review-suggestions
Skill8 starsChanged 7 days agoApache-2.0View on GitHub
Adds a few non-blocking P2 suggestions on maintainability, design and hygiene. Never P0 or P1. Use when you want improvement ideas beyond blocking defects.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- allanbian1017/skillstheir own version, first seen Jul 3, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- allanbian1017/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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- github-pr-reviewSkill
- local-code-reviewSkill
- review-backendSkill
- review-coreSkill
- review-deep-investigationSkill
- review-frontendSkill
- review-publish-githubSkill
- review-requirementsSkill
- review-runtime-checkSkill
- review-securitySkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
Read-only, by review-core's S1 and S10.
- Distinctive: line 36
Keep only the most valuable few: at most five: Prefer a suggestion that removes a future defect or a real cost.
- Distinctive: line 45
Never emit P0 or P1: When a candidate looks serious enough for one, do not raise it here: report it as a finding under the Core's bar when …
- Distinctive: line 49
When nothing meets the bar, add nothing and say so in "Additional expertise".
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
review-suggestions
Adds a short list of non-blocking suggestions to a review-core review. It
emits P2 only, so it can never change the decision: review-core's decision
rule counts P0 and P1, and P2 never blocks. It never lowers, removes or
re-rates an existing P0 or P1, never clears a REVIEW INCOMPLETE trigger, and
never turns a blocking or incomplete decision into a clean one.
It never changes severity, the decision rule, the REVIEW INCOMPLETE
triggers or S1–S5 and S10; those are review-core's.
Requires review-core. Install it alongside this Skill; without it, stop and ask the user to install it.
Entry contract
- Runs only after
review-corehas run on the same target in this run, and only when selected underreview-core's "Mode" (S6, stated there). - Needs no input beyond the target and the Core's findings.
- Read-only, by
review-core's S1 and S10.
Procedure
- Look for suggestions in the changed code, after the Core's review:
- maintainability — duplication the change introduces, a function or file that now does several jobs, unclear naming, dead code the change leaves behind;
- design — a localized weakness: a responsibility in the wrong place, a leaky abstraction, a fragile coupling the change adds;
- hygiene — a lower-risk test gap, misleading documentation or comments, an inconsistency with the repository's own conventions.
- Keep only the most valuable few: at most five. Prefer a suggestion that removes a future defect or a real cost. Drop style, formatting, naming taste and anything a linter or formatter owns. Drop anything that is already a Core finding or a pre-existing issue the change does not touch.
- Add each as a finding in
review-core's shape (location,evidence,impact,fixincluded), always severity P2, numbered after the Core's findings and the other mini-skills'. The evidence rule is the Core's: cite only what you read (S4). - Never emit P0 or P1. When a candidate looks serious enough for one, do not raise it here: report it as a finding under the Core's bar when it meets it, else drop it.
When nothing meets the bar, add nothing and say so in "Additional expertise". Silence is a valid result.
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.