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.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Reads a GitHub issue, creates a feature branch, implements code changes, writes tests, and opens a pull request.'
Expand the 'Use when' clause with natural trigger terms like 'implement issue', 'fix bug', 'create PR', 'pull request from issue', 'work on GitHub issue'.
Clarify the end-to-end workflow so it's distinguishable from other coding or GitHub-related skills — specify whether it handles code generation, testing, branch management, PR creation, etc.
| 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 partially addresses 'when' (given a GitHub issue number and base branch) but completely fails to answer 'what does this do' — 'implement end-to-end' is too vague to constitute a meaningful description of capabilities. | 1 / 3 |
Trigger Term Quality | It includes 'GitHub issue number' and 'base branch' which are natural terms a user might use, but it lacks broader variations or related keywords like 'fix issue', 'PR', 'pull request', 'implement feature', 'code changes', etc. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'GitHub issue number and base branch' provides some specificity that narrows the scope, but 'implement end-to-end' is so vague it could overlap with many development-related skills. | 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 serves as an effective reference for launching and monitoring the implement-issue orchestrator. Its strengths are excellent actionability with executable commands and a clean progressive disclosure structure. The main weakness is the lack of error recovery guidance — when stages fail or max iterations are exceeded, there's no feedback loop or troubleshooting steps documented.
Suggestions
Add a brief error recovery section explaining what to do when the orchestrator exits with codes 1 or 2 (e.g., check stage logs, fix and re-run from a specific stage).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what GitHub issues are or how shell scripts work. Every section provides specific, actionable reference information (exit codes, stages, agents) without padding. | 3 / 3 |
Actionability | Provides exact executable commands for invocation, monitoring, and status checking. The bash commands are copy-paste ready with clear argument placeholders. The stages table and agent selection table give concrete, specific guidance. | 3 / 3 |
Workflow Clarity | The stages table clearly sequences the multi-step process, and monitoring commands are provided. However, there are no explicit validation checkpoints or error recovery feedback loops — if a stage fails (exit code 1 or 2), there's no guidance on what to do next or how to retry/fix. | 2 / 3 |
Progressive Disclosure | The skill serves as a clear overview, referencing schemas in `.claude/scripts/schemas/`, logs in `logs/implement-issue/`, and the orchestrator script itself. Content is well-organized into logical sections (invocation, monitoring, stages, logging, exit codes) without being monolithic or deeply nested. | 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
76a5a21
- 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.