task-management
Manage Joel's task system in Todoist. Triggers on: 'add a task', 'create a todo', 'what's on my list', 'today's tasks', 'what do I need to do', 'remind me to', 'inbox', 'complete', 'mark done', 'weekly review', 'groom tasks', 'what's next', or when actionable items emerge from other work. Also triggers when Joel mentions something he needs to do in passing — capture it.
68
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 is a strong skill description with excellent trigger term coverage and clear 'when to use' guidance. Its main weakness is that the 'what it does' portion is somewhat thin — 'Manage Joel's task system in Todoist' is a single high-level statement rather than a list of specific capabilities. The extensive trigger phrases partially compensate by implying capabilities, but explicit capability listing would strengthen it.
Suggestions
Expand the opening sentence to list specific concrete actions, e.g., 'Creates tasks, marks tasks complete, lists tasks by date/project, performs weekly reviews, and grooms the inbox in Joel's Todoist system.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Todoist task management) and implies actions like adding tasks, completing tasks, and reviewing, but doesn't explicitly list concrete capabilities like 'create tasks, mark tasks complete, list tasks by date, perform weekly reviews'. The actions are mostly embedded in trigger phrases rather than stated as capabilities. | 2 / 3 |
Completeness | The description answers both 'what' (manage Joel's task system in Todoist) and 'when' with extensive explicit trigger guidance including specific phrases and the proactive capture scenario. The 'Triggers on:' clause serves as a clear equivalent to 'Use when...'. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would actually say: 'add a task', 'create a todo', 'what's on my list', 'today's tasks', 'remind me to', 'mark done', 'weekly review', 'what's next'. These are highly natural phrases and cover many variations of how someone would interact with a task system. | 3 / 3 |
Distinctiveness Conflict Risk | Very distinct — it's specifically about Joel's Todoist task management system with highly specific trigger terms like 'inbox', 'weekly review', 'groom tasks'. The combination of a named tool (Todoist) and a named user (Joel) makes it 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 strong, highly actionable skill with excellent CLI examples, clear workflows, and well-defined behavioral rules (task surfaces, anti-patterns, agent vs. human routing). Its main weaknesses are the verbose philosophy section that explains well-known productivity frameworks rather than just encoding their rules, and the monolithic structure that could benefit from splitting the CLI reference and SOPs into separate files.
Suggestions
Compress the Philosophy section to just the 'What This Means In Practice' bullets — Claude doesn't need GTD/Shape Up/Tiny Habits explained, just the operational rules derived from them.
Consider extracting the CLI reference (Read/Write/Filters) into a separate TODOIST-CLI.md to reduce the main skill's token footprint and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The philosophy section (GTD, Shape Up, Tiny Habits) is verbose and explains concepts that are general knowledge rather than actionable configuration. The task surfaces, CLI reference, and SOPs are efficient, but the opening ~40 lines could be cut significantly without losing operational value. | 2 / 3 |
Actionability | Excellent executable CLI commands throughout with concrete examples, specific flags, and copy-paste ready snippets. The priority table with API inversion, filter syntax examples, and inbox processing workflow are all immediately actionable. Good/bad task examples make the distinction concrete. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced: inbox processing has a 5-option decision tree, weekly review has explicit numbered steps, ADR→Tasks has a clear loop with cross-referencing. The 'Could the agent just do this?' checkpoint and the audience-first routing (human/decision/machine) serve as validation gates before task creation. | 3 / 3 |
Progressive Disclosure | The content is a single long document (~250 lines) with no references to supporting files. The philosophy section, CLI reference, filter syntax, and SOPs could be split into separate files. However, the internal structure with clear headers and tables provides reasonable navigability within the monolith. | 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
- joelhooks/joelclaw
- Commit
03f0a59
- 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.