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.
72
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong, well-crafted skill description that clearly communicates what the skill does, when to use it, and what distinguishes it from other skills. It includes explicit trigger terms, prerequisite information, and anti-patterns (what NOT to do manually). The only minor note is the use of imperative voice ('MUST be used') rather than third person declarative, but this doesn't significantly harm clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and components: 'full module (context, provider, tool, hooks, UI components) and all integration wiring', plus explicitly names what NOT to do ('Do NOT manually create todo state management or tool definitions'). Clearly describes the scope of what the skill produces. | 3 / 3 |
Completeness | Clearly answers both 'what' (handles full todo/task module with context, provider, tool, hooks, UI components, and integration wiring) and 'when' (whenever adding a task/todo list feature to a Flows app with Atlas chat, with explicit trigger terms listed). Also includes prerequisite information. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms explicitly listed: 'todo list, task list, task tracking, TodoWrite, todo panel, task panel, progress tracking, add todos, add tasks'. These cover both natural user language ('add tasks', 'task tracking') and technical terms ('TodoWrite'). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — scoped specifically to 'Flows app with Atlas chat' todo/task features, with a named prerequisite ('integrate-atlas-chat'). The combination of the specific framework context and the todo/task domain makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable integration skill with clear step sequencing and concrete code examples at every stage. Its main weakness is slight verbosity in explanatory sections (the file purpose table and the 'Done' summary) and the inability to verify the referenced bundle files. The workflow is well-designed with a read-first approach and a verification step at the end.
Suggestions
Trim or remove the 'Done' section — Claude doesn't need a summary of what the feature does after completing the integration steps.
Consider moving the file-purpose table in Step 2 to a comment in an index file or removing it entirely, since Claude will read the actual source files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanation (e.g., the 'Done' section describing what the agent will do is informational padding Claude doesn't need). The table in Step 2 describing each file's purpose is borderline — useful for orientation but Claude could infer most of it. The inline code examples are well-targeted though. | 2 / 3 |
Actionability | Provides fully executable, copy-paste-ready code snippets for every integration point (TodoProvider wrapping, tool wiring, panel rendering, tool result card rendering). Import paths, hook usage, and wiring patterns are all concrete and specific with clear adjustment notes. | 3 / 3 |
Workflow Clarity | Clear 7-step sequence starting with reading the app state, creating the module, then progressively wiring each piece. Step 1 is a read/verify step, Step 7 is an explicit validation checkpoint (type-check + tests). The ordering is logical and dependencies between steps are clear. | 3 / 3 |
Progressive Disclosure | The skill references a `<skill-dir>/code/` directory with 8 files that should be copied, which is good progressive disclosure of implementation details. However, no bundle files were provided to verify these references, and the skill itself is moderately long (~120 lines) with all integration code inline rather than potentially splitting the wiring examples into a separate reference file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- cognitedata/builder-skills
- Commit
d6af887
- Reviewed
Table of Contents
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.