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

Task Runners

by timmo001 in timmo001/system-bridge

Run and write project tasks so checks, builds, tests and dev servers finish fast - run only what a change needs, in parallel, skipping work that is already up to date.

Apache-2.0Auto-check passedTesting & QA

Install Task Runners

skills CLI
$ npx skills add timmo001/system-bridge --skill task-runners -a claude-code

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

GitHub CLI
$ gh skill install timmo001/system-bridge task-runners --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/task-runners .claude/skills/task-runners && 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
task-runners
GitHub stars
356
Token cost
~1.5k tokens
SKILL.md length
778 words
Files
21 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Run and write project tasks so checks, builds, tests and dev servers finish fast - run only what a change needs, in parallel, skipping work that is already up to date.

  • Works in 6 steps: Find the tasks. List them first (mise… → Pick the narrowest tasks. Map the… → Run them together. Pass independent… → …
  • Running linters
  • SKILL.md covers References, Running, Writing tasks and Measuring
  • Runs Go, TypeScript, Python, Rust and Shell scripts from its folder; calls mise, deno and bun

What it does

Task Runners is an agent skill from timmo001/system-bridge. Run and write project tasks so checks, builds, tests and dev servers finish fast - run only what a change needs, in parallel, skipping work that is already up to date. Use when running linters, type checks, test suites or builds; when writing or reviewing task runner config (mise.toml, package.json scripts, justfile, deno.json, Makefile, pitchfork.toml) or CI steps; or when a check, build or task run is slow.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including reference files (for example `references/examples/bun.md`, `references/examples/deno.md` and `references/examples/github-actions.md`).

It sits in Testing & QA, covering Linting and formatting and Test generation. It works with npm and Deno. The repository describes itself as: A bridge for your systems. The licence is Apache-2.0.

When your agent uses it

  • Running linters
  • Reviewing task runner config (mise.toml
  • Package.json scripts
  • Pitchfork.toml)

Example prompts

  • “/task-runners”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

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

  1. Find the tasks. List them first (mise tasks, just --list, deno task, the scripts in package.json). Prefer a repository's own task over the…
  2. Pick the narrowest tasks. Map the changed files to the tasks that cover them: a YAML edit needs the YAML linter, not the test suite. Use a…
  3. Run them together. Pass independent tasks to one invocation (mise run a ::: b, bun run --parallel a b, pnpm run "/^(a|b)$/"), or start…
  4. Write first, then check. Formatters, code generators and anything else that rewrites files run on their own before the read-only checks…
  5. Background long runs. Start slow builds and full suites in a background shell and keep working; start dev servers through the project's…
  6. Rerun narrowly. After a failure, rerun only what failed (pytest --lf, a single task, a single test file) and widen again only when the fix…

What it can do on your machine

Read from SKILL.md and the folder at commit 504c45d. 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

    Ships script files (Go, TypeScript, Python, Rust and Shell, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • mise
    • deno
    • bun
    • pytest
    • just
    • pnpm

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

  • Network

    No URLs in SKILL.md. Its commands use pnpm, 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

Task Runners loads about 1.5k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 106 tokens; SKILL.md has 778 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~106
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

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 504c45d, republished under its Apache-2.0 licence (© timmo001). 778 words, ~1,493 tokens.

Download SKILL.mdSave it as .claude/skills/task-runners/SKILL.md (or your agent's skills folder). This skill also uses 20 other files; get the full folder from GitHub.
name
task-runners
description
Run and write project tasks so checks, builds, tests and dev servers finish fast - run only what a change needs, in parallel, skipping work that is already up to date. Use when running linters, type checks, test suites or builds; when writing or reviewing task runner config (mise.toml, package.json scripts, justfile, deno.json, Makefile, pitchfork.toml) or CI steps; or when a check, build or task run is slow.
license
Apache-2.0

Task Runners

Fast runs come from three things, in this order: run less, run it at the same time, and skip what is already done. The testing skill decides which checks a change needs; this skill covers running and writing them efficiently.

References

  • references/tools.md: per-tool commands and flags. Read it before running or editing a tool's tasks.
  • references/examples/: a starting config for each tool. Read the one you need before writing or restructuring tasks: mise, Bun, pnpm, npm, Yarn, Deno, just, make, Rust, Go, Python, Vitest, pitchfork, GitHub Actions.
  • references/examples/scripts/: small scripts (check.sh, check.mts, check.py, check.go, check.rs) that run checks in parallel. Where a tool can't run tasks in parallel natively (npm, Yarn in one package, cargo, Go, uv), use an alternative task runner or write your own script from these.

The scripts are a starting point, not a drop-in. They may be out of date or miss what a project needs, such as Windows support, signal handling or timeouts. Check them against current docs and the project's conventions, and adapt or rewrite them as needed.

Running

  1. Find the tasks. List them first (mise tasks, just --list, deno task, the scripts in package.json). Prefer a repository's own task over the raw command it wraps, since the task carries the right flags, directory and dependencies. Local AGENTS.md instructions win.
  2. Pick the narrowest tasks. Map the changed files to the tasks that cover them: a YAML edit needs the YAML linter, not the test suite. Use a tool's changed-file selection where it exists (bun test --changed, deno test --changed, pnpm --filter "...[origin/main]", mise run --affected). Don't run a repository-wide aggregate such as check or validate for a narrow change.
  3. Run them together. Pass independent tasks to one invocation (mise run a ::: b, bun run --parallel a b, pnpm run "/^(a|b)$/"), or start separate commands as parallel tool calls. Never chain independent checks with &&.
  4. Write first, then check. Formatters, code generators and anything else that rewrites files run on their own before the read-only checks, so the checks see the final files.
  5. Background long runs. Start slow builds and full suites in a background shell and keep working; start dev servers through the project's daemon workflow rather than in the foreground.
  6. Rerun narrowly. After a failure, rerun only what failed (pytest --lf, a single task, a single test file) and widen again only when the fix could affect more.
Show full SKILL.md (376 more words)Show less

Writing tasks

  • One job per task. Give each check its own task (lint, lint:yaml, typecheck, test), then group them in an aggregate task through dependencies. A run string chained with && forces everything to run one after another and hides which step failed.
  • Declare real ordering as dependencies. If tests need a build, the test task depends on the build task; the runner then builds once even when several tasks need it. Don't rely on the order tasks are listed in, and don't use lifecycle hooks (pretest) that rebuild behind the runner's back.
  • Install before anything reads dependencies. Tasks that read node_modules, a virtualenv or a vendor directory depend on the install task, so a parallel install cannot run while they read.
  • Keep writers away from readers. Two tasks that write the same file or directory must not run in parallel: a formatter and its own --check, two builds sharing an output, or a code generator and the linter reading its output. Separate them with a dependency or a wait (wait_for in mise) rather than serialising everything.
  • Skip up-to-date work. Declare inputs and outputs (sources/outputs in mise, files/output in deno tasks) on slow tasks with clear inputs, such as builds and generators. Include config and lockfiles in the inputs. Leave cheap checks uncached.
  • Use the tool's own parallelism. Test runners and build tools usually parallelise internally; don't split their work into many tasks unless the pieces need isolation. Turn it on where it is opt-in (bun test --parallel, deno test --parallel, pytest -n auto).
  • Isolate shared state. Parallel tasks and tests need their own ports, temporary directories, databases and lock files. Fix collisions with per-task paths or random ports; serialise only the tasks that genuinely share a resource.
  • Name for grouping. Use group:name task names (lint:yaml, test:unit) so wildcards and aggregates can pick them up, and give each task a short description.
  • Mirror tasks in CI. CI calls the same tasks, and independent checks run as separate jobs or in one parallel task invocation, not as a long chain of steps.

Measuring

Measure before and after a task change: the runner's own timings (mise prints them per task), or hyperfine for repeated runs. Keep the change only if it is faster without making failures harder to read.

© 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

SKILL.md and 20 other files (references) in .agents/skills/task-runners of timmo001/system-bridge.

  • SKILL.md
  • references/examples/bun.md
  • references/examples/deno.md
  • references/examples/github-actions.md
  • references/examples/go.md
  • references/examples/just.md
  • references/examples/make.md
  • references/examples/mise.md
  • references/examples/npm.md
  • references/examples/pitchfork.md
  • references/examples/pnpm.md
  • references/examples/python.md
  • references/examples/rust.md
  • references/examples/scripts/check.go
  • references/examples/scripts/check.mts
  • references/examples/scripts/check.py
  • references/examples/scripts/check.rs
  • references/examples/scripts/check.sh
  • … and 3 more

Open the folder on GitHubat commit 504c45d

Compare with similar skills

Task Runners 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.

Task Runners compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task Runners this skilltimmo001/system-bridge356—~1.5kAutomated safety check: PassApache-2.0
Pre Commitwellwelwel/poku1.2k—~728Automated safety check: PassMIT
Igniteui Angular TestingIgniteUI/igniteui-angular599—~950Automated safety check: PassCustom licence
Deno Runtime and Package Managerdenoland/skills100—~2.7kAutomated safety check: PassMIT
DenoOpenHands/extensions158—~567Automated safety check: PassMIT
Zizkadb TestZIZKA-AI-SL/ZizkaDB123—~358Automated safety check: PassCustom licence

Similar skills

  • Pre Commit

    wellwelwel/poku

    Run the mandatory pre-commit checks for the poku repository before staging a commit.

    1.2k GitHub stars~728 tokensUpdated 3 mo ago
    Testing & QAAuto-check passed

  • Igniteui Angular Testing

    IgniteUI/igniteui-angular

    Quick-reference for running Ignite UI for Angular test suites.

    599 GitHub stars~950 tokensUpdated today
    Frontend & DesignAuto-check passed

  • Deno Runtime and Package Manager

    denoland/skills

    Official

    Guides writing, running and configuring Deno 2.9+ projects: installing npm and JSR dependencies, permissions, config file precedence and the built-in fmt, lint, test and compile toolchain.

    100 GitHub stars~2.7k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

  • Deno

    OpenHands/extensions

    If the project uses deno, use this skill. An agent skill from OpenHands/extensions.

    158 GitHub stars~567 tokensUpdated today
    DevelopmentAuto-check passed

  • Zizkadb Test

    ZIZKA-AI-SL/ZizkaDB

    Run the full ZizkaDB test suite across all layers — lint, Python unit tests, SDK tests, MCP tests, TypeScript tests, and dashboard build verification.

    123 GitHub stars~358 tokensUpdated yesterday
    Testing & QAAuto-check passed

  • Make Git Escrow

    internet-court/internet-court-skill

    Create a new git escrow bounty for a test suite. An agent skill from internet-court/internet-court-skill.

    6.4k GitHub starsUsed in 2 repos~922 tokens
    Testing & QAAuto-check: notes

More from timmo001/system-bridge

All 13 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

  • System Bridge Landing Content Updates

    timmo001/system-bridge

    Update the System Bridge marketing landing page in the Astro + Starlight docs site.

    356 GitHub stars~313 tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Task Runners

What does Task Runners do?

Run and write project tasks so checks, builds, tests and dev servers finish fast - run only what a change needs, in parallel, skipping work that is already up to date. Task Runners is an agent skill from timmo001/system-bridge. Run and write project tasks so checks, builds, tests and dev servers finish fast - run only what a change needs, in parallel, skipping work that is already up to date.

When should I use Task Runners?

Task Runners fits situations like: running linters; reviewing task runner config (mise.toml; package.json scripts; pitchfork.toml).

How do I install Task Runners in Claude Code?

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

How do I install Task Runners in Codex?

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

Can I use Task Runners 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 task-runners -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-runners, .gemini/skills/task-runners, .github/skills/task-runners and .opencode/skills/task-runners in your project.

What does Task Runners need to run?

Going by SKILL.md and its folder, Task Runners needs Go, TypeScript, Python, Rust and a shell for the scripts in its folder and the command-line tools its instructions call (mise, deno, bun, pytest, just and pnpm). Our summary lists: Python 3; A Bash shell.

Does Task Runners 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 Task Runners 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 Task Runners use?

Task Runners 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 Task Runners use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.9k tokens, read only when the agent opens those files.

What are the alternatives to Task Runners?

Skills that share tags, products or a category with Task Runners: Pre Commit (wellwelwel/poku, 1.2k stars), Igniteui Angular Testing (IgniteUI/igniteui-angular, 599 stars), Deno Runtime and Package Manager (denoland/skills, 100 stars) and Deno (OpenHands/extensions, 158 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task Runners?

timmo001 (a GitHub user) maintains it in timmo001/system-bridge, which has 356 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 8, 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.