refactor(mention): move behavioral instructions from prompt to skill#235
Merged
Conversation
…g-in-ci skill The mention prompt duplicated guidance already present in the running-in-ci skill (reply mechanics, multi-way conversation rules, context reading). Move general behavioral instructions to the shared skill where all CI runs benefit, and slim each prompt branch to contain only event-specific context. Skill additions: review inline comment fetching by review ID, review concerns acknowledgment, self-conversation guard, triage skill loading gate. Prompt removals: exact gh api reply commands, detailed context-reading lists, multi-way conversation rules, self-conversation guard, triage loading — all now in the skill. Drops github.repository format arg from pull_request_review_comment branches (4→3 args). Co-Authored-By: Claude <noreply@anthropic.com>
Ari4ka
approved these changes
Apr 11, 2026
tend-agent
added a commit
that referenced
this pull request
Apr 11, 2026
Syncs the checked-in workflow file with the in-repo generator. Pulls in changes from #225 (pull_request_review_comment dedup), #233 (drop bot-author filter), #228 (--paginate on gh api), and #235 (move behavioral instructions from prompt to skill). Generated with the local `generator/` source tree rather than `uvx tend@latest init`, because PyPI 0.0.11 lags behind main for these changes — running `uvx tend@latest init` against the current tree would *add* `timeout-minutes: 60` back and drop the mention generator updates.
This was referenced Apr 11, 2026
tend-agent
pushed a commit
that referenced
this pull request
Apr 13, 2026
When `generator/pyproject.toml` exists (i.e. on the tend repo itself), Step 5 of the nightly skill now regenerates workflows via the in-tree generator instead of `uvx tend@latest`. Adopter repos without `generator/` fall through to the existing `uvx tend@latest` path unchanged. Motivation: PR #264 (from run 24330194038) ran `uvx tend@latest init` with PyPI's `tend` at 0.0.11 (released 2026-04-10). `main` has 10 generator commits landed since — #223 (drop hardcoded job timeouts), #225 (dedup review events), #227 (workflow_extra), #228 (paginate), #231 (inline-reply guidance), #233 (drop bot-author filter on issue_comment), #235 (prompt → skill), #254 (notifications freshness gate + bot-closed-PR drop), etc. Regenerating against the stale wheel reverted each of these. Maintainer flagged the PR as regressions; diagnosis confirmed the PyPI lag. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The mention prompt duplicated guidance already in the
running-in-ciskill (reply mechanics, multi-way conversation rules, context reading instructions). This moves general behavioral instructions into the shared skill and slims each prompt branch to event-specific context only.Skill additions (
running-in-ci/SKILL.md): review inline comment fetching by review ID, review concerns acknowledgment, self-conversation guard, triage skill loading gate.Prompt removals (
workflows.py): exactgh apireply commands, detailed context-reading lists (description, diff, recent comments, CI status), multi-way conversation rules, self-conversation guard, triage loading instruction. Dropsgithub.repositoryformat arg frompull_request_review_commentbranches (4→3 args).Each prompt branch now follows a consistent pattern: identify event → pass dynamic values (URLs, IDs) → state core action. Everything about how to carry out the action (reply mechanics, when to respond, how to read context) lives in the skill.