spec-loop-plan-work-breakdown

Create or revise file-based Spec Loop work breakdown artifacts for task-file work, including splitting a requested single item into subtasks or multiple task files / backlog items when planning or design shows that split is needed.

Quality

74%

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/spec-loop-plan-work-breakdown/SKILL.md

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.

The body is a well-structured, actionable process skill with explicit validation and feedback loops, scoring highly on workflow clarity. Its weak point is conciseness: core rules are repeated across sections and again in the final checklist, and a concrete example breakdown artifact would improve actionability.

Suggestions

Reduce cross-section repetition by stating the standalone/releasable rule, the Fast-payoff preference, and the detail-level rule once and having the Final self-check reference them rather than re-stating each in full.

Add a short worked example of a split breakdown (e.g., a sample task file with two subtasks showing title, Scope, Motivation, and a three-digit prefix) to make the construction guidance copy-paste concrete.

Consider moving the long enumerated 'Forbidden by default' / 'Allowed when they stand alone' lists into a single reference section or file so the main flow stays lean.

Dimension	Reasoning	Score
Conciseness	The content is genuine domain rule-setting Claude would not already know (not padding with general knowledge), but the standalone/releasable rule, the Fast-payoff preference, and the 'only title, Scope, Motivation, Constraints' detail-level rule are each restated across multiple sections and again in the Final self-check, so it could be tightened noticeably.	3 / 5
Actionability	Guidance is concrete and specific for an instruction-only skill — e.g., 'name each (sub)task by its delivered outcome, not by a technical layer', 'number them with readable three-digit prefixes local to the containing folder', and exact section lists to include — with the main gap being no worked example of an actual breakdown artifact.	4 / 5
Workflow Clarity	A clear logical sequence runs from the Scope/Motivation gate through construction to an explicit 'Final self-check' validation checklist, with feedback loops for error recovery (pause on a blocking unknown → clarify/ADR → resume; compact an oversized file → resume), satisfying the validation, feedback-loop, and checklist criteria.	5 / 5
Progressive Disclosure	No bundle files exist and the ~270-line body is monolithic, but it is well-sectioned with clear headers and its references to sibling skills (planning-form-selection-guidance.md, spec-loop-plan-task/SKILL.md, spec-loop-clarify-task/SKILL.md, spec-loop-compact-task-file/SKILL.md) are clearly signaled and one level deep, so structure and navigation are good with only minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

75%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.

The description is specific, third-person, and covers both what the skill does and a trigger condition, with good natural keyword coverage and a clear niche. Its main weakness is the absence of a standalone, explicit 'Use when...' trigger clause, leaving the 'when' embedded and slightly implicit.

Suggestions

Add an explicit 'Use when...' sentence with concrete trigger phrases (e.g., 'Use when splitting a requested task into subtasks or multiple task files/backlog items, or revising an existing file-based work breakdown') to lift completeness and trigger clarity.

Include common synonyms a user might say (e.g., 'break down work', 'decompose task', 'split into subtasks') to broaden natural trigger coverage beyond the current Spec Loop jargon.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Create or revise file-based Spec Loop work breakdown artifacts', 'splitting a requested single item into subtasks or multiple task files / backlog items' — naming the domain with actionable verbs; not quite a comprehensive action list, so it sits at 4 rather than 5.	4 / 5
Completeness	It states both the 'what' (create/revise/split work breakdown artifacts) and a 'when' ('when planning or design shows that split is needed'), but the trigger is embedded as a subordinate clause rather than a clean explicit 'Use when...' phrase, so it falls at 4 instead of 5.	4 / 5
Trigger Term Quality	Natural planning terms like 'work breakdown', 'subtasks', 'task files', 'backlog items', and 'split' are present and would be said by a user in this workflow, though 'Spec Loop'/'task-file' jargon and missing common synonyms keep it just below comprehensive (5).	4 / 5
Distinctiveness Conflict Risk	The niche (file-based work breakdown / splitting) is clearly scoped to the Spec Loop task-file path, but it is an acknowledged companion to the closely related 'spec-loop-plan-task', creating minor overlap risk with that sibling skill rather than minimal conflict (5).	4 / 5
	Total	16 / 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
relative_links	Relative link issues: 6 suspicious	Warning

	Total	15 / 16 Passed

Repository: dpolivaev/spec-loop
Path: skills/spec-loop-plan-work-breakdown/SKILL.md
Commit: 7033338

Reviewed: 6 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.