Agent skill

Evanflow Improve Architecture

by evanklem in evanklem/evanflow

Identify refactoring opportunities by surfacing architectural friction.

Custom licenceAuto-check passedDevelopment

Install Evanflow Improve Architecture

skills CLI
$ npx skills add evanklem/evanflow --skill evanflow-improve-architecture -a claude-code

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

GitHub CLI
$ gh skill install evanklem/evanflow evanflow-improve-architecture --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/evanklem/evanflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evanflow-improve-architecture .claude/skills/evanflow-improve-architecture && 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
evanflow-improve-architecture
GitHub stars
418
Token cost
~950 tokens
SKILL.md length
457 words
Files
1
Skills in repo
14
Repo updated
First seen
Licence
Custom licence

At a glance

Identify refactoring opportunities by surfacing architectural friction.

  • Works in 6 steps: Read Context First → Identify Candidates → Apply the Deletion Test → …
  • Reviewing code for refactoring
  • SKILL.md covers Vocabulary, When to Use, The Flow and Hard Rules, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Evanflow Improve Architecture is an agent skill from evanklem/evanflow. Identify refactoring opportunities by surfacing architectural friction. Apply the deletion test, deep-modules vocabulary, and seams analysis. Each opportunity becomes its own evanflow-writing-plans cycle. Use when reviewing code for refactoring, when a file has grown too large, or when architecture concerns surface during feature work.

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Refactoring and Planning. The repository describes itself as: A TDD-driven iterative feedback loop for software development. 16 cohesive Claude Code skills walk an idea from brainstorm → plan → execute → iterate, with checkpoints throughout.

When your agent uses it

  • Reviewing code for refactoring
  • A file has grown too large
  • Architecture concerns surface during feature work

Example prompts

  • “/evanflow-improve-architecture”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Read Context First
  2. Identify Candidates
  3. Apply the Deletion Test
  4. Embedded Grill — Candidate Selection
  5. Present Opportunities
  6. Hand Off Per Opportunity

What it can do on your machine

Read from SKILL.md and the folder at commit c9ae21f. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Evanflow Improve Architecture loads about 950 tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 457 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~950

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 457 words (~950 tokens).

“See evanflow meta-skill. Key terms: module, interface, depth, seam, adapter, deletion test.”

— opening of SKILL.md by evanklem, Custom licence
name
evanflow-improve-architecture

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/evanflow-improve-architecture of evanklem/evanflow.

Open the folder on GitHubat commit c9ae21f

Compare with similar skills

Evanflow Improve Architecture 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.

Evanflow Improve Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Evanflow Improve Architecture this skillevanklem/evanflow418—~950Automated safety check: PassCustom licence
Plan WritingxenitV1/Antigravity-Workflows1308 repos~994Automated safety check: PassMIT
Workflowbrianlovin/agent-config3771 repos~687Automated safety check: PassNone
Write Specdzhng/skills1k—~4.7kAutomated safety check: PassMIT
Improvefossasia/eventyay-interpretation1.6k10 repos~3.7kAutomated safety check: WarnMIT
Claude Code Clawdbotwin4r/claude-code-clawdbot-skill123—~2.5kAutomated safety check: WarnNone

Similar skills

  • Plan Writing

    xenitV1/Antigravity-Workflows

    Structured task planning with clear breakdowns, dependencies, and verification criteria.

    130 GitHub starsUsed in 8 repos~994 tokens
    DevelopmentAuto-check passed
  • Workflow

    brianlovin/agent-config

    Workflow orchestration for complex coding tasks. An agent skill from brianlovin/agent-config.

    377 GitHub starsUsed in 1 repo~687 tokens
    DevelopmentAuto-check passed
  • Write Spec

    dzhng/skills

    Break large features into independently verifiable, human-reviewable slices under a feature directory in specs/.

    1k GitHub stars~4.7k tokensUpdated 3 days ago
    DevelopmentAuto-check passed
  • Improve

    fossasia/eventyay-interpretation

    Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute.

    1.6k GitHub starsUsed in 10 repos~3.7k tokens
    Agent WorkflowsAuto-check: warnings
  • Claude Code Clawdbot

    win4r/claude-code-clawdbot-skill

    Run Claude Code (Anthropic) from this host via the claude CLI (Agent SDK) in headless mode (-p) for codebase analysis, refactors, test fixing, and structured output.

    123 GitHub stars~2.5k tokensUpdated 8 mo ago
    AI & LLM EngineeringAuto-check: warnings
  • One Three One Rule

    Tommy-yw/RunbookHermes

    Structured decision-making framework for technical proposals and trade-off analysis.

    546 GitHub starsUsed in 3 repos~1.3k tokens
    Agent WorkflowsAuto-check passed

More from evanklem/evanflow

All 14 skills in this repo
  • Evanflow

    evanklem/evanflow

    Meta skill for the EvanFlow system. An agent skill from evanklem/evanflow.

    418 GitHub stars~2.5k tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow Coder Overseer

    evanklem/evanflow

    Orchestrate parallel implementation with coder/overseer pairs.

    418 GitHub stars~3.9k tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow Glossary

    evanklem/evanflow

    Extract canonical domain terms into CONTEXT.md. An agent skill from evanklem/evanflow.

    418 GitHub stars~829 tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow Prd

    evanklem/evanflow

    Synthesize a PRD (Product Requirements Document) for a big new feature.

    418 GitHub stars~817 tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow QA

    evanklem/evanflow

    Conversational bug discovery → issue draft. An agent skill from evanklem/evanflow.

    418 GitHub stars~718 tokensUpdated 4 mo ago
    Auto-check passed
  • Evanflow TDD

    evanklem/evanflow

    Vertical-slice TDD for any production code. An agent skill from evanklem/evanflow.

    418 GitHub stars~2k tokensUpdated 4 mo ago
    Auto-check passed

Questions about Evanflow Improve Architecture

What does Evanflow Improve Architecture do?

Identify refactoring opportunities by surfacing architectural friction. Evanflow Improve Architecture is an agent skill from evanklem/evanflow. Identify refactoring opportunities by surfacing architectural friction.

When should I use Evanflow Improve Architecture?

Evanflow Improve Architecture fits situations like: reviewing code for refactoring; A file has grown too large; architecture concerns surface during feature work.

How do I install Evanflow Improve Architecture in Claude Code?

Run `npx skills add evanklem/evanflow --skill evanflow-improve-architecture -a claude-code`. Or copy the skill folder (skills/evanflow-improve-architecture in evanklem/evanflow) into .claude/skills/evanflow-improve-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Evanflow Improve Architecture in Codex?

Run `npx skills add evanklem/evanflow --skill evanflow-improve-architecture -a codex`. Or copy the skill folder (skills/evanflow-improve-architecture in evanklem/evanflow) into .agents/skills/evanflow-improve-architecture in your project. Codex loads it when a task matches its description.

Can I use Evanflow Improve Architecture 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 evanklem/evanflow --skill evanflow-improve-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evanflow-improve-architecture, .gemini/skills/evanflow-improve-architecture, .github/skills/evanflow-improve-architecture and .opencode/skills/evanflow-improve-architecture in your project.

What does Evanflow Improve Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Evanflow Improve Architecture is instructions for the agent only.

Does Evanflow Improve Architecture access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Evanflow Improve Architecture 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 Evanflow Improve Architecture use?

Evanflow Improve Architecture has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Evanflow Improve Architecture use?

About 950 tokens (SKILL.md is roughly 3.8k 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 Evanflow Improve Architecture?

Skills that share tags, products or a category with Evanflow Improve Architecture: Plan Writing (xenitV1/Antigravity-Workflows, 130 stars), Workflow (brianlovin/agent-config, 377 stars), Write Spec (dzhng/skills, 1k stars) and Improve (fossasia/eventyay-interpretation, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evanflow Improve Architecture?

evanklem (a GitHub user) maintains it in evanklem/evanflow, which has 418 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on May 13, 2026.

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