implement-issue
Triage, plan, and implement a fix or feature for a GitHub issue end-to-end
67
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
32%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 provides a reasonable high-level overview of the skill's purpose but lacks the explicit trigger guidance required for Claude to reliably select it from a large skill library. It names the domain and general workflow but misses concrete sub-actions and natural user language variations.
Suggestions
Add a 'Use when...' clause with explicit triggers like 'Use when the user references a GitHub issue URL, asks to fix a bug from an issue, or wants to implement a feature from a ticket'
Include natural trigger terms users would say: 'bug', 'issue', 'feature request', 'ticket', 'GitHub #123', 'issue number'
Expand specific actions: 'analyze issue requirements, create feature branches, write implementation code, submit pull requests'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (GitHub issues) and lists actions (triage, plan, implement), but 'fix or feature' and 'end-to-end' are somewhat vague without specifying concrete sub-actions like 'create branches', 'write code', 'submit PRs'. | 2 / 3 |
Completeness | Describes what it does (triage, plan, implement fixes/features) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'GitHub issue' which users would naturally say, but misses common variations like 'issue', 'bug', 'feature request', 'ticket', or 'PR'. The terms 'triage' and 'end-to-end' are more technical/process-oriented than user-facing. | 2 / 3 |
Distinctiveness Conflict Risk | Specifies 'GitHub issue' which provides some distinction, but 'fix or feature' and 'implement' could overlap with general coding skills or other development workflow skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%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, highly actionable skill for end-to-end issue implementation. Its strengths are clear workflow sequencing with explicit validation checkpoints and concrete commands throughout. The main weakness is moderate verbosity—some explanatory text could be trimmed without losing clarity, and the document is fairly long for inline consumption.
Suggestions
Trim explanatory sentences like 'This step prevents wasted effort on the wrong solution' and 'This is valuable when you cannot fully predict...' that explain rationale Claude doesn't need.
Consider extracting the category-to-label mapping table and verification checklist to separate reference files to reduce the main skill's length.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some verbose explanations that could be tightened. Phrases like 'This step prevents wasted effort on the wrong solution' and detailed explanations of what each step accomplishes add tokens without adding value for Claude. | 2 / 3 |
Actionability | Provides concrete, executable commands throughout (gh issue view, make format, pytest commands), specific branch naming conventions, exact verification steps, and copy-paste ready code blocks. The guidance is specific and actionable at every step. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (8 numbered steps with substeps), explicit validation checkpoints (7a-7c verification order), feedback loops (stop and fix before proceeding), and a regression proof step for black-box scenarios. The 'Stop with an error if cwd cannot be set' is a good example of explicit error handling. | 3 / 3 |
Progressive Disclosure | References external files appropriately (@CLAUDE.md, @.claude/rules/worktree.md, /worktree-issue skill) but the main content is quite long and monolithic. Some sections like the detailed verification steps or the category table could potentially be split out, though the inline approach is reasonable for a workflow document. | 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 | |
- 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.