convert-github-issue-to-discussion
Convert GitHub issues to discussions using agent-browser. Use when asked to convert, move, or change an issue to a discussion. Requires agent-browser installed and user to log in via headed browser.
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./config/claude/skills/convert-github-issue-to-discussion/SKILL.mdQuality
Discovery
89%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 is a well-crafted description with clear 'what' and 'when' clauses, good trigger term coverage including natural synonyms like 'convert', 'move', and 'change', and a highly distinctive scope. The only minor weakness is that it describes a single action rather than multiple concrete capabilities, but given the narrow scope of the skill, this is reasonable.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the specific action ('Convert GitHub issues to discussions') and the tool ('agent-browser'), but only describes a single action rather than listing multiple concrete capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (convert GitHub issues to discussions using agent-browser) and 'when' (when asked to convert, move, or change an issue to a discussion), with explicit trigger guidance and even prerequisites. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'convert', 'move', 'change', 'issue', 'discussion', 'GitHub'. These cover the common variations a user would naturally say when requesting this task. | 3 / 3 |
Distinctiveness Conflict Risk | Very specific niche — converting GitHub issues to discussions via agent-browser. Unlikely to conflict with other skills due to the narrow, well-defined scope and specific tooling requirement. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides clear, actionable browser automation instructions with concrete commands and realistic snapshot output examples. Its main weaknesses are the lack of error handling/validation steps for a multi-step browser automation workflow and some content duplication between the detailed workflow and the quick reference section. The step that explicitly says 'you don't need to verify' is a missed opportunity for a validation checkpoint.
Suggestions
Add error handling guidance: what to do if 'Convert to discussion' button is not found (e.g., insufficient permissions, issue already converted, or button located in a dropdown menu).
Remove or repurpose Step 8 — either add actual verification (check URL redirected to /discussions/) or remove the step entirely instead of saying 'you don't need to verify'.
Consolidate the Quick Reference with the main workflow to reduce duplication, or make the Quick Reference a truly minimal cheat sheet without overlapping explanations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but has some redundancy — the full step-by-step workflow and the 'Quick Reference' section largely duplicate each other. Step 8 ('Verify Conversion') says 'you don't need to verify, you are done now' which is a wasted step. Some commentary like 'The --headed flag shows the browser window so the user can log in' is mildly unnecessary. | 2 / 3 |
Actionability | Every step includes concrete, executable bash commands with the exact agent-browser CLI syntax. The snapshot output examples show what to look for (button refs, combobox options), making it copy-paste ready and unambiguous. | 3 / 3 |
Workflow Clarity | The steps are clearly sequenced and numbered, but there are validation gaps: no error handling if the 'Convert to discussion' button isn't found (e.g., permissions issue, already converted), no feedback loop for failed conversions, and Step 8 explicitly skips verification. For a multi-step browser automation workflow, missing validation/error recovery caps this at 2. | 2 / 3 |
Progressive Disclosure | The content is reasonably structured with sections (Workflow, Quick Reference, Category Guidelines, Cleanup), but everything is inline in one file. The Quick Reference duplicates the workflow rather than adding value. The skill is borderline long enough that the category guidelines or quick reference could be separated, but the organization is acceptable for the content volume. | 2 / 3 |
Total | 9 / 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.
- Repository
- freekmurze/dotfiles
- Commit
05d40bb
- 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.