reviewing-changes
Skill1 starsChanged 5 months agoMITView on GitHub
Thorough, guided code review for the Slack-Claude Bridge — walks the project Review checklist (session/scope integrity, trigger correctness, local-first scope, secret safety, identity, naming) with the domain reasoning behind each check. Use for an in-depth review. The built-in /code-review already applies the same checklist from CLAUDE.md; load this when you want the guided deep pass.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- okgrit/done-is-a-claimtheir own version, first seen Nov 8, 2026
- Grit-77/done-is-a-claimtheir own version, first seen Oct 15, 2026
- bitwarden/iostheir own version, first seen Oct 8, 2026
- bitwarden/androidtheir own version, first seen Oct 8, 2026
- calebnewtonusc/Chewbaccatheir own version, first seen Aug 11, 2026
- vanenshi/skillstheir own version, first seen Aug 5, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- bitwarden/android★ 9.6ksame name
- bitwarden/ios★ 731same name
- Grit-77/done-is-a-claim★ 33same name
- okgrit/done-is-a-claim★ 33same name
- calebnewtonusc/Chewbacca★ 8same name
- vanenshi/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- bridge-domainSkill
- run-bridgeSkill
- verifying-workSkill
The file
Files
Reviewing Slack-Claude Bridge changes (guided deep pass)
This skill complements — it does not replace — the built-in /code-review. The Review
checklist also lives in CLAUDE.md, which /code-review reads automatically, so a quick review
via /code-review already applies these checks. Load this skill when you want a deeper, guided
walkthrough with the reasoning behind each item.
Step 1 — Generic pass
Review the current diff (git status / git diff, including untracked files): correctness, edge
cases, error handling, security, clarity/naming, test/doc gaps. You may run /code-review for this.
Step 2 — Project checklist (with reasoning)
- Session & scope integrity — channel scope keys on
channel_id; thread scope onchannel_id + thread_ts. Replies post to the correct location (channel vs in-thread). Sessions are reused per scope and persist across bridge restarts. Why: a wrong key collapses or leaks sessions across channels/threads; the wrong post target breaks the channel-vs-thread contract. - Trigger correctness —
mentionignores non-mention messages;autohandles every in-scope message. All four scope×trigger combinations stay consistent. Why: a leaky mention filter makes the bridge respond when it shouldn't; a missed auto message drops work silently. - Local-first scope — flag any hosted service, relay, coordinator, extra Slack command beyond
@claude status, or other PRD "Out of Scope" item. Why: V1 is strictly single-process local. - Secret safety — no hardcoded tokens; credentials only from env; nothing secret logged.
- Identity — the mapping identity appears in Slack responses, logs, and status output.
- Naming — our local process is "the bridge", not "agent" (see CLAUDE.md Terminology).
Step 3 — Report
Separate must-fix (bugs, scope/security violations) from nice-to-have (style). If the change
is sound, say so plainly. See bridge-domain for the full model behind checks 1–2.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

