jj-todo-workflow
Structured TODO commit workflow using JJ (Jujutsu). Use to plan tasks as empty commits with [task:*] flags, track progress through status transitions, manage parallel task DAGs with dependency checking. Enforces completion discipline. Enables to divide work between Planners and Workers. **Requires the working-with-jj skill**
88
85%
Does it follow best practices?
Impact
96%
1.50xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
85%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 description that clearly defines a specific workflow tool for JJ-based task management via commits. It excels at specificity and distinctiveness, with a clear niche that won't overlap with other skills. The main weakness is that trigger terms lean heavily technical, which may not match how users naturally phrase requests for task planning or tracking.
Suggestions
Add more natural-language trigger terms users might say, such as 'task management', 'project planning', 'work breakdown', or 'todo tracking' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: plan tasks as empty commits with [task:*] flags, track progress through status transitions, manage parallel task DAGs with dependency checking, enforce completion discipline, divide work between Planners and Workers. | 3 / 3 |
Completeness | Clearly answers both what (plan tasks as empty commits, track progress, manage parallel task DAGs) and when ('Use to plan tasks...track progress...manage parallel task DAGs with dependency checking'). The 'Use to' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'TODO', 'commit', 'JJ', 'Jujutsu', 'task', 'DAG', and 'dependency', but these are fairly technical. Missing more natural user terms like 'task management', 'project planning', 'work tracking', or 'todo list'. A user might not naturally say 'task DAGs' or '[task:*] flags'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a very clear niche: JJ/Jujutsu-based TODO commit workflow with specific concepts like [task:*] flags, Planners/Workers roles, and task DAGs. Unlikely to conflict with generic task management or git skills. | 3 / 3 |
Total | 11 / 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-crafted skill that provides a complete, actionable workflow for using JJ as a TODO management system. Its strengths are excellent workflow clarity with validation checkpoints, strong actionability with concrete commands throughout, and good progressive disclosure separating concerns across files. The main weakness is moderate verbosity—some sections could be tightened (e.g., the role annotations on every heading, repeated cross-references to the companion skill, and the renaming note) without losing clarity.
Suggestions
Trim the role annotations (Planners & Workers) from section headings—a single legend at the top would suffice and save repetition across ~10 headings.
Remove the NOTE about the 'broken' to 'standby' rename, which is changelog-style information that doesn't help Claude perform the task.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~300 lines) and includes some redundancy (e.g., reminders about which skill scripts come from, the NOTE about renaming 'broken' to 'standby', repeated explanations of --no-edit). However, most content is genuinely instructive and not explaining things Claude already knows. Some tightening is possible but it's not egregiously verbose. | 2 / 3 |
Actionability | The skill provides concrete, executable bash commands throughout, with specific script names, flags, and realistic examples. The quick start section is copy-paste ready, the workflow steps use actual commands, and the helper scripts table gives clear invocation patterns. The TODO description template with a full example is highly actionable. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced (Plan → Work → Complete → Next) with explicit validation checkpoints: verify acceptance criteria before marking done, check dependencies before starting, run tests before transitioning. The 'When to Stop and Report' section provides clear error recovery guidance. The jj-todo-next script includes a feedback loop (review specs → verify compliance → only then mark done). The completion discipline section explicitly caps progression when criteria aren't met. | 3 / 3 |
Progressive Disclosure | The skill is well-structured with a Quick Start overview, then progressively deeper sections (Status Flags, Basic Workflow, Parallel DAGs, AI-Assisted workflow). It references external files appropriately (working-with-jj skill, references/parallel-agents.md) at one level deep with clear signaling. The helper scripts table serves as a concise reference. Content is appropriately split between this skill and its companion. | 3 / 3 |
Total | 11 / 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
- YPares/agent-skills
- Commit
aed1afb
- 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.