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

72%

Does it follow best practices?

Impact

96%

1.50x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./jj-todo-workflow/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and well-sequenced with strong validation discipline, but SKILL.md is a lengthy monolith with some repetition between sections and limited use of bundle files to defer detail.

Suggestions

Consolidate the overlap between 'Quick Start' and 'Basic Workflow' — keep a single concise end-to-end example and link the rest, to improve token efficiency.

Move the larger detail blocks (e.g. the full 'Planning Parallel Tasks (DAG)' walkthrough and 'AI-Assisted TODO Workflow') into a reference file and leave a short summary plus a clearly signaled link, advancing progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and action-oriented with concrete bash blocks, but it repeats material between the Quick Start and Basic Workflow sections and carries some explanatory prose that could be tightened, so it is not the lean level-3 case.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands throughout (jj-todo-create, jj-flag-update, jj-todo-next --mark-as done, jj log revsets) backed by real scripts in scripts/, matching the executable-and-specific anchor.	3 / 3
Workflow Clarity	Multi-step processes are clearly sequenced (numbered Quick Start, Basic Workflow 1-3) with explicit validation checkpoints ('Verify ALL acceptance criteria met', 'FIRST: make check ... ONLY if all checks pass') and a stop-and-report feedback loop, avoiding the destructive/batch cap at 2.	3 / 3
Progressive Disclosure	It has a well-signaled one-level reference (references/parallel-agents.md) and a clear scripts table, but the SKILL.md itself is a long monolithic body with status tables, DAG planning, AI-agent guidance and tips all inline that could be split out, so it does not reach the clean overview-plus-references level.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and clearly distinctive, but its trigger guidance states purpose ("Use to plan tasks") rather than explicit "Use when..." conditions, and it leans on JJ jargon over natural user phrasings.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases, e.g. 'Use when the user wants to plan a task list as commits, track TODO progress, or coordinate Planner/Worker task division in a JJ repo'.

Soften jargon in the trigger portion — surface plain terms like 'plan tasks', 'track TODOs', 'manage task dependencies' alongside '[task:*] flags' and 'DAGs' so users who don't know JJ internals still match.

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" — matching the multiple-specific-actions anchor rather than the domain-only level below.	3 / 3
Completeness	The "what" is explicit and strong, but the only trigger phrasing is "Use to plan tasks..." which states purpose rather than explicit "Use when..." conditions, so per the judging guideline a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains some natural terms a user might say ("TODO", "plan tasks", "track progress") but is heavy on JJ jargon ("empty commits", "[task:*] flags", "DAGs", "status transitions") and lacks common surface-level phrasings, so it sits at the some-keywords-but-missing-variations level rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	It occupies a clear niche (JJ-based TODO/commit workflow) and explicitly states "Requires the working-with-jj skill", making it unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 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
Commit: ac633fa

Reviewed: 5 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.