to-issues
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
91
92%
Does it follow best practices?
Impact
83%
1.48xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does, when to use it, and uses natural trigger terms. It specifies concrete inputs (plan, spec, PRD), outputs (issues on the project issue tracker), methodology (tracer-bullet vertical slices), and includes an explicit 'Use when' clause with multiple trigger scenarios. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Break a plan, spec, or PRD into independently-grabbable issues', 'using tracer-bullet vertical slices'. It names the input types (plan, spec, PRD) and the output (issues on the project issue tracker) with a specific methodology. | 3 / 3 |
Completeness | Clearly answers both 'what' (break plans/specs/PRDs into independently-grabbable issues using tracer-bullet vertical slices) and 'when' (explicit 'Use when' clause covering converting plans to issues, creating implementation tickets, or breaking down work into issues). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'plan', 'spec', 'PRD', 'issues', 'implementation tickets', 'break down work', 'convert a plan into issues', 'issue tracker'. These cover common variations of how users would phrase this request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: converting planning documents into issue tracker tickets using vertical slices. The combination of input types (plan/spec/PRD), output (issues), and methodology (tracer-bullet slices) makes it unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
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 issue tracker tickets. Its strongest aspects are the clear sequencing with an explicit user-approval gate before publishing, and the lean writing style that respects Claude's intelligence. The main weakness is that the actual mechanism for publishing issues to the tracker is left abstract rather than specifying concrete tool calls or commands.
Suggestions
Specify the concrete tool or command used to publish issues to the issue tracker (e.g., a specific MCP tool call, GitHub CLI command, or API endpoint) to improve actionability.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It assumes Claude knows what vertical slices, tracer bullets, and issue trackers are without over-explaining. Every section serves a clear purpose with no padding or redundant explanation. | 3 / 3 |
Actionability | The guidance is concrete in terms of process steps, issue template, and quiz questions, but lacks executable commands or specific tool invocations for interacting with the issue tracker. The instruction to 'publish a new issue to the issue tracker' is somewhat abstract without specifying the exact tool/API call to use. | 2 / 3 |
Workflow Clarity | The 5-step process is clearly sequenced with an explicit human-in-the-loop validation checkpoint (step 4: quiz the user and iterate until approved) before the destructive/irreversible action of publishing issues. Dependency ordering for publishing is explicitly specified, and the feedback loop (iterate until approval) is well-defined. | 3 / 3 |
Progressive Disclosure | For a skill with no bundle files, the content is well-organized with clear sections, an embedded issue template, and vertical-slice rules in a dedicated block. The content length is appropriate for a single file and doesn't need to be split further. The reference to `/setup-matt-pocock-skills` for prerequisite context is a clean one-level-deep pointer. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%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
- coder/agent-tty
- Commit
a05d4e5
- Reviewed
Table of Contents
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.