opencode-repair
Fix OpenCode issues - blank sessions, missing worktrees, duplicate project rows, DB repair
86
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
67%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 effectively lists specific technical issues it addresses and is clearly scoped to OpenCode troubleshooting, making it distinctive. However, it lacks explicit trigger guidance ('Use when...') and could benefit from more natural user-facing keywords that describe symptoms users would report rather than just technical problem names.
Suggestions
Add a 'Use when...' clause with trigger phrases like 'OpenCode not working', 'session problems', 'database errors', or 'project list issues'
Include natural symptom-based keywords users might say such as 'blank screen', 'missing projects', 'corrupted database', or 'OpenCode broken'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'blank sessions, missing worktrees, duplicate project rows, DB repair' - these are distinct, actionable problems the skill addresses. | 3 / 3 |
Completeness | Clearly answers 'what' (fix specific OpenCode issues), but lacks an explicit 'Use when...' clause or trigger guidance. The when is only implied through the problem descriptions. | 2 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'OpenCode', 'sessions', 'worktrees', 'DB repair', but missing natural user phrases like 'not working', 'broken', 'error', or variations users might actually say when experiencing these issues. | 2 / 3 |
Distinctiveness Conflict Risk | Highly specific to 'OpenCode' tool with distinct technical terms like 'worktrees', 'duplicate project rows' - very unlikely to conflict with other skills due to the specific product and issue types named. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality troubleshooting skill with excellent diagnostic flow and actionable fixes. The content efficiently covers multiple root causes with executable commands and proper verification steps. Minor improvement could come from better progressive disclosure if this skill grows or relates to other OpenCode documentation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient with no unnecessary explanations. Every section serves a diagnostic or fix purpose, and Claude's competence with SQL, git, and Python is assumed throughout. | 3 / 3 |
Actionability | Provides fully executable shell commands, SQL queries, and Python scripts that are copy-paste ready. Specific file paths and command structures are given rather than abstract descriptions. | 3 / 3 |
Workflow Clarity | Clear diagnostic sequence (check duplicates → verify paths → check sessions → check global.dat) followed by targeted fixes. Includes verification steps after fixes and explicit 'After any fix' instruction for restart. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections for diagnosis and multiple fix scenarios, but it's a moderately long single file. The Notes section at the end could potentially be split out, and there are no references to related documentation. | 2 / 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.
- 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.