integrate-todo-list

MUST be used whenever adding a task/todo list feature to a Flows app with Atlas chat. Do NOT manually create todo state management or tool definitions — this skill handles the full module (context, provider, tool, hooks, UI components) and all integration wiring. Prerequisite: integrate-atlas-chat must already be set up. Triggers: todo list, task list, task tracking, TodoWrite, todo panel, task panel, progress tracking, add todos, add tasks.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable integration skill with complete code examples, a clear sequenced workflow, and a verification step. Its only weakness is mild conciseness padding in the introduction and the closing summary.

Suggestions

Trim the introductory 'giving the user real-time visibility into what the agent is doing and why' clause — the purpose of a todo list is inferrable, and the body already demonstrates it.

Shorten or remove the 'Done' section's restated behavior bullets since they duplicate the intro and Step descriptions; a one-line wrap-up is enough.

Consider folding the per-file purposes already in the Step-2 table so the body stays a lean overview pointing to the code bundle.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with focused code blocks and no basic-concept explanations, but the intro 'giving the user real-time visibility into what the agent is doing and why' clause and the 'Done' section restating the same behaviors are mildly redundant and could be tightened.	2 / 3
Actionability	Each step ships complete, executable TSX/TS with real imports and a concrete discovery command ('find . -path "/.agents/skills/integrate-todo-list/code" -type d'); placeholders like '{/ existing children */}' are explicitly justified ('adjust path to match the app's conventions').	3 / 3
Workflow Clarity	Seven clearly sequenced steps culminate in an explicit Step-7 verification ('pnpm tsc --noEmit' and running tests to confirm no regression); this is a non-destructive integration so the absence of a deep validate-fix-retry loop is acceptable.	3 / 3
Progressive Disclosure	SKILL.md is a well-sectioned integration overview that points one level deep to a clearly-signaled code bundle via a file/purpose table (types.ts, TodoContext.tsx, TodoPanel.tsx, etc.), avoiding a monolithic wall of inline implementation.	3 / 3
	Total	11 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A high-quality description that clearly states what the skill does, when to use it, and its prerequisite, with a strong set of natural trigger terms and a distinct niche. It uses directive third-person-style voice with no first/second-person pronouns, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete deliverables — 'handles the full module (context, provider, tool, hooks, UI components) and all integration wiring' — naming the specific pieces it produces rather than vague actions.	3 / 3
Completeness	Explicitly answers both what ('handles the full module ... and all integration wiring') and when ('MUST be used whenever adding a task/todo list feature' plus an explicit Triggers list), with a named prerequisite.	3 / 3
Trigger Term Quality	A dedicated 'Triggers:' list gives natural terms users would say — 'todo list, task list, task tracking, TodoWrite, todo panel, task panel, progress tracking, add todos, add tasks' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Clear niche — a todo/task-list feature for a Flows app with Atlas chat — with distinct triggers and a prerequisite (integrate-atlas-chat) that make it unlikely to fire for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: cognitedata/builder-skills
Commit: ab7b5f8

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.