taskify

Task decomposition expert for breaking technical specifications into atomic, implementable tasks with dependencies and priorities. Use when converting specs into actionable task lists for development teams.

Quality

70%

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 ./plugins/dev-skills/skills/taskify/SKILL.md

Quality

Content

57%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 rich with concrete, reusable task-decomposition templates and a clear process sequence, but it is verbose (restating basics Claude knows, with a redundant execution section), monolithic with no reference files, and lacks a validation checkpoint before the batch GitHub-issue creation step. These keep conciseness, progressive disclosure, and workflow clarity at mid-range.

Suggestions

Add an explicit review/dry-run validation checkpoint in the --github workflow before running 'gh issue create' (e.g., 'Print the planned issues and confirm with the user before creating'), which would lift workflow_clarity above the batch-operation cap.

Trim or move the 'Task Decomposition Principles' and 'Task Categorization' tables — Claude already knows these — and consolidate the redundant 'Task Execution' section with the earlier output-format guidance to improve conciseness.

Move the large GitHub-issue and structured-task-file templates into a references/ file (e.g., references/templates.md) and link to them one level deep from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly concrete template material, but noticeably padded: the 'Task Decomposition Principles' and 'Task Categorization' (by type/priority/size/component) sections restate basic project-management concepts Claude already knows, and the 'Task Execution' section duplicates earlier content. Not a 2 because the bulk is actionable template content rather than pure fluff; not a 4 because several sections could be trimmed.	3 / 5
Actionability	Provides copy-paste-ready GitHub issue and structured-task-file templates with concrete labels, file-path placeholders, acceptance-criteria checkboxes, and three named task patterns. As an instruction-only skill the absence of executable code is acceptable; held below 5 by heavy use of placeholders ([entity], ServiceName) and lack of fully worked examples.	4 / 5
Workflow Clarity	A clear numbered sequence exists (Read spec → Identify phases → Create tasks → Map dependencies → Estimate → Prioritize → Add notes → Generate output), but the --github path performs a batch operation (creating many issues via 'gh issue create') with no review/dry-run validation checkpoint before creation. Per the batch-operation cap, workflow clarity cannot exceed 3.	3 / 5
Progressive Disclosure	No bundle files exist and all content (~340 lines, including large reusable templates and categorization tables) is inlined in SKILL.md with no one-level-deep references. Section headers give decent structure, but reference material that would benefit from being split into separate files is inline, matching the 'some structure, content that should be separate is inline' anchor.	3 / 5
	Total	13 / 20 Passed

Description

83%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 description: third-person voice, concrete actions, and an explicit 'Use when' trigger clause that answers both what and when. The main gap is trigger-term breadth (missing synonyms like 'tickets'/'issues'/'backlog') and only modest distinctiveness from general planning skills.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions — 'breaking technical specifications into atomic, implementable tasks with dependencies and priorities' — listing several specific facets (atomic tasks, dependencies, priorities). Not a 5 because it is essentially one decomposition action described with attributes rather than multiple distinct concrete actions.	4 / 5
Completeness	Explicitly answers both what ('Task decomposition expert for breaking technical specifications into atomic, implementable tasks with dependencies and priorities') and when ('Use when converting specs into actionable task lists for development teams') with concrete trigger phrasing. Not a 4 because the 'when' clause is explicit and specific rather than vague.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say — 'converting specs into actionable task lists', 'specifications', 'task lists', 'development teams'. Good coverage but missing common synonyms users might say such as 'tickets', 'issues', 'backlog', or 'Jira', so not a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — spec-to-task decomposition — with distinct triggers, but overlaps slightly with general project-planning or spec-analysis skills, so minor overlap risk keeps it just below 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: rikdc/ai-skills
Path: plugins/dev-skills/skills/taskify/SKILL.md
Commit: cd15778

Reviewed: 2 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.