diffity-resolve-tree
Read open comments from the tree browser and resolve them by making code fixes
Install
npx skills add https://github.com/nilbuild/diffity --skill diffity-resolve-treeSKILL.md
Diffity Resolve Tree Skill
You are reading open comments left on repository files via the diffity tree browser and resolving them by making the requested code changes.
Arguments
thread-id(optional): Resolve a specific thread by ID instead of all open threads. Example:/diffity-resolve-tree abc123
CLI Reference
{{binary}} agent list [--status open|resolved|dismissed] [--json]
{{binary}} agent comment --file <path> --line <n> [--end-line <n>] --body "<text>"
{{binary}} agent resolve <id> [--summary "<text>"]
{{binary}} agent dismiss <id> [--reason "<text>"]
{{binary}} agent reply <id> --body "<text>"
--file,--line,--bodyare required forcomment--end-linedefaults to--line(single-line comment)<id>accepts full UUID or 8-char prefix
Prerequisites
- Check that
{{binary}}is available: runwhich {{binary}}. If not found, {{install_hint}}. - Check that a tree session exists: run
{{binary}} agent list. If this fails with "No active review session", tell the user to start diffity tree first (e.g.{{binary}} tree).
Instructions
- List open comment threads with full details:
If a{{binary}} agent list --status open --jsonthread-idargument was provided, filter to just that thread. The JSON output includes the full comment body, file path, line numbers, and side for each thread. - If there are no open threads, tell the user there's nothing to resolve.
- For each open thread:
a. Skip general comments (filePath
__general__) — these are summaries, not actionable code changes. b. Skip threads where the last comment is an agent reply that asks the user a question and the user hasn't responded yet — the agent is waiting for user input. c.[question]comments (from the user) — read the question, examine the relevant code, and reply with an answer:
Then resolve the thread with a summary of your answer. d. Comments phrased as questions without an explicit{{binary}} agent reply <thread-id> --body "Your answer here"[question]tag (e.g. "should we add X?" or "can we rename this?") are suggestions — treat them as actionable requests and make the change. e. Read the comment body from the JSON output and understand what change is requested. The comment is anchored to a specific file and line range — read the full file to understand context:- If the comment suggests a code change, refactor, or improvement, make the change.
- If the comment suggests adding documentation, add or update the relevant docs.
- If the comment is genuinely unclear, reply asking for clarification:
{{binary}} agent reply <thread-id> --body "Could you clarify what change you'd like here?"
f. After making the change, resolve the thread with a summary:
{{binary}} agent resolve <thread-id> --summary "Fixed: <brief description of what was changed>" - After resolving all applicable threads, run
{{binary}} agent listto confirm status. - Tell the user to check the browser — resolved status will appear within 2 seconds via polling.
Related skills
improve-codebase-architecturemattpocock1MScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.codebase-designmattpocock691KShared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.web-design-guidelinesvercel-labs676KReview UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".code-reviewmattpocock631KReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".