com um clique
feedback
// Manage feedback and bug reports for a project using a local SQLite database. Use when the user asks to log, list, view, resolve, or work through feedback items or bugs.
// Manage feedback and bug reports for a project using a local SQLite database. Use when the user asks to log, list, view, resolve, or work through feedback items or bugs.
Search jackfranklin/references (personal technical reference docs) for files relevant to the current task. Use when you need a reference guide on a library, API, or tool, or when the user invokes /references-search with search keywords as $ARGUMENTS.
Scaffold a new Deno 2 + Hono + Deno KV + Eta + HTMX app with password auth and PWA support. Use when the user wants to create a new personal web app following this stack.
Reviews code changes for hacky patterns, redundant state, parameter sprawl, and leaky abstractions. Use when the user asks to "review code quality", "check for hacky patterns", "quality review", or wants a quality-focused code review.
Reviews code changes to identify opportunities for reusing existing utilities and helpers. Use when the user asks to "review for reuse", "check for duplicate code", "find existing utilities", or wants a reuse-focused code review.
Reviews code changes for efficiency issues, unnecessary work, missed concurrency, and memory leaks. Use when the user asks to "review for efficiency", "check for performance issues", "find memory leaks", or wants an efficiency-focused code review.
Scaffold a new Vite + LitElement + IDB PWA app hosted on Netlify with a private GitHub repo. Use when the user wants to create a new personal web app following this stack.
| name | feedback |
| description | Manage feedback and bug reports for a project using a local SQLite database. Use when the user asks to log, list, view, resolve, or work through feedback items or bugs. |
| user-invocable | false |
You have access to a feedback tracking CLI at ~/dotfiles/claude/skills/feedback/run.
Run it with:
~/dotfiles/claude/skills/feedback/run <command>
feedback add --project <name> --title "..." [--detail "..."] [--priority low|medium|high] [--status open|in-progress|blocked|done] [--category "..."]
feedback list [--project <name>] [--all]
feedback show <id>
feedback done <id>
feedback edit <id> [--title "..."] [--detail "..."] [--priority low|medium|high] [--status open|in-progress|blocked|done] [--category "..."]
feedback projects
Always list before show. The list command returns only titles and IDs — it is token-efficient. Only call show <id> when you need the full detail of a specific item.
Default is open items only. list excludes done items unless --all is passed. This is correct behaviour — do not add --all unless the user specifically asks to see completed items.
Always pass --project. Infer the project name from the current working directory or from context the user has provided. If ambiguous, ask the user before running any command.
Priorities: high for bugs or blockers, medium for improvements (default), low for nice-to-haves.
Statuses: open (default), in-progress, blocked, done. Use done <id> or edit <id> --status done to close items. The list command excludes done items unless --all is passed.
Categories: Free-text tag (e.g. bug, ux, performance, gameplay). Shown in list output as {category}.
Logging new feedback from a conversation:
list --project <name> to retrieve open items.show <id> on the overlapping item, then present your findings to the user and ask: "This looks similar to # — do you want to update that existing item or log a new one?"add once the user has confirmed there is no overlap, or has explicitly asked for a new item.Working through feedback:
list --project <name> to get open items.show <id> only for items being actively discussed.done <id>.User asks "what's left?":
list --project <name> and present the output directly.