Agent skill

Long Task Work

by suriyel in suriyel/longtaskforagent

A skill your agent uses when feature-list.json exists - orchestrate features through the full TDD pipeline with quality gates and code review

No licenceAuto-check: notesTesting & QA

Install Long Task Work

skills CLI
$ npx skills add suriyel/longtaskforagent --skill long-task-work -a claude-code

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

GitHub CLI
$ gh skill install suriyel/longtaskforagent long-task-work --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/suriyel/longtaskforagent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/long-task-work .claude/skills/long-task-work && 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
long-task-work
GitHub stars
177
Token cost
~7.1k tokens
SKILL.md length
3,534 words
Files
5 (incl. references)
Skills in repo
17
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when feature-list.json exists - orchestrate features through the full TDD pipeline with quality gates and code review

  • Works in 9 steps: Orient → Bootstrap → Config Gate → …
  • Feature-list.json exists - orchestrate features through the full TDD pipeline with quality gates and code review
  • SKILL.md covers Checklist, Critical Rules, Red Flags and On Error, plus 1 more section
  • Calls git and python; needs OPENAI_API_KEY

What it does

Long Task Work is an agent skill from suriyel/longtaskforagent. Use when feature-list.json exists - orchestrate features through the full TDD pipeline with quality gates and code review

Its SKILL.md is about 7.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/subagent-development.md`, `references/systematic-debugging.md` and `references/worktree-isolation.md`).

It sits in Testing & QA, covering Quality gates and Test-driven development.

When your agent uses it

  • Feature-list.json exists - orchestrate features through the full TDD pipeline with quality gates and code review
  • Tasks that involve Quality gates
  • Tasks that involve Test-driven development

Example prompts

  • “/long-task-work”

Requirements

  • Python 3
  • A credential in OPENAI_API_KEY

Workflow steps

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

  1. Orient
  2. Bootstrap
  3. Config Gate
  4. Feature Detailed Design
  5. Quality Gates
  6. ST Acceptance Test Cases
  7. Inline Compliance Check (no SubAgent)
  8. Persist
  9. End Session

What it can do on your machine

Read from SKILL.md and the folder at commit ca67fe1. 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
    • python

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

  • Network

    Links to these hosts (documentation or services it may open):

    • platform.openai.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Long Task Work loads about 7.1k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 3,534 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~7.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~10k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:19
    project uses a file-based config (e.g., `.env`), ensure it is sourced so required env vars are set before running checks
  • NoteMentions a .env fileSKILL.md:96
    ` for the exact method (e.g., append to `.env`, set in `application.properties`, export as system env var).

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 3,534 words (~7,095 tokens).

“Execute multi-session software projects by implementing one feature per cycle. Each cycle follows a strict pipeline: Orient → Gate → Plan → TDD → Quality → ST Acceptance → Inline Check → Persist.”

— opening of SKILL.md by suriyel
name
long-task-work

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (references) in skills/long-task-work of suriyel/longtaskforagent.

  • SKILL.md
  • SKILL.md.template
  • references/subagent-development.md
  • references/systematic-debugging.md
  • references/worktree-isolation.md

Open the folder on GitHubat commit ca67fe1

Compare with similar skills

Long Task Work 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.

Long Task Work compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Long Task Work this skillsuriyel/longtaskforagent177—~7.1kAutomated safety check: NotesNone
Feature Plannerserendipity1004/cc-feature-implementer176—~2.4kAutomated safety check: PassNone
Shift Left Testingpetrkindlmann/qa-skills165—~6.7kAutomated safety check: PassMIT
Handsontable Test Writing Disciplinehandsontable/handsontable22k—~1.3kAutomated safety check: PassCustom licence
Conductor Workflow Patternswshobson/agents40k9 repos~426Automated safety check: PassMIT
TDDpietheinstrengholt/rssmonster56430 repos~906Automated safety check: PassMIT

Similar skills

  • Feature Planner

    serendipity1004/cc-feature-implementer

    Creates phase-based feature plans with quality gates and incremental delivery structure.

    176 GitHub stars~2.4k tokensUpdated 9 mo ago
    Testing & QAAuto-check passed
  • Shift Left Testing

    petrkindlmann/qa-skills

    Move quality earlier in the development lifecycle. An agent skill from petrkindlmann/qa-skills.

    165 GitHub stars~6.7k tokensUpdated 4 mo ago
    Testing & QAAuto-check passed
  • Handsontable Test Writing Discipline

    handsontable/handsontable

    Keeps tests honest: write them from the requirement, treat the code as the first suspect when a test is red, and refuse every way of faking a passing run.

    22k GitHub stars~1.3k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the…

    40k GitHub starsUsed in 9 repos~426 tokens
    DevelopmentAuto-check passed
  • TDD

    pietheinstrengholt/rssmonster

    Test-driven development. An agent skill from pietheinstrengholt/rssmonster.

    564 GitHub starsUsed in 30 repos~906 tokens
    Testing & QAAuto-check passed
  • TDD Workflow

    hellangleZ/burn-in-cceverywhere-ralph

    A skill your agent uses when writing new features, fixing bugs, or refactoring code.

    112 GitHub starsUsed in 11 repos~2.4k tokens
    Testing & QAAuto-check passed

More from suriyel/longtaskforagent

All 17 skills in this repo
  • Long Task Init

    suriyel/longtaskforagent

    A skill your agent uses when ATS doc exists (or auto-skipped) but feature-list.json not yet created - scaffold project artifacts and populate features from Design §10.2

    177 GitHub stars~5.6k tokensUpdated 3 mo ago
    Auto-check: notes
  • Long Task Explore

    suriyel/longtaskforagent

    A skill your agent uses for on-demand deep exploration of an existing codebase - analyzes architecture, data flow, domain model, API surface, dependencies, and code health

    177 GitHub stars~2.7k tokensUpdated 3 mo ago
    Auto-check passed
  • Long Task TDD

    suriyel/longtaskforagent

    A skill your agent uses when implementing a feature through TDD in a long-task project - enforces Red-Green-Refactor cycle

    177 GitHub stars~4.4k tokensUpdated 3 mo ago
    Auto-check: notes
  • Using Long Task

    suriyel/longtaskforagent

    A skill your agent uses when starting any session in a long-task project - routes to the correct phase skill based on project state

    177 GitHub stars~3.6k tokensUpdated 3 mo ago
    Auto-check passed
  • Long Task Ats

    suriyel/longtaskforagent

    A skill your agent uses when design doc exists but no ATS doc and no feature-list.json - generate a global Acceptance Test Strategy mapping every requirement to acceptance scenarios with category…

    177 GitHub stars~3.7k tokensUpdated 3 mo ago
    Auto-check passed
  • Long Task Design

    suriyel/longtaskforagent

    A skill your agent uses when SRS doc exists but no design doc and no feature-list.json - take the approved SRS as input and produce an architecture/design document focused on HOW to build it

    177 GitHub stars~4.5k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Long Task Work

What does Long Task Work do?

A skill your agent uses when feature-list.json exists - orchestrate features through the full TDD pipeline with quality gates and code review. Long Task Work is an agent skill from suriyel/longtaskforagent.

When should I use Long Task Work?

Long Task Work fits situations like: feature-list.json exists - orchestrate features through the full TDD pipeline with quality gates and code review; tasks that involve Quality gates; tasks that involve Test-driven development.

How do I install Long Task Work in Claude Code?

Run `npx skills add suriyel/longtaskforagent --skill long-task-work -a claude-code`. Or copy the skill folder (skills/long-task-work in suriyel/longtaskforagent) into .claude/skills/long-task-work in your project. Claude Code loads it when a task matches its description.

How do I install Long Task Work in Codex?

Run `npx skills add suriyel/longtaskforagent --skill long-task-work -a codex`. Or copy the skill folder (skills/long-task-work in suriyel/longtaskforagent) into .agents/skills/long-task-work in your project. Codex loads it when a task matches its description.

Can I use Long Task Work 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 suriyel/longtaskforagent --skill long-task-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/long-task-work, .gemini/skills/long-task-work, .github/skills/long-task-work and .opencode/skills/long-task-work in your project.

What does Long Task Work need to run?

Going by SKILL.md and its folder, Long Task Work needs the command-line tools its instructions call (git and python) and credentials named OPENAI_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY.

Does Long Task Work access the network?

SKILL.md names 1 domain. As links in the text: platform.openai.com. This is read from the text; nothing was executed.

Is Long Task Work safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Long Task Work use?

No licence was found for Long Task Work or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Long Task Work use?

About 7.1k tokens (SKILL.md is roughly 28k 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 3.4k tokens, read only when the agent opens those files.

What are the alternatives to Long Task Work?

Skills that share tags, products or a category with Long Task Work: Feature Planner (serendipity1004/cc-feature-implementer, 176 stars), Shift Left Testing (petrkindlmann/qa-skills, 165 stars), Handsontable Test Writing Discipline (handsontable/handsontable, 22k stars) and Conductor Workflow Patterns (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Long Task Work?

suriyel (a GitHub user) maintains it in suriyel/longtaskforagent, which has 177 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on June 23, 2026.

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