to-issues

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.

0.95x

Quality

71%

Does it follow best practices?

Impact

80%

0.95x

Average score across 1 eval scenario

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/engineering/to-issues/SKILL.md

Quality

Content

85%

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

This is a well-structured, concise skill that clearly defines a multi-step workflow for breaking plans into vertical-slice issues. Its strongest aspects are the clear sequencing with an explicit user-approval feedback loop before publishing, and the lean writing style that respects Claude's intelligence. The main weakness is that issue tracker interactions are described abstractly rather than with specific tool calls, though this may be intentional given that the tracker tooling is expected to be configured via the referenced setup command.

Suggestions

Consider adding a brief example of what a good vertical slice breakdown looks like (e.g., 2-3 example slice titles with their dependency relationships) to make the guidance more concrete.

Specify the expected tool or method for interacting with the issue tracker (e.g., GitHub CLI commands, MCP tool calls) to make steps 1 and 5 more actionable.

Dimension	Reasoning	Score
Conciseness	The skill is lean and efficient. It assumes Claude knows what vertical slices, tracer bullets, ADRs, and issue trackers are. Every section serves a purpose with no unnecessary explanation of basic concepts. The issue template is appropriately detailed without being verbose.	3 / 3
Actionability	The skill provides a clear process and a concrete issue template, but lacks executable commands or specific tool invocations for interacting with the issue tracker. Steps like 'fetch it from the issue tracker' and 'publish a new issue' are described abstractly rather than with specific tool calls or commands. The guidance is specific enough to follow but not fully copy-paste ready.	2 / 3
Workflow Clarity	The 5-step process is clearly sequenced with logical ordering. Step 4 provides an explicit feedback loop (quiz the user, iterate until approved) before the destructive action of publishing issues. Step 5 specifies dependency-ordered publishing so blockers get real IDs first. The instruction to not close/modify parent issues is a good safety constraint.	3 / 3
Progressive Disclosure	For a skill with no bundle files, the content is well-organized with clear sections, an embedded template using XML-style tags for scoping, and appropriate inline detail. The reference to `/setup-matt-pocock-skills` for prerequisite context is a clean one-level-deep pointer. The skill is under 100 lines and doesn't need external files.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 communicates a clear and distinctive purpose—decomposing planning documents into issue tracker tickets using a specific methodology. However, it lacks an explicit 'Use when...' clause and could benefit from broader trigger term coverage (e.g., 'tickets', 'stories', 'backlog') and more enumeration of concrete sub-actions.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to break down a plan, spec, PRD, or requirements document into trackable issues or tickets.'

Include common synonym trigger terms users might naturally say, such as 'tickets', 'stories', 'tasks', 'backlog', 'Jira', 'Linear', or 'task breakdown'.

Dimension	Reasoning	Score
Specificity	It names a specific action ('break a plan/spec/PRD into issues') and mentions a methodology ('tracer-bullet vertical slices'), but it only describes one core action rather than listing multiple concrete capabilities like creating, labeling, prioritizing, or assigning issues.	2 / 3
Completeness	It answers 'what does this do' reasonably well but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2.	2 / 3
Trigger Term Quality	Includes some good natural terms like 'plan', 'spec', 'PRD', 'issues', 'issue tracker', and 'vertical slices', but misses common variations users might say such as 'break down', 'task breakdown', 'tickets', 'stories', 'backlog', 'Jira', 'Linear', or 'project planning'.	2 / 3
Distinctiveness Conflict Risk	The combination of breaking down plans/specs/PRDs into issue tracker issues using tracer-bullet vertical slices is quite distinctive and unlikely to conflict with other skills. The methodology reference ('tracer-bullet vertical slices') and the specific input-output framing create a clear niche.	3 / 3
	Total	9 / 12 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: mattpocock/skills
Commit: 6eeb81b

Reviewed: 10 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.