ds-quality-gate
Skill20 starsChanged 46 days agoMITView on GitHub
Run the review pipeline against the current branch or feature as a finite quality gate — a sequenced set of strict review passes.
In this repository52 other files it gives its agents.
- ds-dev-skill-benchSkill
- ds-agent-reviewSkill
- ds-architecture-planSkill
- ds-arenaSkill
- ds-blast-radiusSkill
- ds-blueprintSkill
- ds-bug-reviewSkill
- ds-clarity-reviewSkill
- ds-code-quality-reviewSkill
- ds-comment-reviewSkill
- ds-data-modeSkill
- ds-data-reviewSkill
- ds-debugSkill
- ds-deslopSkill
- ds-doc-quality-reviewSkill
- ds-exploreSkill
- ds-git-modeSkill
- ds-go-reviewSkill
- ds-grill-meSkill
- ds-handoffSkill
- ds-howSkill
- ds-humanizeSkill
- ds-interaction-modeSkill
- ds-java-reviewSkill
- ds-notebook-reviewSkill
- ds-onboardingSkill
- ds-osvSkill
- ds-perf-planSkill
- ds-project-checkpointSkill
- ds-project-resumeSkill
- ds-python-reviewSkill
- ds-reflectSkill
- ds-retroSkill
- ds-roadmapSkill
- ds-rust-reviewSkill
- ds-security-reviewSkill
- ds-semgrepSkill
- ds-shell-reviewSkill
- dsSkill
- ds-specSkill
- ds-step-modeSkill
- ds-tdd-modeSkill
- ds-test-modeSkill
- ds-test-quality-reviewSkill
- ds-tiger-style-modeSkill
- ds-tldtSkill
- ds-ts-reviewSkill
- ds-ui-modeSkill
- ds-ui-quality-reviewSkill
- ds-verify-thisSkill
- ds-zig-reviewSkill
- ds-zoom-outSkill
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
- Distinctive: line 30
Ask: "Accept all / reject all / list numbers to skip?"
- Distinctive: line 34
If a pass finds nothing: say so in one line and move on.
- Very specific: line 47
Never skip a pass silently.
- Distinctive: line 50
If the user says "skip" or "next" mid-pass, honor it and proceed.
≈ “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
When invoked, run the quality gate: six strict review passes in sequence, bookended by /ds-deslop — run first to clean the incoming diff, and again last to strip any slop the between-pass fixes introduced. Each pass surfaces findings, you accept or reject them, the agent implements the accepted ones, then the next pass runs. The gate is finite — it runs once through the passes and finishes, not a standing mode. Say "stop" or "skip the rest" at any point to end it early.
Scope: the changed files on the current branch (same as /ds-code-quality-review with no argument). Narrow it by passing a path — /ds-quality-gate src/handlers/ limits every pass to that path.
The pipeline (in order)
1. /ds-deslop — strip narrating comments, defensive overkill, type escape hatches (clean the incoming diff)
2. /ds-code-quality-review — single source of truth + structure: delete duplicates, competing implementations, and dead abstractions, then is the diff making the codebase worse? (run early, so later passes don't audit code that should have been deleted)
3. /ds-test-quality-review — is the risky logic covered with real, non-trivial tests?
4. /ds-security-review — exploitability: input, auth, secrets, I/O, injection
5. /ds-bug-review — correctness: real bugs, not style
6. /ds-data-review — data correctness: schema, queries, transactions, migrations. Only when the change touches one of those; otherwise skip with a note
7. /ds-doc-quality-review — is the public API, config, and non-obvious behavior documented?
8. /ds-deslop — final cleanup: re-run to strip any slop the between-pass fixes introducedEach pass answers a different question. They do not overlap. The order matters: strip noise first so the structural and correctness passes see signal, not slop — and strip it again last, because this gate implements accepted fixes between passes, and those fixes are themselves freshly-generated code that can carry slop.
Per-pass loop
After each pass:
- Show findings for that pass only.
- Ask: "Accept all / reject all / list numbers to skip?"
- Implement accepted findings immediately before moving to the next pass.
- Confirm what changed, then proceed.
If a pass finds nothing: say so in one line and move on. Do not pad.
Invocation
/ds-quality-gate # run the full pipeline on branch changes
/ds-quality-gate src/api/ # scope every pass to a pathSay "stop" or "skip the rest" at any point to end the gate early. After the final pass, report a one-paragraph summary: what was fixed, what was skipped, and whether the branch is ready for /ds-verify-this.
Rules
- Never skip a pass silently. If a pass is irrelevant (e.g.,
/ds-security-reviewon a pure-data-model change with no I/O, or/ds-data-reviewon a change that touches no schema, queries, transactions, or migrations), say so and move on. - Implement accepted findings before the next pass — don't batch them all at the end.
/ds-deslopbookends the pipeline: first so reviewers (and the later passes) see clean code, and last so slop introduced by the gate's own between-pass fixes doesn't survive. The final deslop is the closing step — nothing runs after it.- If the user says "skip" or "next" mid-pass, honor it and proceed.
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.

