speckit-taskstoissues

Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/speckit-taskstoissues/SKILL.md

Quality

Content

50%

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

The body provides a clear sequenced workflow with concrete commands and explicit safety checkpoints, but it is held back by verbatim duplication of the hook protocol and an underspecified core issue-creation step. Adding error-recovery for the batch operation and extracting the shared hook rules would meaningfully raise quality.

Suggestions

Deduplicate the Pre-Execution and Post-Execution hook sections — extract the shared condition/enabled/dots-to-hyphens rules into one block referenced by both to cut ~25 redundant lines.

Specify the issue-creation action concretely: which GitHub MCP tool to call, how to derive issue title/body from each task, and how to represent task dependencies (the 'dependency-ordered' output is never defined).

Add an error-recovery feedback loop for the batch issue-creation step (e.g. what to do if the remote is not GitHub, the prerequisites script fails, or an issue fails to create).

Dimension	Reasoning	Score
Conciseness	The body is accurate and project-specific, but the Pre-Execution and Post-Execution hook sections duplicate the condition/enabled/dots-to-hyphens rules almost verbatim (~25 redundant lines) that could be tightened into a single shared block.	2 / 3
Actionability	Concrete commands are present (the prerequisites script, 'git config --get remote.origin.url') plus hook output templates, but the core action ('use the GitHub MCP server to create a new issue') is underspecified — no MCP tool name, no issue title/body, and 'dependency-ordered' is never defined.	2 / 3
Workflow Clarity	A clear numbered sequence with explicit CAUTION validation checkpoints exists, but this batch issue-creation operation has no error-recovery feedback loop for script failure, a non-GitHub remote, or partial creation failures.	2 / 3
Progressive Disclosure	The body is well-sectioned and self-contained with no nested references, but the duplicated hook protocol is substantial inline content that should live in a single one-level-deep shared reference rather than being repeated.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 states what the skill does but omits any explicit trigger/usage guidance, leaving the 'when' unanswered and trigger-term coverage partial. It is specific to a narrow niche yet lacks the natural-language triggers that would make it discoverable and cleanly distinguishable.

Suggestions

Add a 'Use when...' clause with explicit triggers, e.g. 'Use when converting spec-kit tasks into GitHub issues, or when the user asks to create issues from a task list.'

Include natural-language trigger variations users would actually say (e.g. 'tasks', 'task list', 'create issues', 'GitHub issues', 'dependencies').

Clarify how dependencies are represented in the issues so the 'dependency-ordered' promise is concrete rather than aspirational.

Dimension	Reasoning	Score
Specificity	It names the domain ('GitHub issues') and a concrete action ('Convert existing tasks into... dependency-ordered GitHub issues'), but offers a single primary action rather than the multiple distinct concrete actions the top anchor requires.	2 / 3
Completeness	The 'what' is clear, but there is no explicit 'when should Claude use it' trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Relevant natural terms like 'tasks' and 'GitHub issues' appear, but there is no 'Use when...' clause and common variations users might say are missing, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	It occupies a narrow niche (spec-kit tasks to GitHub issues) with low conflict risk, but the top anchor requires distinct triggers and none are present.	2 / 3
	Total	8 / 12 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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: unoplatform/uno
Path: .claude/skills/speckit-taskstoissues/SKILL.md
Commit: 5927220

Reviewed: about 15 hours 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.