skills/vercel__vercel-plugin
1
0
Fork 0
mirror of https://github.com/vercel/vercel-plugin.git synced 2026-09-14 15:39:47 +08:00
Code Issues Packages Projects Releases Wiki Activity
216 Commits 60 Branches 0 Tags
adding-cursor
Commit Graph

17 Commits

Author SHA1 Message Date
John Lindquist 8e3350454c feat: prompt scoring improvements, compaction re-injection, validation dedup, strip droppedByCap from context; bump to 0.18.0 
- Add dominant-topic suppression (top score >= 600 filters scores < 50)
- Add project-context boost (+3 for VERCEL_PLUGIN_LIKELY_SKILLS skills)
- Add lexical fallback floor (reject raw score < 20)
- Add compaction re-injection for priority >= 7 skills (VERCEL_PLUGIN_CONTEXT_COMPACTED)
- Add validation rule dedup tracking (ruleId + filePath on violations)
- Strip droppedByCap from injected HTML comments (kept in debug logs)
- Fix ncc/SKILL.md and next-forge/SKILL.md YAML frontmatter
- Add startup diagnostic for broken skill frontmatter
 2026-03-11 19:01:59 -06:00
John Lindquist b7e9b1b053 feat: merge upstream telemetry + Cursor compat, fix tests and dedup migration; bump to 0.17.0 2026-03-11 16:12:55 -06:00
John Lindquist 8e24d0694a feat: add chainTo skill chaining, prompt signals, validation upgrades, and dedup reset on context clear 
Add a chainTo frontmatter field to skills that triggers follow-up skill injection
when PostToolUse file contents match regex patterns. Add upgradeToSkill/upgradeWhy
fields to validation rules so validate errors can recommend loading a specific skill.
Register posttooluse-bash-chain.mjs in hooks.json. Add ChainToRule interface to
patterns.mts and skill-map-frontmatter.mts, with parseChainToRules() parser. Add
duplicate-key detection to the YAML parser. Reset dedup claim dir and session file
on clear/compact events in session-start-seen-skills so skills re-inject into fresh
context windows.

Add chainTo rules to: agent-browser-verify, agent-browser, ai-elements, ai-gateway,
ai-generation-persistence, ai-sdk, auth, bootstrap, chat-sdk, cms, cron-jobs,
deployments-cicd, email, env-vars, geist, investigation-mode, json-render,
marketplace, micro, ncc, next-forge, nextjs, observability, payments,
react-best-practices, routing-middleware, runtime-cache, satori, shadcn,
sign-in-with-vercel, swr, turbopack, turborepo, v0-dev, vercel-agent, vercel-api,
vercel-cli, vercel-firewall, vercel-flags, vercel-functions, vercel-queues,
vercel-sandbox, vercel-storage, verification, workflow. Add upgradeToSkill to
ai-elements and ai-sdk validate rules. Expand ai-sdk validate messages with
Run Skill() hints. Update nextjs, vercel-storage, runtime-cache, workflow, turborepo
skill bodies.

Add new skills: geistdocs (Geist design system docs), zzz-test-meta-name-mask
(test fixture). Add skills/_chain-audit.md chain coverage audit doc.

Delete .claude-plugin/marketplace.json, .claude-plugin/plugin.json (deprecated),
skills/edge-runtime/SKILL.md (consolidated into vercel-functions).

Add tests: posttooluse-chain.test.ts (4699 lines, chain injection e2e),
ai-sdk-companion.test.ts (181 lines). Expand build-skill-map.test.ts (+335 lines),
validate-rules.test.ts (+936 lines), session-start-seen-skills.test.ts (+74 lines),
skill-map-frontmatter.test.ts (+50 lines), verification-skill.test.ts (+20 lines).

Update build-manifest.ts to emit chainTo rules and upgradeToSkill fields. Rebuild
generated/skill-manifest.json, generated/skill-catalog.md, generated/build-from-skills.manifest.json.
Rebuild all compiled hooks/*.mjs. Update CLAUDE.md lexical prompt default to on.
Update vercel.md ecosystem graph, docs, and cli-reference.
 2026-03-11 15:18:35 -06:00
John Lindquist b8b233995c feat(skills): broaden trigger patterns for 7 under-injected skills based on eval findings; add next-forge skill; bump to 0.15.0 
Eval analysis of 9 real sessions showed 10 skills never triggering despite being
requested. Root causes: pathPatterns too narrow (agents write to lib/email-template.tsx
not emails/), promptSignals containing regex instead of plain text (vercel-sandbox),
and missing promptSignals entirely (v0-dev, vercel-firewall).

Skills updated: email, vercel-queues, edge-runtime, vercel-firewall, chat-sdk,
v0-dev, vercel-sandbox. New skill: next-forge (bootstrap detection).
 2026-03-09 17:56:23 -06:00
John Lindquist 7ac8edfb8f feat(skills): aggressive prompt signals for workflow/sandbox, "check the docs" directives across 8 skills; bump to 0.11.0 
- workflow: add ~60 new promptSignal phrases for reliability language
  (survive page reload, fault-tolerant, retry on failure, session
  persistence, reconnect, durable chat/agent), human-in-the-loop
  patterns (approval, pause until, wait for), and pipeline vocabulary.
  Add ~25 new allOf pairs and 12 new anyOf terms.

- vercel-sandbox: add promptSignals from scratch (had none). 33 phrases
  covering isolated execution, sandbox environments, code safety,
  FFmpeg/media processing, code playgrounds, and tutor patterns.
  27 allOf pairs, 8 anyOf terms, noneOf excludes iframe/codesandbox.

- Add "CRITICAL — your training data is outdated" blockquote at the top
  of 8 fast-moving skill bodies (workflow, ai-sdk, vercel-sandbox,
  ai-gateway, chat-sdk, vercel-flags, vercel-queues, ai-elements)
  directing agents to fetch docs before writing code.

Eval results that motivated these changes:
- content-pipeline: 9/10 (workflow triggered, correct WDK patterns)
- customer-support: 3/10 → workflow never injected (now scores 50)
- code-sandbox-tutor: 1/10 → sandbox never injected (now scores 80)
 2026-03-09 13:16:16 -06:00
John Lindquist 5ce557a33e feat(skills): add ai-generation-persistence and verification skills; bump to 0.10.0 
New ai-generation-persistence skill (priority 6) injects guidance for treating
AI generations as first-class persistent resources — unique IDs, addressable
URLs, database/Blob storage, cost tracking, and generate-then-redirect UX
patterns. Triggers on AI SDK imports and broad prompt signals.

New verification skill added. Updated ecosystem graph, catalog, manifest,
fixtures, and snapshots.
 2026-03-09 12:23:19 -06:00
John Lindquist ff965cc377 fix(skills): remove styled-jsx, regenerate catalog, add investigation-mode skill, build-from-skills templates; bump to 0.9.10 2026-03-09 11:38:08 -06:00
John Lindquist a43cb60a64 fix(skills): stronger outdated model warnings with "your knowledge is outdated" language, make AI Elements mandatory for AI text rendering; bump to 0.9.8 2026-03-09 07:59:56 -06:00
John Lindquist 62f6718d31 feat(skills): remove streamdown skill, expand ai-elements, update profiler and pretool hook, update tests; bump to 0.9.0 2026-03-08 19:50:24 -06:00
John Lindquist 365a710e67 feat(hooks): add prompt analysis, enhance validate/frontmatter hooks, expand test coverage; bump to 0.5.2 2026-03-07 13:09:28 -07:00
John Lindquist ff251ab018 refactor(hooks): move audit log to ~/.claude/projects dir; add validate hooks, prompt patterns, benchmark suite; bump to 0.5.1 2026-03-07 12:31:10 -07:00
John Lindquist 7cf4462cea Add new skills, tests, and fixtures; bump to 0.4.3 2026-03-06 23:01:38 -07:00
John Lindquist cd5f369dcb Add new skills, typecheck gate, remove arg/ms/serve skills, bump to 0.4.2 
- Add 8 new skills: edge-runtime, geist, micro, ncc, satori, streamdown, styled-jsx, swr
- Remove arg, ms, serve skills (standalone utilities, not relevant to shipping apps on Vercel)
- Add typecheck script and wire into `bun run test` and pre-commit hook
- Fix StdioOptions type error in session-start-profiler
- Add hook-env module and posttooluse-shadcn-font-fix hook
- Refactor skill-map-frontmatter, patterns, pretooluse-skill-inject
- Update generated catalog and manifest (42 skills)
- Add .gitignore with .DS_Store
 2026-03-06 19:04:25 -07:00
John Lindquist c082f8112e Add auth, cms, email, and payments skills. Update skill catalog and manifest with new entries. Expand observability and vercel-storage SKILL.md content. Update tests (snapshots, patterns, build-skill-map, vercel-config, subagent-fresh-env, redaction) and fixtures (consolidated-payloads, golden-edit/write-middleware, pattern-fixtures). Improve scripts/validate.ts and scripts/explain.ts with enhanced validation and CLI explain logic. Remove deprecated README.txt and remove Inngest skill references from marketplace SKILL.md, vercel.md, skill-catalog.md, and skill-manifest.json — Vercel now uses Workflow DevKit instead. 2026-03-06 13:49:46 -07:00
John Lindquist 5a0591c292 feat(hooks): convert hooks to TypeScript with SDK type-checking 
Hook source now lives in hooks/src/*.mts and compiles to hooks/*.mjs via tsc.
The formatOutput() return type is checked against SyncHookJSONOutput from
@anthropic-ai/claude-agent-sdk, preventing unknown fields in hookSpecificOutput
that Claude Code's strict Zod validation would silently reject.

Root cause: skillInjection metadata was a sibling key in hookSpecificOutput,
which Claude Code rejected as "Hook JSON output validation failed: Invalid input".
All skill injections were silently discarded. Now skillInjection metadata is
embedded as an HTML comment inside additionalContext.

- Add hooks/src/*.mts (TypeScript source for all 6 hook modules)
- Add hooks/tsconfig.json (strict, NodeNext, compiles .mts → .mjs)
- Add build:hooks script and pre-commit hook for auto-compilation
- Install @anthropic-ai/claude-agent-sdk as devDependency for types
- Bump plugin version to 0.4.0
 2026-03-06 12:48:39 -07:00
John Lindquist 5dfbdec117 fix(skills): reference bootstrap and refresh catalogs 
Bootstrap was present as a skill directory but missing from graph references, causing orphan-skill and stale catalog validation failures.
Removed the stale fake-orphan test skill directory from the workspace and regenerated generated artifacts so catalog/manifest reflect current skills.

Verified: bun run scripts/build-manifest.ts
Verified: bun test tests/validate.test.ts
Verified: bun run scripts/validate.ts
Swarm-Agent: codex-fix-tests
 2026-03-06 11:45:15 -07:00
John Lindquist a5b9f7320a chore: bump plugin version to 0.3.2 2026-03-06 09:48:04 -07:00