create-invoke-task
Create a new Python invoke task for the dda CLI
65
58%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/create-invoke-task/SKILL.mdQuality
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is narrow and project-specific, which helps with distinctiveness, but it is too terse—listing only a single action and lacking any 'Use when...' guidance. It would benefit from enumerating concrete sub-actions and explicitly stating the trigger conditions under which Claude should select this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to add a new CLI command, create an invoke task, or extend the dda CLI.'
List more specific actions or sub-capabilities, such as 'scaffolds task boilerplate, registers the task in tasks.py, adds argument parsing and docstrings.'
Include natural trigger term variations like 'pyinvoke', 'tasks.py', 'CLI command', 'dda command' to improve keyword coverage.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (Python invoke task for dda CLI) and one action (create), but it only describes a single action without listing additional concrete capabilities or details about what creating such a task involves. | 2 / 3 |
Completeness | The description answers 'what' (create a new Python invoke task) but completely lacks any 'Use when...' clause or explicit trigger guidance, which per the rubric should cap completeness at 2, and since the 'when' is entirely missing, it scores a 1. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'Python', 'invoke task', and 'dda CLI' that a user familiar with the project might use, but it misses common variations or synonyms (e.g., 'pyinvoke', 'tasks.py', 'command', 'CLI command'). | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'dda CLI' and 'invoke task' provides some specificity that narrows the scope, but it could still overlap with general Python CLI or task-creation skills without clearer distinguishing triggers. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
85%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, concise skill that clearly guides Claude through creating an invoke task. The workflow is logical with good conditional branching and a verification step. The main weakness is the lack of an inline code example showing a minimal @task function, which would make the skill more immediately actionable without requiring file reads first.
Suggestions
Add a minimal executable code example in Step 3 showing a complete @task decorated function (e.g., a simple task with one parameter) so Claude has an immediate template without needing to read reference files first.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what invoke is, what decorators are, or other concepts Claude already knows. Every section serves a clear purpose and there's no padding or unnecessary context. | 3 / 3 |
Actionability | The skill provides concrete guidance (specific files to read, specific patterns to follow, specific commands to run) but lacks executable code examples — there's no sample @task decorated function showing the exact pattern to follow. The instruction to 'follow the patterns from Step 2' delegates the concrete example to reading existing files rather than providing a copy-paste template. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 steps: gather info → read reference → create task → register if needed → verify. It includes a verification step with a concrete command, and the conditional logic (new module vs existing) is clearly delineated. The feedback loop is implicit but the verification step catches errors. | 3 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines), the content is well-organized with clear sections. It references specific files in the codebase (tasks/auth.py, tasks/agent.py, tasks/__init__.py) as one-level-deep references for deeper learning, which is appropriate progressive disclosure within a repository context. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- DataDog/datadog-agent
- Commit
0f36ad4
- 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.