arn-code-taskify
This skill should be used when the user says "taskify", "create task list", "create tasks", "convert plan to tasks", "generate tasks from plan", "create tasks from plan", "turn plan into tasks", "arness code taskify", or wants to convert a structured project plan's TASKS.md into an executable Claude Code task list with proper dependency management.
86
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 description excels at trigger term coverage and completeness, providing an extensive list of natural phrases that would activate the skill and clearly stating both what it does and when to use it. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., parsing dependencies, generating ordered task sequences, handling parallel vs sequential tasks). The description is functional and effective for skill selection despite being somewhat narrow in capability description.
Suggestions
Expand the capability description to list more specific concrete actions, e.g., 'Parses TASKS.md files, resolves task dependencies, generates ordered executable task lists, and handles parallel vs sequential task execution.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description mentions converting a structured project plan's TASKS.md into an executable Claude Code task list with dependency management, which names the domain and a key action, but doesn't list multiple concrete actions beyond the single conversion task. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (convert a structured project plan's TASKS.md into an executable Claude Code task list with proper dependency management) and 'when' (lists explicit trigger phrases and conditions). The trigger guidance is very explicit. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'taskify', 'create task list', 'create tasks', 'convert plan to tasks', 'generate tasks from plan', 'turn plan into tasks', and mentions TASKS.md specifically. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific trigger terms like 'taskify' and 'arness code taskify', and a clear niche around converting TASKS.md files into Claude Code task lists with dependency management. Unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 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-crafted skill with excellent actionability and workflow clarity — the 5-step process is clearly sequenced with concrete tool calls, validation checkpoints, and error recovery paths. The main weakness is moderate verbosity, particularly in the task list persistence setup section which could be more concise, and the lack of progressive disclosure for what is a fairly lengthy document. The error handling section partially duplicates guidance already embedded in the workflow steps.
Suggestions
Tighten the 'Deferred Task List Setup' section — the branching logic for persistent task lists is verbose and could be condensed into a more compact decision tree format.
Consider extracting the error handling section since most error cases are already addressed inline in the workflow steps; either consolidate into the steps or keep only truly additional guidance in the separate section.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some verbose sections that could be tightened — the deferred task list setup section is quite lengthy with multiple branching paths explained in detail, and the error handling section partially repeats guidance already given in the workflow steps. However, it avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific tool calls (TaskCreate, TaskUpdate, TaskList, AskUserQuestion), exact field mappings with examples, specific parameter formats, and concrete example mappings (e.g., Task 1 → claude_id '5'). The table for parsing fields and the ID map examples make implementation unambiguous. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 explicit steps with validation at multiple points: Step 1 validates config existence, Step 2 validates parsed data (duplicates, invalid references, circular deps) with a user decision gate, Step 3 enforces sequential ordering, Step 4 handles dependency wiring, and Step 5 provides explicit verification against the source TASKS.md with discrepancy warnings. Error recovery paths are well-defined. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and a logical flow, but it's a fairly long monolithic document (~150+ lines of content) with no references to external files. The deferred task list setup and error handling sections could potentially be split out. However, since no bundle files exist, there's limited opportunity for external references, and the content is all directly relevant. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
1fe948f
- 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.