Monorepo review loop
Skill jcdavis131/cursor-agent-skills/skills/monorepo-review-loop
A recurring review workflow that walks a monorepo through a fixed arc — orient, plan, fan out reviewers, review code, run gates, check guards, align metadata, deploy+smoke, close out — using the 39 codified skills as the steps. Use to continuously update and refine a detailed monorepo so "done" is unambiguous, every claim is auditable, and docs/registry/tests/deploy stay aligned with the code. Run on a cadence (e.g. daily) or on demand after a batch of changes.From its SKILL.md
npx -y skills add jcdavis131/cursor-agent-skills --skill monorepo-review-loopAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.7 KB, 585 tokens by cl100k_base, as published. Nobody here has run it
Monorepo Review Loop
Goal: Review and refine the monorepo so docs, registry, tests, gates, and deploy stay aligned — "done" is unambiguous.
Commands and gates per phase: reference.md
Cadence: daily or on demand after a batch of changes.
The arc (10 phases)
| Phase | Skills | Exit gate |
|---|---|---|
| 0 Orient | session-orient, correct-assumptions, disk-pressure-proactive | Healthy env or docker-free task chosen |
| 1 Lane & Plan | lane-discipline, follow-procedure, progress-board, auto-mode | Board with tracker-tied deliverables in lane |
| 2 Review fan-out | sme-fanout, verify-subagent-output | SME reviews conformant; top-3 synthesized |
| 3 Code review | match-conventions, use-design-system, dependency-hygiene, abstract-the-provider, conservative-rename, policy-as-config, idempotent-seed-script | Conventions + shared primitives |
| 4 Gate pass | smoke-import, affected-tests, validate-gate, a11y-gate | Gates green; corpus size stated |
| 5 Guard pass | respect-the-guard, shell-confirm-hygiene, pre-commit-hygiene, agent-guardrails, deterministic-core-llm-judgment | Guards structural; secrets clean |
| 6 Metadata | metadata-align | Registry/docs match structure |
| 7 Deploy & smoke | use-available-integrations, post-deploy-smoke, event-driven-wait | One e2e path proven live |
| 8 Triage | background-failure-triage, silent-op-recovery, diagnose-before-retry, fill-the-wait, cost-transparency | Failures diagnosed; no blind retries |
| 9 Close-out | readiness-report, document-non-action, close-the-loop, logical-commit-split, persist-learnings, recap-on-long-session | Handoff + SHA + learnings persisted |
Loop discipline (all phases)
cost-transparency · fill-the-wait · event-driven-wait · progress-board · lane-discipline
Anti-patterns
Deploy before gates; skip metadata-align "because nothing changed"; close without commit SHA; persist learnings only at end; treat thin-corpus green as proof.
Pair with
Runner: scripts/monorepo_review_loop.py · Artifacts: knowledge/reviews/monorepo-review-<date>.md, HANDOFF.md
What ships with it: 1 file
7.9 KB alongside SKILL.md
- reference.md7.9 KB
Gives 0 of the 12 instructions most review quality skills give in 585 tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07
- Ask questions one at a timein 81 of 1048, across 64 files
- Provide a recommended answer for each questionin 73 of 1048, across 50 files
- Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
- Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
- Interview the user relentlessly about the planin 38 of 1048, across 13 files
- Order findings by severityin 31 of 1048
- Resolve each branch of the decision treein 27 of 1048, across 5 files
- Run a grilling sessionin 26 of 1048, across 5 files
- Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
- Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
- Create documentation files lazilyin 24 of 1048, across 5 files
- Assign severity to every findingin 24 of 1048
Said here and by no other author read
- check disk pressure during orientation
- tie board deliverables to the tracker
- fan out reviews to subject-matter experts
- review code against conventions and shared primitives
- pass smoke import and affected tests gates
- run accessibility checks
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.