task-decomposition

Use this skill when a user presents a large, vague goal. Break it into concrete, ordered sub-tasks before starting any work. Apply whenever the request is larger than a single focused action.

Quality

76%

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 ./memory_data/skills/task-decomposition/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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

The body is concise and well-organized with a clear sequenced workflow and an explicit user-confirmation checkpoint. The main gap is the lack of a concrete worked example, which leaves actionability just short of fully copy-paste-ready guidance.

Suggestions

Add a short worked example showing an input vague goal and the resulting ordered sub-task list to make the procedure fully actionable.

Optionally pair the anti-pattern with its corrected counterpart so the contrast demonstrates the intended behavior.

Clarify step 4 ("flag any unknowns") with one concrete example of an unknown and how to surface it.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation and every line earns its place ("Before starting a large goal, decompose it." plus a tight 5-step list and one anti-pattern), matching the lean 3-anchor.	3 / 3
Actionability	The steps are concrete directives ("Restate the end goal in one sentence", "List the concrete sub-tasks... in order"), but there is no worked example showing what a good decomposition looks like, leaving guidance actionable yet incomplete as in the 2-anchor.	2 / 3
Workflow Clarity	Steps are clearly sequenced 1-5 with an explicit validation checkpoint ("Confirm the breakdown with the user before executing"); for a simple single-purpose skill this satisfies the 3-anchor.	3 / 3
Progressive Disclosure	A simple under-50-line skill with well-organized sections (intro, Steps, Anti-pattern) and no need for external references, which the rubric permits to score 3 on progressive disclosure.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 clearly answers both what and when with explicit triggers, but its single-action framing and limited trigger-term coverage keep specificity and trigger quality at the mid level. Distinctiveness is reasonable but not fully separated from broader planning skills.

Suggestions

Add a second concrete action (e.g., "Estimate effort and surface dependencies") to lift specificity from one action to multiple distinct actions.

Broaden trigger terms with natural user phrasings such as "break this down", "where do I start", or "too big to tackle at once" for better trigger coverage.

Sharpen the trigger to distinguish it from generic planning skills, e.g. scope it to ambiguous multi-step requests rather than any large goal.

Dimension	Reasoning	Score
Specificity	Names one main action ("Break it into concrete, ordered sub-tasks") with modifiers, but does not list multiple distinct concrete actions as the 3-anchor requires; it is more than the vague 1-anchor though.	2 / 3
Completeness	Explicitly states what ("Break it into concrete, ordered sub-tasks") and when ("Use this skill when a user presents a large, vague goal" / "Apply whenever the request is larger than a single focused action"), satisfying the 3-anchor for both.	3 / 3
Trigger Term Quality	Has natural phrasings ("large, vague goal", "larger than a single focused action") a user might say, but coverage is thin with no term variations, matching the 2-anchor rather than the broad 3-anchor.	2 / 3
Distinctiveness Conflict Risk	The decomposition niche is fairly distinct, but the "large goal / planning" trigger could overlap with general planning or scaffolding skills, matching the 2-anchor rather than a clearly non-conflicting 3.	2 / 3
	Total	9 / 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: aiming-lab/MetaClaw
Path: memory_data/skills/task-decomposition/SKILL.md
Commit: 922caf3

Reviewed: 9 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.