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

Crystallize

by eric-tramel in eric-tramel/moraine

Turn a rough feature, bug, refactor, architecture, documentation, or operations idea into a ready-to-implement local plan file.

Apache-2.0Auto-check passedAgent Workflows

Install Crystallize

skills CLI
$ npx skills add eric-tramel/moraine --skill crystallize -a claude-code

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

GitHub CLI
$ gh skill install eric-tramel/moraine crystallize --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/eric-tramel/moraine.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/moraine-dev/skills/crystallize .claude/skills/crystallize && 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
crystallize
GitHub stars
117
Token cost
~1.6k tokens
SKILL.md length
610 words
Files
2
Skills in repo
19
Repo updated
First seen
Licence
Apache-2.0

At a glance

Turn a rough feature, bug, refactor, architecture, documentation, or operations idea into a ready-to-implement local plan file.

  • The user asks to crystallize
  • SKILL.md covers Overview, Plan Artifact, Research Wave and Draft Plan, plus 2 more sections
  • Calls git
  • De-risk ambiguous work before implementation

What it does

Crystallize is an agent skill from eric-tramel/moraine. Turn a rough feature, bug, refactor, architecture, documentation, or operations idea into a ready-to-implement local plan file. Use when the user asks to crystallize, shape, refine, plan, spec, or de-risk ambiguous work before implementation; the workflow researches the codebase, public prior art, and relevant history, debates the proposed approach with subagents, and writes a final plan with no open questions.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Subagents and Intellectual property. The repository describes itself as: Unified realtime agent trace database & search MCP. The licence is Apache-2.0.

When your agent uses it

  • The user asks to crystallize
  • De-risk ambiguous work before implementation
  • The workflow researches the codebase
  • Public prior art

Example prompts

  • “/crystallize”

What it can do on your machine

Read from SKILL.md and the folder at commit 2fb4aec. 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

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Crystallize loads about 1.6k tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 610 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~107
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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 eric-tramel/moraine at commit 2fb4aec, republished under its Apache-2.0 licence (© eric-tramel). 610 words, ~1,558 tokens.

Download SKILL.mdSave it as .claude/skills/crystallize/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
crystallize
description
Turn a rough feature, bug, refactor, architecture, documentation, or operations idea into a ready-to-implement local plan file. Use when the user asks to crystallize, shape, refine, plan, spec, or de-risk ambiguous work before implementation; the workflow researches the codebase, public prior art, and relevant history, debates the proposed approach with subagents, and writes a final plan with no open questions.

Crystallize

Overview

Use this skill to convert rough input into an implementation plan that another agent can execute without needing the original discussion. The output is a single ignored local Markdown file under the gitignored plans/ directory.

Do not implement the plan while crystallizing. Inspect, research, and reason; only write the plan artifact.

Plan Artifact

Create plans/ if it does not exist:

bash
mkdir -p plans

Choose a unique filename:

  • Derive a lowercase hyphenated slug from the rough input.
  • Prefix it with a UTC timestamp from date -u +%Y%m%d-%H%M%S.
  • Use plans/<timestamp>-<slug>.md.
  • If the file already exists, append -2, -3, etc.

Keep plans/ and every plan file ignored and untracked. Do not add them to git, do not create a tracked placeholder, and do not include plan files in commits.

Research Wave

Launch parallel subagents before drafting the plan. Give each subagent the raw user input, any linked issue or document text, and explicit permission to inspect the workspace. Do not include your intended solution.

Use these research roles unless a role is plainly irrelevant:

  • CodebaseResearch: identify affected crates, modules, APIs, tests, docs, and local patterns. Return concrete file paths and constraints.
  • HistoryResearch: use Moraine MCP tools directly when prior or active agent context may matter. Search past sessions by keywords, inspect relevant sessions, and return only actionable history.
  • PublicPriorArtResearch: research public implementations, official docs, standards, libraries, and comparable approaches. Prefer primary sources and include links when external sources influence the plan.
  • RiskResearch: identify correctness, security, performance, migration, compatibility, rollout, and testing risks.

Subagent prompt shape:

text
Research this rough implementation idea for Moraine.
Focus only on <role>.
Return evidence, concrete file paths or source links, constraints, and recommended plan implications.
Do not draft the whole plan and do not assume my preferred approach.

Rough input:
<raw user input>

Wait for every required research subagent to finish. If a subagent fails, retry once with a narrower prompt. If a role is still unavailable, perform that research yourself before drafting.

Draft Plan

Synthesize the research into a concrete plan. Resolve ambiguities yourself using evidence and repository conventions. Do not ask the user open-ended questions unless the request would require an external decision that cannot be inferred safely; if that happens, stop before writing the final plan.

The draft must include implementation steps, affected files, validation, risks, and acceptance criteria. It must be specific enough that another agent can start from the plan file alone.

Show full SKILL.md (255 more words)Show less

Debate Wave

Before finalizing, launch a second parallel wave of subagents to argue against the draft plan. Provide the draft and the research summary, not private reasoning.

Use these debate roles:

  • PlanSkeptic: find bugs, missing requirements, invalid assumptions, and vague steps.
  • PlanSimplifier: force the minimal viable approach and remove unnecessary generalization.
  • PlanIdiomaticReviewer: check language, framework, library, and repo idioms.
  • PlanScopeGuard: reject scope creep and unrelated cleanup.
  • PlanValidationReviewer: verify the validation strategy would prove the change works.

Debate prompt shape:

text
Attack this implementation plan for Moraine from the <role> perspective.
Be direct. Identify blockers, weak assumptions, unnecessary scope, and missing validation.
Return required changes to make the plan ready to implement. If it is ready, say so.

Draft plan:
<draft plan>

Research summary:
<research summary>

Resolve every substantive objection. If debate agents disagree, decide the best course using evidence, repo conventions, and the user's original objective. Prefer the PlanScopeGuard when other roles request broader behavior that crosses the task boundary.

Run targeted follow-up only with the debate subagents whose objections required interpretation or whose facet changed after revision. Do not start a whole new debate wave unless the draft was fundamentally replaced.

Final Plan Requirements

The final plan must have no open questions, no TBD, no unresolved alternatives, and no "ask the user" steps. Every uncertainty must be converted into a decision, assumption, or explicit non-goal.

Write the plan file with this structure:

markdown
# <short plan title>

Status: Ready to implement
Created: <UTC timestamp>
Source input: <brief quote or summary of the rough input>

## Objective

<one concrete outcome>

## Context

- Codebase findings:
- History findings:
- Public prior art:
- Constraints:

## Decisions

- <decision and rationale>

## Non-Goals

- <explicitly out-of-scope work>

## Implementation Plan

1. <step>
   - Files:
   - Change:
   - Tests:

## Validation

- <commands, checks, fixtures, manual QA, or docs build steps>

## Risks And Mitigations

- <risk>: <mitigation>

## Acceptance Criteria

- <observable completion criterion>

## Implementation Handoff

<concise prompt an implementation agent can use to execute the plan>

Include exact file paths where possible. Include commands with expected outcomes. For stack-facing Moraine changes, include sandbox validation. For public prior art that materially influenced the plan, include source links in Context.

Before finishing, run:

bash
git check-ignore -v plans/<plan-file>.md

The expected result is that root .gitignore ignores the plan file through the plans/ rule. In the final response, report the plan path and state that it was intentionally left ignored and untracked.

© eric-tramel, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in plugins/moraine-dev/skills/crystallize of eric-tramel/moraine.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 2fb4aec

Compare with similar skills

Crystallize 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.

Crystallize compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Crystallize this skilleric-tramel/moraine117—~1.6kAutomated safety check: PassApache-2.0
Survey Patternstobihagemann/turbo407—~539Automated safety check: PassMIT
Patent Brainstorm Path Trackerillusionaireal/oh-my-patent103—~1.6kAutomated safety check: PassMIT
Innovationtravisjneuman/.claude101—~2.7kAutomated safety check: PassMIT
Development AssistantRobThePCGuy/Claude-Patent-Creator196—~1.3kAutomated safety check: NotesMIT
Spec Contract Compliance Reviewbbartling/open-fdd172—~1.4kAutomated safety check: PassCustom licence

Similar skills

  • Survey Patterns

    tobihagemann/turbo

    Survey the codebase for analogous features, reusable utilities, and existing patterns relevant to a proposed change, reading any source the task names outside this repo.

    407 GitHub stars~539 tokensUpdated yesterday
    Legal & ComplianceAuto-check passed

  • Patent Brainstorm Path Tracker

    illusionaireal/oh-my-patent

    Records, branches and visualizes the rounds of a patent brainstorming session, scoring each candidate and letting you restore an abandoned idea.

    103 GitHub stars~1.6k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Innovation

    travisjneuman/.claude

    Innovation management expertise for innovation frameworks (Design Thinking, Stage-Gate), ideation processes, innovation portfolio management, venture capital, open innovation, and IP strategy.

    101 GitHub stars~2.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Development Assistant

    RobThePCGuy/Claude-Patent-Creator

    Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.

    196 GitHub stars~1.3k tokensUpdated yesterday
    Agent WorkflowsAuto-check: notes

  • Spec Contract Compliance Review

    bbartling/open-fdd

    A skill your agent uses to compare any codebase against a specification, API contract, protocol, policy, RFC, security baseline, or product requirements document.

    172 GitHub stars~1.4k tokensUpdated today
    Legal & ComplianceAuto-check passed

  • Poweruser Feature Audit

    pydantic/pydantic-ai

    Official

    Independent power-user audit of a big new-feature PR. An agent skill from pydantic/pydantic-ai.

    20k GitHub stars~2.9k tokensUpdated today
    Testing & QAAuto-check passed

More from eric-tramel/moraine

All 19 skills in this repo

  • Moraine Release Publisher

    eric-tramel/moraine

    Cuts and publishes a Moraine release end to end: version bump PR, tag, GitHub release notes, workflow check and PyPI package verification.

    117 GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed

  • Moraine Release Notes

    eric-tramel/moraine

    Rewrites a moraine GitHub release body into a usage-focused format with install block, what's new, platform table, upgrade notes and one deduplicated changelog.

    117 GitHub stars~2.7k tokensUpdated 3 days ago
    Auto-check passed

  • Multi-Persona Code Review

    eric-tramel/moraine

    Coordinates a delegated review of a Moraine PR or local change by seven focused reviewer subagents, merges their findings and follows up on the fixes.

    117 GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Elegance-Focused Code Review

    eric-tramel/moraine

    Looks at a pull request for the smallest good design, hunting for simplifications and architectural moves that remove whole classes of problems.

    117 GitHub stars~473 tokensUpdated 3 days ago
    Auto-check passed

  • Idiomatic Code Review

    eric-tramel/moraine

    Reviews a pull request for idiomatic implementation: use of the language, standard library, ecosystem conventions and the repository's own patterns.

    117 GitHub stars~469 tokensUpdated 3 days ago
    Auto-check passed

  • Code Review Security Review

    eric-tramel/moraine

    Review a PR through the CodeReviewSecurityReview persona. An agent skill from eric-tramel/moraine.

    117 GitHub stars~497 tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Crystallize

What does Crystallize do?

Turn a rough feature, bug, refactor, architecture, documentation, or operations idea into a ready-to-implement local plan file. Crystallize is an agent skill from eric-tramel/moraine. Turn a rough feature, bug, refactor, architecture, documentation, or operations idea into a ready-to-implement local plan file.

When should I use Crystallize?

Crystallize fits situations like: the user asks to crystallize; de-risk ambiguous work before implementation; the workflow researches the codebase; public prior art.

How do I install Crystallize in Claude Code?

Run `npx skills add eric-tramel/moraine --skill crystallize -a claude-code`. Or copy the skill folder (plugins/moraine-dev/skills/crystallize in eric-tramel/moraine) into .claude/skills/crystallize in your project. Claude Code loads it when a task matches its description.

How do I install Crystallize in Codex?

Run `npx skills add eric-tramel/moraine --skill crystallize -a codex`. Or copy the skill folder (plugins/moraine-dev/skills/crystallize in eric-tramel/moraine) into .agents/skills/crystallize in your project. Codex loads it when a task matches its description.

Can I use Crystallize 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 eric-tramel/moraine --skill crystallize -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/crystallize, .gemini/skills/crystallize, .github/skills/crystallize and .opencode/skills/crystallize in your project.

What does Crystallize need to run?

Going by SKILL.md and its folder, Crystallize needs the command-line tools its instructions call (git).

Does Crystallize access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Crystallize 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 Crystallize use?

Crystallize is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Crystallize use?

About 1.6k tokens (SKILL.md is roughly 6.2k 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 Crystallize?

Skills that share tags, products or a category with Crystallize: Survey Patterns (tobihagemann/turbo, 407 stars), Patent Brainstorm Path Tracker (illusionaireal/oh-my-patent, 103 stars), Innovation (travisjneuman/.claude, 101 stars) and Development Assistant (RobThePCGuy/Claude-Patent-Creator, 196 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Crystallize?

eric-tramel (a GitHub user) maintains it in eric-tramel/moraine, which has 117 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 5, 2026.

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