chore(skills): remove dated patterns and redundancy from skill prompts

[waleedlatif1]

Summary

• Audited every skill under .agents/skills (plus add-settings-page) for instructions written for older models, stale paths/commands, and content duplicated across skills or already covered by CLAUDE.md and .claude/rules
• Fixed stale references: safeCompare import path, helm poll-cron shape, bun test → vitest invocation, CONNECTOR_META_REGISTRY icon read, deleted v2 rollout gate, cursorScopeKey, file-parse path, chunkArray source, getHostedModels provider list, provider flag consumption matrix, Exa hosted-key reference, defineWorkspaceOperation example missing the required capability
• Resolved skill-vs-rule disagreements: mutation onSuccess/onSettled, returned hook callbacks, read-once URL params, settings-page chrome ownership, block outputs nested example, credential oauth-input inference, boolean sub-block type, shadow-vs-border and press-scale guidance in the vendored design skills
• Collapsed duplicate copies to one owner: resolved-secret rules now live only in add-tools; add-integration points at add-tools/add-block/add-trigger instead of carrying drifted partial copies; validate-model reuses add-model's consumption matrix; babysit defers to ship's "What to Omit"
• Removed history narratives, migration-relative phrasing, pinned counts, and emphasis boosters; kept every tool contract, exact command sequence, and reasoned constraint

Type of Change

• Chore

Testing

bun run skills:sync --check, bun run lint, check-block-registry, and bun run check:audits (45 audits) all pass.

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated
docs	Ready	Preview	Sep 2, 2026 5:29pm UTC

[greptile-apps]

Greptile Summary

The PR streamlines and updates skill prompts by removing stale guidance, consolidating duplicated instructions, and correcting repository references and behavioral contracts.

• Centralizes model capability-consumption guidance and synchronizes validation skills with their authoritative counterparts.
• Updates block, integration, trigger, connector, UI, testing, and release instructions to reflect current repository behavior.
• Removes dated migration narratives and redundant emphasis while preserving required commands and constraints.

Confidence Score: 5/5

The PR appears safe to merge.

No blocking failure remains.

Important Files Changed

Filename	Overview
.agents/skills/add-model/SKILL.md	The reasoning capability matrix now includes Z.AI, Meta, and LiteLLM for reasoningEffort, plus Z.AI and Kimi for resolved thinkingLevel, matching current provider implementations.
.agents/skills/validate-model/SKILL.md	Model validation now reuses the centralized add-model capability guidance rather than maintaining a drift-prone duplicate.
.agents/skills/add-integration/SKILL.md	Integration guidance delegates specialized tool, block, and trigger contracts to their owning skills and removes redundant copies.
.agents/skills/add-block/SKILL.md	Block-authoring guidance is condensed and corrected for output schemas, canonical parameters, selector behavior, and current validation commands.

_{Reviews (2): Last reviewed commit: "chore(skills): correct provider matrix a..." | Re-trigger Greptile}

[cubic-dev-ai]

All reported issues were addressed across 34 files

_{Re-trigger cubic}

[waleedlatif1]

@greptile

[waleedlatif1]

@cubic-dev-ai review this PR

[cubic-dev-ai]

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.