planning-and-task-breakdown

Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/planning-and-task-breakdown/SKILL.md

Quality

Content

88%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.

This is a strong, highly actionable process skill: concrete templates, a well-sequenced workflow with validation checkpoints and error-recovery paths, and disciplined handling of pre-existing plan conflicts. The only weaknesses are minor — light motivational padding in the rationalizations section and a single reference pointing at a file not present in the bundle.

Dimension	Reasoning	Score
Conciseness	The body is overwhelmingly prescriptive — templates, sizing tables, explicit rules — with only minor over-explanation: the "Common Rationalizations" table ("Planning is the task. Implementation without a plan is just typing.") and Overview editorializing are coaching that could be trimmed. Not level 5's "every token earns its place", but well above level 3.	4 / 5
Actionability	As an instruction-only skill it provides copy-paste-ready artifacts: a complete task template (description, acceptance criteria, verification, dependencies, files, scope), a full plan-document template, concrete paths (`tasks/plan.md`, `tasks/todo.md`), and concrete tracker mappings (`bd dep add`, "blocked by"). Placeholders like "[the repository's focused-test command]" are appropriately justified by cross-project genericity.	5 / 5
Workflow Clarity	A clear 5-step sequence with explicit checkpoints after every 2-3 tasks, feedback loops for error recovery (validation fails → fix → re-validate; existing incomplete plan → stop and ask), and a final verification checklist before implementation. Matches the top anchor including checklists for complex processes.	5 / 5
Progressive Disclosure	Well-organized sections with clear headers and appropriately inline templates. The single external reference (`../../references/definition-of-done.md`) is clearly signaled and one level deep, but no `references/` bundle directory exists, leaving a dangling out-of-bundle path — a minor organization gap that keeps it below level 5.	4 / 5
	Total	18 / 20 Passed

Description

70%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 solid description with an explicit and well-constructed "Use when..." trigger section — the strongest part. The "what" clause is thinner than the rubric's top anchors: it states one action where the skill actually delivers dependency mapping, acceptance criteria, sizing, checkpoints, and plan documents.

Suggestions

Expand the "what" clause with 2-3 more of the skill's concrete outputs, e.g. "Breaks work into ordered tasks with acceptance criteria, dependency ordering, and verification checkpoints; produces a plan document and task list."

Add natural trigger synonyms users commonly say, such as "plan this work", "break this down", or "create a todo list", to broaden keyword coverage.

Consider naming the concrete artifacts (plan document, task list, external tracker items) to sharpen distinctiveness from generic planning advice.

Dimension	Reasoning	Score
Specificity	The single concrete action "Breaks work into ordered tasks" names the domain but leaves the capability surface thin — no mention of acceptance criteria, dependency ordering, checkpoints, or plan documents that the skill actually delivers. This matches the anchor for naming a domain with 1-2 concrete actions rather than the several specific actions of level 4.	3 / 5
Completeness	Both "what" ("Breaks work into ordered tasks") and "when" (three explicit "Use when..." clauses) are present. The "what" is clear but minimal — a one-clause action summary — which keeps it below level 5's standard of comprehensively and explicitly answering both.	4 / 5
Trigger Term Quality	Triggers like "have a spec", "task feels too large to start", "estimate scope", and "parallel work" are natural phrases users would say. Common synonyms such as "plan", "break this down", "decompose", or "todo list" are missing, so it falls just short of comprehensive level-5 coverage.	4 / 5
Distinctiveness Conflict Risk	The trigger conditions (oversized tasks, scope estimation, parallelization) are specific enough to distinguish it from most skills, though it retains overlap risk with general project-planning or spec-writing skills. Minor overlap only, matching level 4.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: addyosmani/agent-skills
Path: skills/planning-and-task-breakdown/SKILL.md
Commit: 2686b62

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.