Agent skill

Task List

by romeerez in romeerez/orchid-orm

A skill your agent uses when user asks to write a task list, not to do a task

MITAuto-check passedAgent Workflows

Install Task List

skills CLI
$ npx skills add romeerez/orchid-orm --skill task-list -a claude-code

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

GitHub CLI
$ gh skill install romeerez/orchid-orm task-list --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/romeerez/orchid-orm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/task-list .claude/skills/task-list && 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-list
GitHub stars
543
Token cost
~2.1k tokens
SKILL.md length
822 words
Files
2
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when user asks to write a task list, not to do a task

  • Works in 3 steps: Read the provided spec.md fully before… → Read relevant code, tests, exports,… → If tasks.md exists in the same folder,…
  • User asks to write a task list
  • SKILL.md covers Input, Context To Read, tasks.md and Final Check
  • Calls pnpm

What it does

Task List is an agent skill from romeerez/orchid-orm. Use when user asks to write a task list, not to do a task

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Agent Workflows, covering Task breakdown. The licence is MIT.

When your agent uses it

  • User asks to write a task list
  • Not to do a task

Example prompts

  • “/task-list”

Workflow steps

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

  1. Read the provided spec.md fully before writing tasks.
  2. Read relevant code, tests, exports, docs, and guidelines needed to identify affected packages and likely implementation areas.
  3. If tasks.md exists in the same folder, read it first, preserve still-correct tasks, remove stale tasks, and reconcile it with final spec.md.

What it can do on your machine

Read from SKILL.md and the folder at commit de54a3b. 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:

    • 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 List loads about 2.1k tokens when it runs. Until then it costs about 17 tokens; SKILL.md has 822 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~17
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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 romeerez/orchid-orm at commit de54a3b, republished under its MIT licence (© romeerez). 822 words, ~2,094 tokens.

Download SKILL.mdSave it as .claude/skills/task-list/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
task-list
description
Use when user asks to write a task list, not to do a task

Create or update exactly:

  • tasks.md in the same directory as the provided spec.md

This is a task-list command for an existing spec, not research-only and not implementation.

By default, write a full task list that covers the complete spec. Only write a partial task list when the user explicitly asks for a limited scope.

Input

The prompt must provide a path to changes/<feature-name>/<NUMBER-idea-name>/spec.md.

If no spec path is provided, ask one focused question for the path. If the path is not an existing spec.md file, stop and report it.

Context To Read

  1. Read the provided spec.md fully before writing tasks.
  2. Read relevant code, tests, exports, docs, and guidelines needed to identify affected packages and likely implementation areas.
    • Always include root guidelines/code.md or guidelines/test.md, plus nested guidelines/code.md or guidelines/test.md files for directories likely to change.
    • Respect package boundaries: public APIs export from src/index.ts; downstream internal pqb access goes through pqb/internal.
  3. If tasks.md exists in the same folder, read it first, preserve still-correct tasks, remove stale tasks, and reconcile it with final spec.md.

tasks.md

Output path: same directory as the provided spec.md.

If it exists, read it first, preserve still-correct tasks, remove stale tasks, and reconcile it with final spec.md.

The file must start with this section before any package or docs work:

md
## 0. read spec.md and guidelines

- 0.1 Read `spec.md`, including `spec.md` `## Detailed Design`, before starting any later task. Follow that design for every later task, and make sure the final implementation matches it exactly.
- 0.2 Check whether any later task you were prompted to do requires coding. If yes, read and follow every guideline below for that work, and verify that all produced code follows them to the letter.

- you must follow guidelines/code.md or guidelines/test.md for coding
- you must follow <relevant-nested-path>/guidelines/code.md or <relevant-nested-path>/guidelines/test.md for coding

Section 0 rules:

  • It contains exactly two numbered entries, 0.1 and 0.2; both are plain list items, not checkboxes.
  • Guideline bullets are required supporting lines, not subtasks.
  • Include root guidelines/code.md or guidelines/test.md and every relevant nested guidelines/code.md or guidelines/test.md for directories the implementation will change.

After section 0, only these sections are valid:

  • affected package sections, ordered by dependency: lower-level packages before downstream packages
  • for full task lists only, optional docs section, only for repo-root docs/ work, placed after package work
  • for full task lists only, final changeset section with the next number and one non-coding task that follows .agents/skills/changeset/SKILL.md

Package section names must be package folder names or root package script names. For schema config work, use zod and/or valibot, never schema-configs or schemaConfigs. Keep package-local docs in the relevant package section.

Every implementation checkbox task after section 0:

  • is a responsibility/change-slice title, not the instruction itself
  • is complete only when all nested subtasks are done
  • owns an indented numbered subtask list, e.g. 1.1.1, 1.1.2
  • has at least one actionable subtask; do not add filler
  • stays high-level, not file-by-file or helper-by-helper
  • may mention likely code locations, exported functions, or docs pages when useful for orientation

If one requirement spans multiple packages, create a separate task in each affected package section. Do not create empty sections, standalone test tasks, generic research tasks, vague cleanup tasks, or exact test-writing instructions.

Every package coding task must start its subtask list with:

  • <task>.1 scope: <short package area or capability class>
  • <task>.2 acceptance: <high-level expected outcome>

Then add change-specific subtasks. End every coding task with these exact verification subtasks after the numeric prefix:

  • verify implementation against guidelines
  • code must be covered by tests
  • tests and types must pass: run pnpm verify
  • reconcile spec.md for every new user-visible requirement
Show full SKILL.md (314 more words)Show less

When writing those lines in tasks.md, keep the backticks around spec.md and pnpm verify as shown in the example below.

Non-coding tasks, including repo-root docs-only tasks and the final changeset task, do not get the four coding verification subtasks.

Use this structure:

md
## 0. read spec.md and guidelines

- 0.1 Read `spec.md`, including `spec.md` `## Detailed Design`, before starting any later task. Follow that design for every later task, and make sure the final implementation matches it exactly.
- 0.2 Check whether any later task you were prompted to do requires coding. If yes, read and follow every guideline below for that work, and verify that all produced code follows them to the letter.

- you must follow guidelines/code.md or guidelines/test.md for coding
- you must follow packages/pqb/src/query/guidelines/code.md or packages/pqb/src/query/guidelines/test.md for coding

## 1. pqb

- [ ] 1.1 <change slice title>
  - 1.1.1 scope: query-builder read-only query capability
  - 1.1.2 acceptance: read-only query objects keep read behavior and reject mutation APIs at the type level.
  - 1.1.3 <high-level actionable subtask>
  - 1.1.4 verify implementation against guidelines
  - 1.1.5 code must be covered by tests
  - 1.1.6 tests and types must pass: run `pnpm verify`
  - 1.1.7 reconcile `spec.md` for every new user-visible requirement

## 2. orm

- [ ] 2.1 <change slice title>
  - 2.1.1 scope: ORM table configuration
  - 2.1.2 acceptance: table declarations can opt into read-only query objects without changing default writable behavior.
  - 2.1.3 <high-level actionable subtask>
  - 2.1.4 verify implementation against guidelines
  - 2.1.5 code must be covered by tests
  - 2.1.6 tests and types must pass: run `pnpm verify`
  - 2.1.7 reconcile `spec.md` for every new user-visible requirement

## 3. docs

- [ ] 3.1 <docs change slice title>
  - 3.1.1 <high-level docs subtask>

## 4. changeset

- [ ] 4.1 Finalize the change
  - 4.1.1 Follow `.agents/skills/changeset/SKILL.md` to finalize the change.

Do not add docs or changeset sections to a partial task list. A partial task list should contain section 0 and only the affected package or script sections needed for the explicitly requested scope.

While writing tasks.md, keep this implementation-time rule in mind but do not emit it as its own section:

  • If later user input is only a non-feature design ask, implementation preference, wording tweak, or detail that does not change user-visible behavior or public API, do not add it to spec.md.
  • If it changes user-visible behavior, adds/changes a requirement, or changes public API, update the relevant ## Detailed Design subsection before implementation. Add a new responsibility-centered subsection only when none fits.
  • Keep Summary, What Changes, Assumptions, and Capabilities aligned when the design materially changes.

Final Check

Before finishing, verify:

  • the provided path is an existing spec.md under changes/<feature-name>/<NUMBER-idea-name>/
  • relevant Orchid docs, code, tests, exports, and guidelines were inspected
  • every important What Changes item and declared capability is covered by tasks.md
  • tasks.md starts with section 0; 0.1 and 0.2 are the only numbered entries there and are not checkboxes
  • section 0 lists root and relevant nested code or test guidelines
  • every later checkbox task has numbered subtasks; package tasks start with scope: and acceptance:
  • every coding task ends with the four required verification subtasks, including pnpm verify
  • non-coding tasks do not include coding verification subtasks
  • sections are only affected packages, optional root docs for full task lists, and final changeset for full task lists
  • tasks are ordered for iterative implementation, avoid standalone test tasks, avoid exact test-writing instructions, and fully cover the design unless the user explicitly requested a partial task list

© romeerez, MIT. 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 1 other file in .agents/skills/task-list of romeerez/orchid-orm.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit de54a3b

Compare with similar skills

Task List 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 List compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Task List this skillromeerez/orchid-orm543—~2.1kAutomated safety check: PassMIT
MemPalace Task HandoffMemPalace/mempalace59k—~1.9kAutomated safety check: PassMIT
Planning And Task Breakdownabashev/vfs-s31068 repos~1.9kAutomated safety check: PassApache-2.0
Incremental Implementationaddyosmani/agent-skills103k1 repos~2.3kAutomated safety check: PassMIT
ULW Plan Workflowcode-yeongyu/oh-my-openagent70k—~3.9kAutomated safety check: PassCustom licence
Implementation Plan Creatortailcallhq/forgecode7.6k1 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • MemPalace Task Handoff

    MemPalace/mempalace

    Creates, hands off, claims, executes and closes agent tasks through the MemPalace logstream, with approval of the exact task before it is recorded.

    59k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Breaks work into ordered tasks. An agent skill from abashev/vfs-s3.

    106 GitHub starsUsed in 8 repos~1.9k tokens
    Agent WorkflowsAuto-check passed
  • Incremental Implementation

    addyosmani/agent-skills

    Delivers a change in thin vertical slices, each implemented, tested, verified and committed before the next, using vertical, contract-first or risk-first slicing.

    103k GitHub starsUsed in 1 repo~2.3k tokens
    Agent WorkflowsAuto-check passed
  • ULW Plan Workflow

    code-yeongyu/oh-my-openagent

    Explore-first planning that turns a vague or large request into one decision-complete work plan, written only after your approval and executed by a separate worker.

    70k GitHub stars~3.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Implementation Plan Creator

    tailcallhq/forgecode

    Writes a structured Markdown implementation plan with checkbox tasks, verification criteria and risks, then checks it with a validation script; no code changes.

    7.6k GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check passed
  • Runs a whole project unattended on an agtx kanban board, decomposing the goal, starting tasks, unblocking workers and merging each result.

    1.7k GitHub stars~3.8k tokensUpdated 5 days ago
    Agent WorkflowsAuto-check passed

More from romeerez/orchid-orm

All 13 skills in this repo
  • Spec

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "write spec" or "make spec".

    543 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Type Optimizer

    romeerez/orchid-orm

    A skill your agent uses when need to optimize TypeScript types.

    543 GitHub stars~798 tokensUpdated today
    Auto-check passed
  • Code Doc

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "code doc" to create or update internal Orchid ORM code documentation from changes/ specs, short-code feature folders, or existing implementation code.

    543 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Ideas

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "write ideas" or "make ideas".

    543 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Implemenation Note

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "implementation note" for an existing change idea.

    543 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Refine

    romeerez/orchid-orm

    A skill your agent uses when the user prompts "refine design".

    543 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

Questions about Task List

What does Task List do?

A skill your agent uses when user asks to write a task list, not to do a task. Task List is an agent skill from romeerez/orchid-orm.

When should I use Task List?

Task List fits situations like: user asks to write a task list; not to do a task.

How do I install Task List in Claude Code?

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

How do I install Task List in Codex?

Run `npx skills add romeerez/orchid-orm --skill task-list -a codex`. Or copy the skill folder (.agents/skills/task-list in romeerez/orchid-orm) into .agents/skills/task-list in your project. Codex loads it when a task matches its description.

Can I use Task List 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 romeerez/orchid-orm --skill task-list -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-list, .gemini/skills/task-list, .github/skills/task-list and .opencode/skills/task-list in your project.

What does Task List need to run?

Going by SKILL.md and its folder, Task List needs the command-line tools its instructions call (pnpm).

Does Task List 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 List 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 List use?

Task List 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 Task List use?

About 2.1k tokens (SKILL.md is roughly 8.4k 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 Task List?

Skills that share tags, products or a category with Task List: MemPalace Task Handoff (MemPalace/mempalace, 59k stars), Planning And Task Breakdown (abashev/vfs-s3, 106 stars), Incremental Implementation (addyosmani/agent-skills, 103k stars) and ULW Plan Workflow (code-yeongyu/oh-my-openagent, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Task List?

romeerez (a GitHub user) maintains it in romeerez/orchid-orm, which has 543 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 7, 2026.

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