fresh Claude Code session can pick up where this one left off. Covers assessing recent work, structuring the continuation file with objective, completed, in-progress, next-steps, and context sections, and verifying the file is actionable. Use when ending a session with unfinished work, handing off context between sessions, or preserving task state that git alone cannot capture.

write-claude-md

9
from pjt222/agent-almanac

Create an effective CLAUDE.md file that provides project-specific instructions to AI coding assistants. Covers structure, common sections, do/don't patterns, and integration with MCP servers and agent definitions. Use when starting a new project where AI assistants will be used, improving AI behavior on an existing project, documenting project conventions and constraints, or integrating MCP servers or agent definitions into a project workflow.

vishnu-bhaga

9
from pjt222/agent-almanac

Preservation and sustenance — maintaining working state under perturbation, memory anchoring, consistency enforcement, and protective stabilization. Maps Vishnu's sustaining presence to AI reasoning: holding what works steady, anchoring verified knowledge against drift, and ensuring continuity through change. Use when a working approach is at risk from scope creep, when context drift threatens verified knowledge, after shiva-bhaga dissolution to protect what survived, when a long session risks losing earlier decisions through context compression, or before making changes to a currently functioning system.

version-ml-data

9
from pjt222/agent-almanac

Version machine learning datasets using DVC (Data Version Control) with remote storage backends, build reproducible data pipelines with dependency tracking, integrate with Git workflows, and ensure data lineage for model reproducibility. Use when versioning large datasets that do not fit in Git, tracking data changes alongside code changes, ensuring ML experiment reproducibility, sharing datasets across team members, or auditing data lineage for compliance requirements.