Agent skill

Effect Principles

by timmo001 in timmo001/system-bridge

Apply the Effect way of reasoning in codebases that do not use Effect, in any programming language.

Apache-2.0Auto-check passed

Install Effect Principles

skills CLI
$ npx skills add timmo001/system-bridge --skill effect-principles -a claude-code

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

GitHub CLI
$ gh skill install timmo001/system-bridge effect-principles --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/timmo001/system-bridge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/effect-principles .claude/skills/effect-principles && 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
effect-principles
GitHub stars
356
Token cost
~1.7k tokens
SKILL.md length
880 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
Apache-2.0

At a glance

Apply the Effect way of reasoning in codebases that do not use Effect, in any programming language.

  • Works in 6 steps: Establish the boundary with… → Identify only the concrete ambiguities… → Find the smallest existing seams that… → …
  • Reviewing non-Effect code so dependencies
  • SKILL.md covers Hard Gate, Workflow, Principles and Translation Guide, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Effect Principles is an agent skill from timmo001/system-bridge. Apply the Effect way of reasoning in codebases that do not use Effect, in any programming language. Use when editing or reviewing non-Effect code so dependencies, failures, state, boundaries, resources, time, and workflows stay explicit without adding Effect-shaped architecture or broader scope.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A bridge for your systems. The licence is Apache-2.0.

When your agent uses it

  • Reviewing non-Effect code so dependencies
  • Workflows stay explicit without adding Effect-shaped architecture

Example prompts

  • “/effect-principles”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Establish the boundary with changeset-scope, then read the nearest project guidance and enough surrounding code to understand it.
  2. Identify only the concrete ambiguities introduced, modified, or exposed by that scope: untrusted input, implicit dependencies, expected…
  3. Find the smallest existing seams that own them. Prefer function signatures, local unions, existing interfaces, adapters, parsers, platform…
  4. Tighten the relevant seams together when scoped behaviour crosses them. Change callers outside the original files only when required to…
  5. Compare the result against the hard gate. Revert the idea if it adds more ceremony than truth.
  6. Apply testing and run the smallest reliable verification that proves the changed contract. Add tests when they protect important behaviour…

What it can do on your machine

Read from SKILL.md and the folder at commit 608d62d. 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

Effect Principles loads about 1.7k tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 880 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 timmo001/system-bridge at commit 608d62d, republished under its Apache-2.0 licence (© timmo001). 880 words, ~1,667 tokens.

Download SKILL.mdSave it as .claude/skills/effect-principles/SKILL.md (or your agent's skills folder).
name
effect-principles
description
Apply the Effect way of reasoning in codebases that do not use Effect, in any programming language. Use when editing or reviewing non-Effect code so dependencies, failures, state, boundaries, resources, time, and workflows stay explicit without adding Effect-shaped architecture or broader scope.
license
Apache-2.0

Effect Principles Without Effect

Use the discipline behind Effect's APIs, not Effect's APIs themselves. Express it through the current language's native features and the repository's existing conventions, dependencies, and architecture.

For any bounded task, follow changeset-scope; this skill supplies engineering criteria but never expands investigation, finding, or edit scope.

Hard Gate

Apply a principle only when the resulting change:

  • stays inside the scope and amount of change the user requested;
  • when working from a branch, diff, pull request, or injected work scope, is directly required by those changes;
  • uses existing language or repository constructs;
  • does not add Effect, an Effect substitute, a dependency container, a generic result type, or a new architectural layer;
  • does not increase conceptual surface area, indirection, or the amount a reader must learn;
  • is at least as readable as the code it replaces.

The user's guidance on how much to change is authoritative. Do not treat this skill as permission to improve nearby code. If meeting a principle requires more files, callers, wrappers, types, helpers, or abstractions than the scoped behaviour requires, keep the existing design. Report a larger opportunity separately only when the user asked for architectural advice.

Workflow

  1. Establish the boundary with changeset-scope, then read the nearest project guidance and enough surrounding code to understand it.
  2. Identify only the concrete ambiguities introduced, modified, or exposed by that scope: untrusted input, implicit dependencies, expected failures, invalid states, uncontrolled side effects, retry policy, resource lifetime, or concurrent workflows.
  3. Find the smallest existing seams that own them. Prefer function signatures, local unions, existing interfaces, adapters, parsers, platform primitives, or framework lifecycles already in use.
  4. Tighten the relevant seams together when scoped behaviour crosses them. Change callers outside the original files only when required to keep that behaviour correct; do not propagate the pattern further.
  5. Compare the result against the hard gate. Revert the idea if it adds more ceremony than truth.
  6. Apply testing and run the smallest reliable verification that proves the changed contract. Add tests when they protect important behaviour or catch a meaningful failure that existing checks miss.

Principles

Make requirements visible
  • Pass a dependency as an existing parameter or constructor field when the caller already chooses it.
  • Keep ambient framework state where the framework owns it; do not introduce dependency injection merely to imitate Effect context.
  • Do not create an interface for a single concrete value unless a real boundary or existing test seam already calls for one.
Make invalid states harder to express
  • Prefer the repository's existing sum types, tagged variants, enums, constrained value types, schemas, guards, and state machines.
  • Narrow broad or nullable values at the boundary instead of scattering casts and checks through consumers.
  • Add a new model only when it removes at least as much branching or ambiguity as it introduces.
Treat failures according to their contract
  • Distinguish expected failures only when callers handle them differently.
  • Use the codebase's existing error mechanism: exceptions, rejected promises, error classes, status objects, or established result types.
  • Preserve unexpected defects and context. Do not catch, wrap, or convert every failure for uniformity.
  • Recover, retry, or fall back only at the boundary that can make a truthful decision.
Show full SKILL.md (351 more words)Show less
Keep workflows explicit
  • Keep sequencing, cleanup, cancellation, retry limits, and ownership visible in the function that controls them.
  • Prefer native and existing primitives for cleanup, cancellation, lifecycle, queues, asynchronous work, and scheduling.
  • Do not build generic pipeline, schedule, scope, or resource helpers for one workflow.
Keep pure decisions separate from effects when natural
  • Extract a pure decision only when it has a clear name, removes duplication, or can be understood independently.
  • Keep one-off logic inline when extraction would create a shallow helper or split a readable operation.
  • Keep transport and framework adapters thin when an existing domain or application function already owns the rule; do not create that layering solely for symmetry.
Make concurrency and time deliberate
  • State whether work is sequential, concurrent, cancellable, retried, or best-effort when the behaviour matters.
  • Prefer deterministic synchronization already available in the project over arbitrary sleeps.
  • Add retry, caching, batching, or background work only when required by the task and supported by the operation's real semantics.

Translation Guide

Use this to recognise Effect's intent without reproducing its API surface:

Effect disciplineNon-Effect expression
Requirements in the environmentExisting parameters, constructor fields, context, or framework injection
Typed error channelExisting distinguishable expected-error contract
Schema at boundariesExisting parser, validator, guard, schema library, or explicit narrowing
Tagged stateExisting sum type, tagged variant, enum, or state machine
Scoped resourcesExisting lifecycle, cleanup construct, disposal, or cancellation handling
ScheduleExisting bounded retry or timing policy near the owning operation
Structured concurrencyOwned promises/tasks with explicit cancellation and joining
Service and LayerExisting interface and composition root, but only when both already have a reason to exist

Do Nots

  • Do not add Effect or recreate Effect, Layer, Context, Exit, Cause, Option, or Either under local names.
  • Do not replace the language's ordinary async, exception, optional-value, or framework-state patterns project-wide.
  • Do not add wrappers that only rename a platform or library API.
  • Do not turn local implementation details into public contracts.
  • Do not widen a focused fix into a domain-model, service, validation, or error-handling migration.
  • Do not claim a change is safer when its new ceremony obscures the control flow.

© timmo001, 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

Just SKILL.md in .agents/skills/effect-principles of timmo001/system-bridge.

Open the folder on GitHubat commit 608d62d

Compare with similar skills

Effect Principles 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.

Effect Principles compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Effect Principles this skilltimmo001/system-bridge356—~1.7kAutomated safety check: PassApache-2.0
Codebase Onboardingaffaan-m/ECC274k3 repos~2kAutomated safety check: PassMIT
Codebase Onboardingaffaan-m/ECC274k1 repos~1.1kAutomated safety check: PassMIT
Codebase Onboardingaffaan-m/ECC274k—~270Automated safety check: PassMIT
Acquire Codebase Knowledgegithub/awesome-copilot40k1 repos~2.3kAutomated safety check: PassMIT
Codebase Onboardingalirezarezvani/claude-skills28k—~652Automated safety check: PassMIT

Similar skills

  • Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry points, conventions, and a starter CLAUDE.md.

    274k GitHub starsUsed in 3 repos~2k tokens
    DevelopmentAuto-check passed
  • 分析一个陌生的代码库,并生成一个结构化的入门指南,包括架构图、关键入口点、规范和一个起始的CLAUDE.md文件。适用于加入新项目或首次在代码仓库中设置Claude Code时。

    274k GitHub starsUsed in 1 repo~1.1k tokens
    DevelopmentAuto-check passed
  • 不慣れなコードベースを分析し、アーキテクチャマップ、主要なエントリポイント、規約、スターターCLAUDE.mdを含む構造化オンボーディングガイドを生成します。新しいプロジェクトに参加するか、リポでClaude Codeを初めてセットアップする場合に使用します。

    274k GitHub stars~270 tokensUpdated 2 days ago
    DevelopmentAuto-check passed
  • Acquire Codebase Knowledge

    github/awesome-copilot

    Official

    Maps an unfamiliar codebase into seven evidence-backed documents in docs/codebase/, using a scan script and templates, for onboarding or architecture write-ups.

    40k GitHub starsUsed in 1 repo~2.3k tokens
    DevelopmentAuto-check passed
  • Codebase Onboarding

    alirezarezvani/claude-skills

    Analyze a codebase and generate onboarding documentation for engineers, tech leads, and contractors.

    28k GitHub stars~652 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Deepseek Reason

    ruvnet/ruflo

    Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions.

    74k GitHub stars~626 tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

More from timmo001/system-bridge

All 12 skills in this repo
  • Writing Style

    timmo001/system-bridge

    Write commit messages, PR and issue text and comments, docs (README), code comments, and user-facing strings (notifications, UI labels, toasts, error messages) in the project owner's voice: concise…

    356 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • System Bridge Go Backend

    timmo001/system-bridge

    System Bridge Go backend conventions - error wrapping, graceful degradation for data modules, nil-pointer safety, context-aware Module.Update, structured slog logging, and errcheck-clean deferred…

    356 GitHub stars~841 tokensUpdated today
    Auto-check passed
  • System Bridge Testing Workflow

    timmo001/system-bridge

    How to test System Bridge - Go table-driven tests and commands, web-client quality checks (lint/typecheck/format, no unit tests), the Chrome DevTools MCP interactive test loop for UI and WebSocket…

    356 GitHub stars~843 tokensUpdated today
    Auto-check passed
  • System Bridge Troubleshooting

    timmo001/system-bridge

    Known System Bridge build and runtime failures and their fixes, plus per-OS token/log/settings/data file locations.

    356 GitHub stars~637 tokensUpdated today
    Auto-check passed
  • System Bridge Docs Page Workflow

    timmo001/system-bridge

    Add or restructure a page in the System Bridge Astro + Starlight docs site under docs/ - create the content file, set frontmatter, and wire the sidebar.

    356 GitHub stars~376 tokensUpdated today
    Auto-check passed
  • Update the System Bridge marketing landing page in the Astro + Starlight docs site.

    356 GitHub stars~313 tokensUpdated today
    Auto-check passed

Questions about Effect Principles

What does Effect Principles do?

Apply the Effect way of reasoning in codebases that do not use Effect, in any programming language. Effect Principles is an agent skill from timmo001/system-bridge. Apply the Effect way of reasoning in codebases that do not use Effect, in any programming language.

When should I use Effect Principles?

Effect Principles fits situations like: reviewing non-Effect code so dependencies; workflows stay explicit without adding Effect-shaped architecture.

How do I install Effect Principles in Claude Code?

Run `npx skills add timmo001/system-bridge --skill effect-principles -a claude-code`. Or copy the skill folder (.agents/skills/effect-principles in timmo001/system-bridge) into .claude/skills/effect-principles in your project. Claude Code loads it when a task matches its description.

How do I install Effect Principles in Codex?

Run `npx skills add timmo001/system-bridge --skill effect-principles -a codex`. Or copy the skill folder (.agents/skills/effect-principles in timmo001/system-bridge) into .agents/skills/effect-principles in your project. Codex loads it when a task matches its description.

Can I use Effect Principles 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 timmo001/system-bridge --skill effect-principles -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/effect-principles, .gemini/skills/effect-principles, .github/skills/effect-principles and .opencode/skills/effect-principles in your project.

What does Effect Principles need to run?

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

Does Effect Principles 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 Effect Principles 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 Effect Principles use?

Effect Principles is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Effect Principles use?

About 1.7k tokens (SKILL.md is roughly 6.7k 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 Effect Principles?

Skills that share tags, products or a category with Effect Principles: Codebase Onboarding (affaan-m/ECC, 274k stars), Codebase Onboarding (affaan-m/ECC, 274k stars), Codebase Onboarding (affaan-m/ECC, 274k stars) and Acquire Codebase Knowledge (github/awesome-copilot, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Effect Principles?

timmo001 (a GitHub user) maintains it in timmo001/system-bridge, which has 356 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 7, 2026.

Source: timmo001/system-bridge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.