implement-issue
Use when given a GitHub issue number and base branch to implement end-to-end
72
59%
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
40%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 has a 'Use when' clause which is good, but it critically lacks specificity about what the skill actually does. 'Implement end-to-end' is extremely vague and could mean anything from reading an issue and writing code to creating PRs and running tests. The trigger terms are somewhat useful but incomplete.
Suggestions
Replace 'implement end-to-end' with specific concrete actions, e.g., 'reads the GitHub issue, creates a feature branch, implements the required changes, writes tests, and opens a pull request'.
Add more natural trigger term variations such as 'fix issue', 'implement feature', 'GH issue', 'pull request', 'PR', or 'resolve issue'.
Expand the 'Use when' clause to cover more trigger scenarios, e.g., 'Use when the user wants to implement a GitHub issue, fix a bug from an issue, or create a PR for a specific issue number'.
| 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 'end-to-end' implementation entails (e.g., reading issues, creating branches, writing code, opening PRs). | 1 / 3 |
Completeness | It has a 'Use when' clause specifying the trigger condition (given a GitHub issue number and base branch), but the 'what does this do' part is extremely vague — 'implement end-to-end' doesn't explain what the skill actually does. | 2 / 3 |
Trigger Term Quality | It includes 'GitHub issue number' and 'base branch' which are natural terms a user might use, but it's missing common variations like 'issue', 'PR', 'pull request', 'implement feature', 'fix bug', or 'GH issue'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'GitHub issue number' and 'base branch' provides some specificity, but 'implement end-to-end' is so vague it could overlap with many coding/development skills. It's unclear how this differs from other GitHub or coding workflow skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
79%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 invocation commands and a comprehensive overview of the orchestration pipeline. Its main weakness is the lack of explicit error recovery guidance—when a stage fails, there's no feedback loop or troubleshooting steps described. The progressive disclosure is adequate but could better signal how to navigate supporting files.
Suggestions
Add error recovery guidance: what to do when a stage fails (e.g., check stage logs, re-run from failed stage, common failure patterns)
Add a brief troubleshooting section or link to one, covering common exit code 1/2 scenarios and how to resolve them
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose—invocation commands, stage table, exit codes, agent selection—without explaining what GitHub issues are or how shell scripts work. No unnecessary padding. | 3 / 3 |
Actionability | Provides fully executable bash commands for invocation and monitoring, concrete jq queries for status checking, and specific file paths for schemas and logs. The invocation section is copy-paste ready with clear argument substitution. | 3 / 3 |
Workflow Clarity | The stages table clearly sequences the multi-step process and the exit codes provide error categorization. However, there are no explicit validation checkpoints or feedback loops described—if a stage fails, there's no guidance on how to diagnose, fix, or retry. For a complex orchestration workflow, this is a gap. | 2 / 3 |
Progressive Disclosure | References to schemas in `.claude/scripts/schemas/` and the orchestrator script are mentioned but not deeply linked. The stages table is inline which is appropriate, but the agent descriptions could reference separate docs. Without bundle files to verify, the references to external scripts and schemas are present but minimally signaled. | 2 / 3 |
Total | 10 / 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
0d67646
- 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.