implement-issue
Use when given a GitHub issue number and base branch to implement end-to-end
69
55%
Does it follow best practices?
Impact
93%
3.20xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/implement-issue/SKILL.mdQuality
Discovery
22%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 description is critically incomplete — it specifies a trigger condition (GitHub issue + base branch) but fails to describe what the skill actually does beyond the vague phrase 'implement end-to-end.' Without concrete actions or outputs, Claude cannot make an informed decision about when to select this skill over others, and users cannot understand its purpose.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Reads a GitHub issue, creates a feature branch, implements the required code changes, writes tests, and opens a pull request.'
Expand trigger terms to include natural variations like 'fix issue', 'implement feature', 'work on issue #', 'PR', 'pull request', 'feature branch'.
Clarify the 'what' portion by describing the end-to-end workflow and expected outputs (e.g., code changes, commits, pull requests).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'implement end-to-end' but never specifies what concrete actions are performed. There are no specific capabilities listed — no mention of what is being implemented, what steps are taken, or what outputs are produced. | 1 / 3 |
Completeness | It provides a partial 'when' clause ('Use when given a GitHub issue number and base branch') but the 'what' is extremely vague — 'implement end-to-end' does not explain what the skill actually does. The what is essentially missing. | 1 / 3 |
Trigger Term Quality | It includes 'GitHub issue number' and 'base branch' which are natural terms a user might use, but it lacks common variations like 'issue', 'PR', 'pull request', 'fix issue', 'implement feature', or 'branch' that users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'GitHub issue number and base branch' provides some specificity that narrows the domain, but 'implement end-to-end' is so vague it could overlap with many development-related skills like code generation, PR creation, or project scaffolding. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
87%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 provides clear executable commands and comprehensive reference tables for an orchestration workflow. Its main weakness is the lack of explicit error recovery guidance—when a stage fails (exit code 1 or 2), there's no described feedback loop for diagnosing and fixing the issue. The skill excels at being a quick-reference guide but could benefit from a brief troubleshooting or error handling section.
Suggestions
Add a brief error recovery section describing what to do when the orchestrator exits with code 1 or 2 (e.g., check stage logs, fix issue, re-run from failed stage)
Include guidance on how to interpret status.json errors and resume or retry failed stages
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose—invocation commands, monitoring, stages, exit codes, agent selection—without explaining concepts Claude already knows. No padding or unnecessary context. | 3 / 3 |
Actionability | Provides fully executable bash commands for invocation and monitoring, concrete argument specifications, and clear tables for stages, exit codes, and agent selection. Copy-paste ready commands throughout. | 3 / 3 |
Workflow Clarity | The stages table provides a clear sequence of the pipeline, but there are no explicit validation checkpoints or error recovery feedback loops described. The skill delegates to an orchestrator script but doesn't describe what to do if a stage fails, how to retry, or how to interpret status.json for error recovery. | 2 / 3 |
Progressive Disclosure | Content is well-structured with clear sections and appropriate references to external resources (schemas in `.claude/scripts/schemas/`, logs directory, orchestrator script). Information is organized for quick scanning with tables and headers, and references are one level deep. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- aaddrick/claude-desktop-debian
- Commit
814cd52
- 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.