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

Developing Marchat

by Cod-e-Codes in Cod-e-Codes/marchat

Implements and refactors marchat Go code with project toolchain and quality gates.

MITAuto-check passedTesting & QA

Install Developing Marchat

skills CLI
$ npx skills add Cod-e-Codes/marchat --skill developing-marchat -a claude-code

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

GitHub CLI
$ gh skill install Cod-e-Codes/marchat developing-marchat --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/Cod-e-Codes/marchat.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/developing-marchat .claude/skills/developing-marchat && 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
developing-marchat
GitHub stars
137
Token cost
~870 tokens
SKILL.md length
385 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Implements and refactors marchat Go code with project toolchain and quality gates.

  • Works in 5 steps: Confirm scope: client, server, shared… → Read the matching domain skill… → Check ARCHITECTURE.md and PROTOCOL.md if… → …
  • Adding features
  • SKILL.md covers Before coding, Current information, Implementation rules and After substantive code changes, plus 2 more sections
  • Calls go and git

What it does

Developing Marchat is an agent skill from Cod-e-Codes/marchat. Implements and refactors marchat Go code with project toolchain and quality gates. Use when adding features, fixing bugs, touching client/server/plugin code, or when the user asks to develop, build, or validate marchat changes.

Its SKILL.md is about 870 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 Testing & QA, covering Refactoring and Quality gates. It works with Go. The repository describes itself as: Terminal chat for developers: Go WebSocket server + Bubble Tea TUI client, optional E2E, reactions, DMs, channels, plugins, files, code snippets, admin UI. Backends: SQLite… The licence is MIT.

When your agent uses it

  • Adding features
  • Touching client/server/plugin code
  • The user asks to develop
  • Validate marchat changes

Example prompts

  • “Use the developing-marchat skill to implement and refactors marchat Go code with project toolchain and quality gates”
  • “/developing-marchat”

Requirements

  • Docker

Workflow steps

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

  1. Confirm scope: client, server, shared wire types, plugins, config, or docs-only.
  2. Read the matching domain skill (client-marchat, etc.) before editing that area.
  3. Check ARCHITECTURE.md and PROTOCOL.md if the change crosses process boundaries.
  4. Prefer extending existing types and helpers over new parallel APIs.
  5. Verify library APIs and toolchain from go.mod, repo source, or official docs - not model memory.

What it can do on your machine

Read from SKILL.md and the folder at commit 3440f09. 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:

    • go
    • 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

Developing Marchat loads about 870 tokens when it runs. Until then it costs about 62 tokens; SKILL.md has 385 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~62
When it runs · the whole SKILL.md, loaded when a task matches
~870

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 Cod-e-Codes/marchat at commit 3440f09, republished under its MIT licence (© Cod-e-Codes). 385 words, ~870 tokens.

Download SKILL.mdSave it as .claude/skills/developing-marchat/SKILL.md (or your agent's skills folder).
name
developing-marchat
description
Implements and refactors marchat Go code with project toolchain and quality gates. Use when adding features, fixing bugs, touching client/server/plugin code, or when the user asks to develop, build, or validate marchat changes.

Developing marchat

Read .cursor/rules/marchat.mdc for always-on constraints. Use domain skills (client-marchat, server-marchat, plugins-marchat, database-marchat, protocol-marchat) when work is localized.

Before coding

  1. Confirm scope: client, server, shared wire types, plugins, config, or docs-only.
  2. Read the matching domain skill (client-marchat, etc.) before editing that area.
  3. Check ARCHITECTURE.md and PROTOCOL.md if the change crosses process boundaries.
  4. Prefer extending existing types and helpers over new parallel APIs.
  5. Verify library APIs and toolchain from go.mod, repo source, or official docs - not model memory.

Current information

This repo (go.mod, ARCHITECTURE.md, PROTOCOL.md, .cursor/) overrides general model knowledge. For Cursor skills/rules, CI, packaging, or dependency APIs not spelled out here, web search or fetch official documentation before implementing.

Implementation rules

  • Go 1.26+ idioms; toolchain patch in go.mod is authoritative for CI and Docker.
  • Never hand-edit go.mod versions; use go get -u package or go get package@latest, then go mod tidy.
  • Parameterized SQL only; dialect differences go through server/db_dialect.go.
  • Chat E2E is a global ChaCha20-Poly1305 symmetric key, not per-user X25519 exchange.
  • Do not log secrets (keys, passphrases, admin keys, session secrets).
  • Minimize diff scope; no drive-by refactors or stubs.

After substantive code changes

Run from repo root unless only plugin/sdk changed:

bash
gofmt -w .
go vet ./...
go test ./...
go test -race ./...
go test -coverprofile=mergedcoverage ./...
go tool cover -func=mergedcoverage

If golangci-lint is installed:

bash
golangci-lint run ./...

Nested plugin/sdk module (separate go.mod): run on every substantive root change, and always when plugin/sdk files changed:

bash
cd plugin/sdk && go test ./...

Windows: CI runs -race on Linux; local -race on Windows may require CGO for some packages - still run it when the toolchain allows. See testing-marchat for coverage profiles and CI DB smoke.

Show full SKILL.md (135 more words)Show less

Completion checklist (all required before responding)

  • Compiles; go vet clean for touched packages
  • go test ./... and go test -race ./... run and reported (not assumed)
  • cd plugin/sdk && go test ./... run (nested module; skip only for docs-only or unrelated isolated edits)
  • Tests added or updated for behavior changes (testing-marchat skill)
  • Docs/changelog/coverage updated if user-visible or totals shifted (writing-marchat-docs); update ARCHITECTURE/PROTOCOL/skills when behavior changes, not CHANGELOG alone
  • Domain skill and .cursor/skills/ updated when shipped behavior or agent workflow changes
  • No protocol or keystore breaking change without explicit discussion and changelog note
  • Commit message drafted via git-workflow-marchat for all uncommitted files in the working tree

Git

Do not git commit or git push unless the user asks. Always end substantive work with a suggested commit message covering the full git diff, not only files touched in the last reply.

© Cod-e-Codes, MIT. 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 .cursor/skills/developing-marchat of Cod-e-Codes/marchat.

Open the folder on GitHubat commit 3440f09

Compare with similar skills

Developing Marchat 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.

Developing Marchat compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Developing Marchat this skillCod-e-Codes/marchat137—~870Automated safety check: PassMIT
Triage Sonarqubenetdata/netdata81k—~2.8kAutomated safety check: NotesGPL-3.0
Sonarqube Analysishbmartin/graphviz2drawio275—~508Automated safety check: NotesGPL-3.0
Ccg Workflowfengshao1227/ccg-workflow5.9k—~2.3kAutomated safety check: PassMIT
Asw Remove AI Slopswjgoarxiv/antigravity-swarm167—~2.7kAutomated safety check: PassMIT
Verifycodewithmukesh/dotnet-claude-kit751—~2kAutomated safety check: NotesMIT

Similar skills

  • Triage Sonarqube

    netdata/netdata

    Inspect, review, or apply authorized triage decisions to SonarCloud issues and security hotspots; also review the Sonar helpers.

    81k GitHub stars~2.8k tokensUpdated today
    Testing & QAAuto-check: notes

  • Sonarqube Analysis

    hbmartin/graphviz2drawio

    Inspect SonarQube Cloud/SonarCloud findings for this repository using local .env credentials.

    275 GitHub stars~508 tokensUpdated 2 mo ago
    Testing & QAAuto-check: notes

  • Ccg Workflow

    fengshao1227/ccg-workflow

    How to run a non-trivial change end to end with the CCG role tools (ccganalyze / ccgdesign / ccgbuild / ccgdebug / ccgoptimize / ccgreview / ccgtest) and the verify- quality gates.

    5.9k GitHub stars~2.3k tokensUpdated 23 days ago
    Testing & QAAuto-check passed

  • Asw Remove AI Slops

    wjgoarxiv/antigravity-swarm

    Remove AI-looking code smells from branch changes or explicit files.

    167 GitHub stars~2.7k tokensUpdated 3 mo ago
    Testing & QAAuto-check passed

  • Verify

    codewithmukesh/dotnet-claude-kit

    Run a comprehensive 7-phase verification pipeline for .NET projects: build, analyzers, antipattern detection, tests, security, formatting, and diff review.

    751 GitHub stars~2k tokensUpdated 2 mo ago
    Testing & QAAuto-check: notes

  • Workflow Orchestration

    vxcozy/workflow-orchestration

    Disciplined task execution with planning, verification, and self-improvement loops.

    116 GitHub stars~1k tokensUpdated 5 mo ago
    Agent WorkflowsAuto-check passed

More from Cod-e-Codes/marchat

All 11 skills in this repo

  • Debugging Marchat

    Cod-e-Codes/marchat

    Diagnoses marchat client and server issues using -doctor, env configuration, and logs.

    137 GitHub stars~668 tokensUpdated 5 days ago
    Auto-check: notes

  • Git Workflow Marchat

    Cod-e-Codes/marchat

    Drafts conventional commit messages and pull request bodies for marchat without committing or pushing unless explicitly requested.

    137 GitHub stars~482 tokensUpdated 5 days ago
    Auto-check: notes

  • Testing Marchat

    Cod-e-Codes/marchat

    Writes and runs marchat tests with race detection, coverage, and dialect smoke patterns.

    137 GitHub stars~802 tokensUpdated 5 days ago
    Auto-check passed

  • Client Marchat

    Cod-e-Codes/marchat

    Implements marchat terminal client TUI, commands, keystore, and WebSocket client behavior.

    137 GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed

  • Database Marchat

    Cod-e-Codes/marchat

    Changes marchat SQL schema and queries across SQLite, PostgreSQL, and MySQL using dialect helpers.

    137 GitHub stars~985 tokensUpdated 5 days ago
    Auto-check passed

  • Plugins Marchat

    Cod-e-Codes/marchat

    Develops and maintains marchat plugins: SDK, host IPC, manager install path, store downloads, and Ed25519 licenses.

    137 GitHub stars~558 tokensUpdated 5 days ago
    Auto-check passed

Works with

Categories

Questions about Developing Marchat

What does Developing Marchat do?

Implements and refactors marchat Go code with project toolchain and quality gates. Developing Marchat is an agent skill from Cod-e-Codes/marchat. Implements and refactors marchat Go code with project toolchain and quality gates.

When should I use Developing Marchat?

Developing Marchat fits situations like: adding features; touching client/server/plugin code; the user asks to develop; validate marchat changes.

How do I install Developing Marchat in Claude Code?

Run `npx skills add Cod-e-Codes/marchat --skill developing-marchat -a claude-code`. Or copy the skill folder (.cursor/skills/developing-marchat in Cod-e-Codes/marchat) into .claude/skills/developing-marchat in your project. Claude Code loads it when a task matches its description.

How do I install Developing Marchat in Codex?

Run `npx skills add Cod-e-Codes/marchat --skill developing-marchat -a codex`. Or copy the skill folder (.cursor/skills/developing-marchat in Cod-e-Codes/marchat) into .agents/skills/developing-marchat in your project. Codex loads it when a task matches its description.

Can I use Developing Marchat 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 Cod-e-Codes/marchat --skill developing-marchat -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/developing-marchat, .gemini/skills/developing-marchat, .github/skills/developing-marchat and .opencode/skills/developing-marchat in your project.

What does Developing Marchat need to run?

Going by SKILL.md and its folder, Developing Marchat needs the command-line tools its instructions call (go and git). Our summary lists: Docker.

Does Developing Marchat 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 Developing Marchat 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 Developing Marchat use?

Developing Marchat is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Developing Marchat use?

About 870 tokens (SKILL.md is roughly 3.5k 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 Developing Marchat?

Skills that share tags, products or a category with Developing Marchat: Triage Sonarqube (netdata/netdata, 81k stars), Sonarqube Analysis (hbmartin/graphviz2drawio, 275 stars), Ccg Workflow (fengshao1227/ccg-workflow, 5.9k stars) and Asw Remove AI Slops (wjgoarxiv/antigravity-swarm, 167 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Developing Marchat?

Cod-e-Codes (a GitHub user) maintains it in Cod-e-Codes/marchat, which has 137 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 3, 2026.

Source: Cod-e-Codes/marchat on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.