Address Feedback With Replies
Triage, fix, ship, and answer the Slack threads the user pointed at, in one
pass. This is review-latest-feedback aimed at a specific set of threads
instead of the whole sweep. That skill owns the Slack contract: the 👀 / ✅ / 🎫
reactions, the one-sentence reply and its wording, which channels are fair
game, the "leave it alone" rules, and maintainer reactions such as :upvote:. Read it first and
follow it. This file adds only what is specific to working a given thread.
Use the connected Slack integration for every read and write, and confirm which
profile is connected before the first write. Never drive Slack through a browser or
computer use.
1. Read everything first
- Read the parent message and every reply. Open every screenshot, file, video,
transcript, and linked recording; the error text there is often the whole
diagnosis.
- Fetch linked artifacts through their own connector or public URL. If one is
permission-gated or expired, say so separately from "absent": ask for access
or a fresh link only if you truly need it, otherwise carry on and note the
limit.
- If someone in the thread already named the cause, shared a repro, linked a
fix, or said it's being handled, verify that and build on it. Never ask the
reporter to repeat it.
- If the report has a run ID, inspect that persisted run, its events and tool
cards first. Don't ask for the prompt or last tool card until that is
exhausted.
- Search recent Slack, local Git history, and merged PRs for repeat reports and
existing fixes before editing. A repeat of something already fixed is a
regression: find why the earlier fix didn't hold.
- Read
address-feedback, concurrent-agents, and verifying-changes. Re-read
dirty files and keep peer work intact; never reset, stash, or overwrite it.
2. Decide: fix, build, or needs a person
Apply the decision gate before reacting or editing, using the buckets in
review-latest-feedback:
- Objectively broken (errors, dead clicks, lost or wrong data,
regressions, slowness, clipping, overlap, broken layout): fix it.
- Subjective UX asks (add, move, hide, restyle a control; "hard to find"):
don't auto-implement. These get 🎫 and a reply that it's logged for a product decision,
naming no one.
Concrete critique of an existing surface that is clearly a defect is a bug,
not a UX ask. A maintainer's
:upvote: on a feature request means build the
smallest version that does what was asked; no second sign-off needed.
- Not actionable (praise, chatter, announcements, bot forwards, duplicates):
no reaction, no reply.
Pick the fix altitude using address-feedback: smallest owning seam for one
report, the shared primitive for a repeated failure, and never a global agent
rule from one data point.
Once a thread is in scope, add 👀 before investigating, one thread at a time,
and only if you'll finish answering it in this run. If the reaction fails,
resolve that before going on.
3. Clusters and questions
- When several threads report the same underlying issue, drive one fix and one
piece of work for the cluster. Reply in each reporter's own thread once, in
the usual one-sentence style, rather than sending a pile of duplicates.
- Ask a reporter a question only when one specific missing detail blocks a safe
fix to an otherwise clear bug, and only one question may be pending per
thread. Before asking, re-read the whole thread, including earlier questions
from this skill,
review-latest-feedback, or @agent-native, and check it
hasn't already been answered or resolved.
- Never ask for evidence that is already in the thread, for access you only
lack internally, or for a subjective product choice.
- An answer from anyone in the thread counts. Re-read the full thread, then try
the fix with the new detail before asking anything else. A partial answer
keeps the existing question pending. Ask a new question only about a single,
different, still-blocking detail.
4. Fix, verify, ship
Group independent fixes across subagents with disjoint files, reproduce where
you reasonably can, fix, and verify as verifying-changes describes (a test
that fails before and passes after, or the flow working in the running app).
Timebox one item to about 30 minutes; if it doesn't yield, it becomes 🎫 with a
line on what you learned. Put the fixes in one PR and run /ship through the
merge, with every fixed thread's Slack link in the PR body's Reports
section. Only the PR this run opened gets pushed, merged, or commented on.
5. Close the loop
Run review-latest-feedback step 5 for every thread you put 👀 on. That
step owns the replies, reactions, and skip rules. Its no-duplicate check
covers the Reports threads /ship already closed out after the merge.
Then re-read each thread you touched and confirm the reply landed under the
right parent. If a participant replies after you
post, re-read the whole thread before deciding what to do next.
If the user says earlier replies were too technical, edit every reply from this
run, not just the latest example.
6. Recap
Briefly: threads fixed (with links), threads needing a person and who,
questions asked, anything you couldn't verify, and the PR link.
Related skills
review-latest-feedback (Slack contract), address-feedback (classification
and fix altitude), concurrent-agents, verifying-changes.
1---2name: address-feedback-with-replies3description: >-4 Fix the feedback in specific Slack threads or a named Slack scope and answer5 each reporter in-thread. Use when the user points at particular Slack6 feedback and says "address this feedback", "fix these and reply", or links7 threads. For a full sweep of the feedback channels use review-latest-feedback.8scope: dev9metadata:10 source: https://skillmd.com/skills/builderio/address-feedback-with-replies11 internal: true12---1314# Address Feedback With Replies1516Triage, fix, ship, and answer the Slack threads the user pointed at, in one17pass. This is `review-latest-feedback` aimed at a specific set of threads18instead of the whole sweep. That skill owns the Slack contract: the 👀 / ✅ / 🎫19reactions, the one-sentence reply and its wording, which channels are fair20game, the "leave it alone" rules, and maintainer reactions such as `:upvote:`. Read it first and21follow it. This file adds only what is specific to working a given thread.2223Use the connected Slack integration for every read and write, and confirm which24profile is connected before the first write. Never drive Slack through a browser or25computer use.2627## 1. Read everything first2829- Read the parent message and every reply. Open every screenshot, file, video,30 transcript, and linked recording; the error text there is often the whole31 diagnosis.32- Fetch linked artifacts through their own connector or public URL. If one is33 permission-gated or expired, say so separately from "absent": ask for access34 or a fresh link only if you truly need it, otherwise carry on and note the35 limit.36- If someone in the thread already named the cause, shared a repro, linked a37 fix, or said it's being handled, verify that and build on it. Never ask the38 reporter to repeat it.39- If the report has a run ID, inspect that persisted run, its events and tool40 cards first. Don't ask for the prompt or last tool card until that is41 exhausted.42- Search recent Slack, local Git history, and merged PRs for repeat reports and43 existing fixes before editing. A repeat of something already fixed is a44 regression: find why the earlier fix didn't hold.45- Read `address-feedback`, `concurrent-agents`, and `verifying-changes`. Re-read46 dirty files and keep peer work intact; never reset, stash, or overwrite it.4748## 2. Decide: fix, build, or needs a person4950Apply the decision gate before reacting or editing, using the buckets in51`review-latest-feedback`:5253- **Objectively broken** (errors, dead clicks, lost or wrong data,54 regressions, slowness, clipping, overlap, broken layout): fix it.55- **Subjective UX asks** (add, move, hide, restyle a control; "hard to find"):56 don't auto-implement. These get 🎫 and a reply that it's logged for a product decision,57 naming no one.58 Concrete critique of an existing surface that is clearly a defect is a bug,59 not a UX ask. A maintainer's `:upvote:` on a feature request means build the60 smallest version that does what was asked; no second sign-off needed.61- **Not actionable** (praise, chatter, announcements, bot forwards, duplicates):62 no reaction, no reply.6364Pick the fix altitude using `address-feedback`: smallest owning seam for one65report, the shared primitive for a repeated failure, and never a global agent66rule from one data point.6768Once a thread is in scope, add 👀 before investigating, one thread at a time,69and only if you'll finish answering it in this run. If the reaction fails,70resolve that before going on.7172## 3. Clusters and questions7374- When several threads report the same underlying issue, drive one fix and one75 piece of work for the cluster. Reply in each reporter's own thread once, in76 the usual one-sentence style, rather than sending a pile of duplicates.77- Ask a reporter a question only when one specific missing detail blocks a safe78 fix to an otherwise clear bug, and only one question may be pending per79 thread. Before asking, re-read the whole thread, including earlier questions80 from this skill, `review-latest-feedback`, or `@agent-native`, and check it81 hasn't already been answered or resolved.82- Never ask for evidence that is already in the thread, for access you only83 lack internally, or for a subjective product choice.84- An answer from anyone in the thread counts. Re-read the full thread, then try85 the fix with the new detail before asking anything else. A partial answer86 keeps the existing question pending. Ask a new question only about a single,87 different, still-blocking detail.8889## 4. Fix, verify, ship9091Group independent fixes across subagents with disjoint files, reproduce where92you reasonably can, fix, and verify as `verifying-changes` describes (a test93that fails before and passes after, or the flow working in the running app).94Timebox one item to about 30 minutes; if it doesn't yield, it becomes 🎫 with a95line on what you learned. Put the fixes in one PR and run `/ship` through the96merge, with every fixed thread's Slack link in the PR body's `Reports`97section. Only the PR this run opened gets pushed, merged, or commented on.9899## 5. Close the loop100101Run `review-latest-feedback` step 5 for every thread you put 👀 on. That102step owns the replies, reactions, and skip rules. Its no-duplicate check103covers the `Reports` threads `/ship` already closed out after the merge.104105Then re-read each thread you touched and confirm the reply landed under the106right parent. If a participant replies after you107post, re-read the whole thread before deciding what to do next.108109If the user says earlier replies were too technical, edit every reply from this110run, not just the latest example.111112## 6. Recap113114Briefly: threads fixed (with links), threads needing a person and who,115questions asked, anything you couldn't verify, and the PR link.116117## Related skills118119`review-latest-feedback` (Slack contract), `address-feedback` (classification120and fix altitude), `concurrent-agents`, `verifying-changes`.