gate-check
Skill40 starsChanged 7 months agoMITView on GitHub
Validate readiness to advance between development phases. Synthesizes QA, perf, security, asset, balance, and localization verdicts into a single PASS/CONCERNS/FAIL with specific blockers and required artifacts. Use when asking 'are we ready to advance?'.
20 other projects use a version of this.
Adopted by
Most recently taken up by
- microsoft/cat-agent-skillstheir own version, first seen Nov 8, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- supernovae-st/nikatheir own version, first seen Oct 28, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
- nuncaeslupus/literary-critictheir own version, first seen Oct 13, 2026
Used with
Projects with it also use setup-engine, team-level and 1 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
CoralGameSkillsetup-engine
Configure the project's game engine and version. Pins the engine in CLAUDE.md, detects knowledge gaps, and populates engine reference docs via WebSearch when the version is beyond the LLM's training data.
Also in 13 projects that use this
CoralGameSkillteam-level
Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.
Also in 12 projects that use this
- +1 more from CoralGame
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 20
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- pixel-cellar/Claude-Code-Game-Studios★ 324same name
- striderZA/OpenCodeGameStudios★ 118same name
- microsoft/cat-agent-skills★ 101same name
- supernovae-st/nika★ 96same name
- tranhieutt/software_development_department★ 71same name
- CoralGame/Claude-Code-Game-Studios★ 19same name
- phj128/autoworker★ 18same name
- dawn840705/codex-code-studios★ 17same name
- CodePhobiia/claude-roblox-game-studio★ 9same name
10 more not listed
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 repository77 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design/CLAUDE.mdCLAUDE.md
- docs/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- tests/CLAUDE.mdCLAUDE.md
- adoptSkill
- architecture-decisionSkill
- architecture-reviewSkill
- asset-auditSkill
- asset-specSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- bug-triageSkill
- changelogSkill
- code-reviewSkill
- consistency-checkSkill
- content-auditSkill
- create-architectureSkill
- create-control-manifestSkill
- create-epicsSkill
- create-storiesSkill
- day-one-patchSkill
- design-bibleSkill
- design-reviewSkill
- design-systemSkill
- dev-storySkill
- estimateSkill
- extractSkill
- helpSkill
- hotfixSkill
- launch-checklistSkill
- localizeSkill
- map-systemsSkill
- milestone-reviewSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- prd-reviewSkill
- project-stage-detectSkill
- propagate-design-changeSkill
- prototypeSkill
- qa-planSkill
- quick-designSkill
- regression-suiteSkill
- release-checklistSkill
- retrospectiveSkill
- reverse-documentSkill
- review-all-prdsSkill
- scope-checkSkill
- security-auditSkill
- setup-frameworkSkill
- skill-improveSkill
- skill-testSkill
- smoke-checkSkill
- soak-testSkill
- sprint-planSkill
- sprint-statusSkill
- startSkill
- story-doneSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 19 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 28
No argument — ask the user.
- Very specific: line 67
All MVP PRDs reviewed via /review-all-prds with PASS verdict.
- Distinctive: line 82
All Critical / Must-Have features implemented per PRD.
- Distinctive: line 114
Look for contradictions between artifacts:
- Distinctive: line 139
All required-for-this-gate artifacts at +1, no contradictions -> PASS.
- Very specific: line 198
Ask before writing to production/gates/gate-[from-to]-[date].md.
- Very specific: line 215
If verdict is PASS and the user agrees, ask: "May I update production/stage.txt to [to]?"
“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Gate Check
Phase advancement requires more than vibes. This skill collects every recent verdict artifact, cross-checks them for staleness and consistency, and emits a single PASS / CONCERNS / FAIL ruling. It is intentionally cross-system synthesis — therefore Opus tier.
Phase 1: Determine Source and Target Phase
Parse the argument:
- Explicit form:
prototype->preproduction,preproduction->production,production->polish,polish->release,release->live-ops. --auto— readproduction/stage.txtand use the next standard transition.- No argument — ask the user.
Each gate has a different artifact bar (see Phase 3).
Phase 2: Inventory Recent Artifacts
Glob the latest of each artifact type:
production/qa/qa-signoff-*.mdproduction/qa/smoke-*.mdproduction/perf/perf-profile-*.mdproduction/security/security-audit-*.mdproduction/assets/asset-audit-*.mdproduction/balance/balance-check-*.mdproduction/localization/loc-report-*.mddocs/tech-debt.mdproduction/qa/soak/[date]/summary.mdproduction/releases/release-checklist-*.mdproduction/releases/launch-checklist-*.mddocs/architecture/for ADR statusesproduction/qa/bugs/for open S1/S2 counts
For each, capture: path, last modified date, verdict.
Apply staleness rule: any artifact older than 14 days is suspect for a release-tier gate. Flag and surface.
Phase 3: Apply the Gate-Specific Bar
prototype -> preproduction
Required:
- Architecture artifacts present (
docs/architecture/master-architecture.md, ADRs, control manifest). - All MVP PRDs reviewed via
/review-all-prdswith PASS verdict. - No
proposedADRs blocking.
preproduction -> production
Required:
/test-setupcomplete and CI runs green.- Foundation epics done.
- First sprint plan approved.
production -> polish
Required:
- All Critical / Must-Have features implemented per PRD.
- Latest QA sign-off APPROVED on the most recent sprint.
- Open S1/S2 bugs == 0.
- Tech debt register reviewed in last 30 days.
polish -> release
Required:
- Latest perf profile HEALTHY.
- Latest security audit RELEASE OK.
- Soak test summary PASS.
- Localization 100% on every target locale.
- Asset audit CLEAN.
- Balance check BALANCED.
- Regression suite green.
- Open S1/S2 == 0; open S3 reviewed.
release -> live-ops
Required:
/launch-checklistGO.- Day-one patch scoped or N/A.
- Crash + analytics live and verified post-deploy.
- On-call rotation defined.
- Rollback plan documented.
Phase 4: Cross-Verdict Consistency
Look for contradictions between artifacts:
- QA sign-off says "no S1/S2" but
production/qa/bugs/shows open S1 -> contradiction. - Perf profile HEALTHY but soak summary lists memory growth -> recheck.
- Security RELEASE OK but tech debt register has a P0 deprecated-API with pending OS removal -> conflict.
- Asset audit CLEAN but localization report has missing locales for store screenshots -> partial.
Surface every contradiction. None can be silently passed through.
Phase 5: Apply Severity Rules
Convert each artifact's status to a contribution:
- Verdict PASS / GREEN / APPROVED -> +1.
- Verdict WITH CONDITIONS / WARNINGS / NEEDS WORK -> 0 (note conditions).
- Verdict FAIL / RED / NOT APPROVED / BLOCKING -> -1.
- Stale (> 14 days) -> 0 with a note suggesting re-run.
Compute the gate result:
- All required-for-this-gate artifacts at +1, no contradictions -> PASS.
- Any -1 OR any required artifact missing OR any contradiction unresolved -> FAIL.
- Otherwise (mix of +1 and 0 with no -1) -> CONCERNS.
Phase 6: Build Specific Blocker List
For FAIL verdicts, every -1 contributes a specific blocker line:
- "QA sign-off NOT APPROVED — sprint-04 build failed manual QA on
paywall flow. Re-run
/team-qaafter fix." - "Soak test FAIL — 12 MB/h leak after 4 hours. Open story to address before re-running soak."
For CONCERNS, every conditions/warnings entry contributes a recommended follow-up.
Phase 7: Render the Verdict
# Gate Check: [from] -> [to]
Date: [date]
Tier: [PASS / CONCERNS / FAIL]
## Artifact Inventory
| Artifact | Date | Verdict | Stale? | Contribution |
|----------|------|---------|--------|--------------|
| QA sign-off (sprint-04) | 2026-04-29 | APPROVED | no | +1 |
| Perf profile | 2026-05-01 | HEALTHY | no | +1 |
| Security audit | 2026-04-12 | RELEASE WITH PLAN | borderline | 0 |
| Soak summary | (none) | MISSING | — | -1 |
## Cross-Verdict Conflicts
- [list, or "None"]
## Blockers
- [each -1 contribution as a one-line action]
## Concerns
- [each 0 contribution as a recommended follow-up]
## Required Artifacts Missing
- [list]
## Verdict: [PASS / CONCERNS / FAIL]
Rationale: [synthesis paragraph]
## Recommended Path
- [if PASS] Update `production/stage.txt` to [to] and proceed.
- [if CONCERNS] Either accept conditions or address top 1-2 concerns.
- [if FAIL] Address listed blockers in priority order; re-run gate
after each.Ask before writing to production/gates/gate-[from-to]-[date].md.
Phase 8: Update Session State
Append to production/session-state/active.md:
## Gate Check — [date]
- Direction: [from] -> [to]
- Verdict: [PASS / CONCERNS / FAIL]
- Blockers: [count]
- Path: [path]
- Next: [advance | resolve and re-run]If verdict is PASS and the user agrees, ask:
"May I update production/stage.txt to [to]?"
Quality Gates / PASS-FAIL
This skill IS the gate. The verdict is binding for phase advancement.
Examples
Example 1 — polish -> release:
QA APPROVED, perf HEALTHY, security RELEASE OK, soak PASS,
localization 100%, asset CLEAN, balance BALANCED, regression GREEN.
Verdict: PASS. Stage updated to release.
Example 2 — production -> polish: QA APPROVED but 3 S2 bugs open in production/qa/bugs/. Verdict: FAIL with one blocker: "Resolve open S2 bugs (BUG-104, BUG-109, BUG-117) or document explicit deferral."
Next Steps
- PASS -> proceed with stage transition.
- CONCERNS -> resolve top concerns, re-run if release-tier.
- FAIL -> drive blockers to closure; re-run.
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.

