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**

1.50x

Quality

80%

Does it follow best practices?

Impact

96%

1.50x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

73%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 well-structured, actionable skill body with strong workflow sequencing and validation discipline. It would benefit from trimming repetition around completion discipline and pushing more peripheral material into reference files to tighten the token budget.

Suggestions

Consolidate the repeated completion-discipline guidance into a single canonical checklist; the 'No Good Enough' content, the Quick Start step 3/5, and the Status Flags notes largely overlap.

Move the 'AI-Assisted TODO Workflow' and 'Planning Parallel Tasks (DAG)' sections (or the description template) into reference files and keep one-line pointers in the main body.

Make the helper-script invocation example concrete by showing the actual full-path form once (e.g. /path/to/scripts/jj-todo-create) since the Quick Start already flags this gap.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's intelligence about JJ, but several sections restate the same points (completion discipline is hammered across Quick Start, Status Flags, and a dedicated Tips section) and there is light over-explanation of the Planner/Worker framing.	3 / 5
Actionability	Provides concrete, runnable commands throughout (jj-todo-create, jj-flag-update, jj-todo-next with expected output, dependency-check revsets) and a copy-pasteable description template; minor gaps are placeholder IDs like <T1-id> and the noted-but-not-written full script paths.	4 / 5
Workflow Clarity	The full plan → work → verify → transition cycle is clearly sequenced with explicit validation checkpoints ('make check' before marking done, 'ONLY if all checks pass'), dependency warnings, and a feedback loop for deviations via Post-Implementation notes.	5 / 5
Progressive Disclosure	Good structure with a well-signaled one-level-deep reference (references/parallel-agents.md) and a clear scripts table, but the main file still inlines a fair amount of material (full description template, AI-assisted workflow, parallel DAG planning) that is appropriately placed rather than ideally split.	4 / 5
	Total	16 / 20 Passed

Description

87%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 strong, specific description with explicit 'Use to' trigger guidance and a clear dependency declaration. It distinguishes itself well from sibling skills; minor gains possible by trading some process vocabulary for more everyday trigger phrasing.

Suggestions

Consider adding a few everyday trigger phrases (e.g. 'TODO list', 'task breakdown', 'track what's left to do') alongside the process terms so users who don't know the [task:*] convention still match it.

Spell out one or two most concrete operations (e.g. 'create empty revisions as specs and mark them done when complete') to lift specificity from 4 to 5.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'plan tasks as empty commits with [task:*] flags', 'track progress through status transitions', 'manage parallel task DAGs with dependency checking', 'Enforces completion discipline' — but they are somewhat abstracted and could enumerate more concrete operations.	4 / 5
Completeness	Clearly states what it does (structured TODO commit workflow with status flags and DAGs) and explicitly when to use it ('Use to plan tasks...'), plus a hard dependency note ('Requires the working-with-jj skill').	5 / 5
Trigger Term Quality	Includes natural, greppable terms users would say ('TODO', 'commit workflow', 'plan tasks', 'parallel task DAGs', 'Planners and Workers'), though it leans slightly on process jargon rather than the most common phrasings.	4 / 5
Distinctiveness Conflict Risk	The JJ + [task:*] TODO-commit niche plus the explicit dependency on working-with-jj makes it highly distinct and unlikely to trigger for the wrong skill.	5 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: YPares/agent-skills
Path: jj-todo-workflow/SKILL.md
Commit: e9d2149

Reviewed: 3 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.