integrate-todo-list

TodoWrite panel for an already-approved in-app useAtlasChat UI. New AI features use integrate-fusion-agent. Triggers: TodoWrite, todo panel — only when useAtlasChat already exists.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%Weight 40%Scale 1-5

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

A tight, highly actionable integration guide with sequenced steps and copy-paste code. The main gaps are a non-explicit validation feedback loop and bundle files that are referenced but not shipped alongside the SKILL.md being reviewed.

Suggestions

Turn Step 7 into an explicit feedback loop: "If `tsc --noEmit` reports errors, fix them and re-run before proceeding" to raise workflow clarity to 5.

Replace or supplement the `find . -path ...` discovery with a direct relative reference to the code bundle, and ensure the `code/` files are actually present in the skill bundle so the references are verifiable.

Trim a few justifying-asides (e.g. the null-render safety note) that restate what the code already shows.

Dimension	Reasoning	Score
Conciseness	Largely lean — tables, code blocks, and imperative steps with no padding of concepts Claude already knows — with a few earned rationale comments (e.g. "Keep a ref so getAppContext always reads fresh state"). Not a 5 because a couple of inline explanations (e.g. "TodoPanel returns null when the list is empty, so it's safe to always render it") could be trimmed.	4 / 5
Actionability	Provides copy-paste ready TSX/TS in Steps 3-6, a concrete `find` command and file table in Step 2, specific files to read in Step 1, and the exact verify command (`pnpm tsc --noEmit`) in Step 7, covering the common integration cases.	5 / 5
Workflow Clarity	Seven clearly sequenced steps with a terminal validation checkpoint (Step 7: type-check + tests). Not a 5 because the error-recovery feedback loop is only weakly implied ("confirm there are no errors") rather than an explicit validate-fix-revalidate cycle.	4 / 5
Progressive Disclosure	Well-organized into per-step section headers, with implementation code offloaded to a one-level-deep `<skill-dir>/code/` directory surfaced via a `find` command and a clear file-purpose table. Not a 5 because navigation relies on a runtime `find` rather than a direct relative path, and no bundle files are present in this review to confirm the referenced code files actually exist.	4 / 5
	Total	17 / 20 Passed

Description

82%Weight 40%Scale 1-5

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 concise, well-targeted description that explicitly states both capability and trigger conditions, and proactively distinguishes itself from a sibling skill. Its only weakness is that it names essentially one concrete action under two synonyms rather than a broad action list.

Suggestions

Expand the action list beyond the single panel concept (e.g. "add a TodoWrite tool, render a live progress panel, and inject task state into prompts") to lift specificity toward 5.

Add a couple of common natural synonyms like "task list" or "checklist" alongside "todo panel" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("in-app useAtlasChat UI") and one concrete action ("TodoWrite panel"), but "TodoWrite" and "todo panel" are synonyms for the same action rather than multiple distinct actions, matching the 1-2 concrete actions anchor. Not a 4 because it does not list several distinct specific actions.	3 / 5
Completeness	Clearly answers both what ("TodoWrite panel for an already-approved in-app useAtlasChat UI") and when ("Triggers: TodoWrite, todo panel — only when useAtlasChat already exists") with concrete trigger phrases, matching the explicit what-and-when anchor.	5 / 5
Trigger Term Quality	Explicitly lists "Triggers: TodoWrite, todo panel" plus the "useAtlasChat" precondition, giving good natural keyword coverage a user would say; not a 5 because a few common variations (e.g. "task list", "checklist") are missing.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche gated on "useAtlasChat already exists" plus explicit conflict avoidance ("New AI features use integrate-fusion-agent"), giving minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 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
Path: skills/integrate-todo-list/SKILL.md
Commit: c87160a

Reviewed: 5 days 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.