fix: update vendored skills to latest versions#229
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
🔍 Tessl Skill Review
|
| Dimension | Score | Detail |
|---|---|---|
| conciseness | ██░ 2/3 | The skill is mostly efficient but includes some unnecessary content. The long list of resource guides with full descriptions adds bulk, and the adapter catalog subpath section explains usage patterns that Claude could infer from types. The core concepts section is somewhat redundant given the quick start example. However, most sections earn their place. |
| actionability | ███ 3/3 | The skill provides fully executable code examples: scaffold commands with exact flags, a complete quick start TypeScript example, streaming integration code, and JSX card examples. The CLI flags are specific and copy-paste ready, and the webhook/route patterns point to concrete file paths. |
| workflow clarity | ██░ 2/3 | The scaffolding workflow is clear with explicit commands, and the quick start shows a logical progression. However, there are no validation checkpoints — no steps to verify the bot is running, no error handling guidance for webhook setup, and no feedback loops for common failure modes like missing env vars or adapter misconfiguration. |
| progressive disclosure | ███ 3/3 | The skill excels at progressive disclosure with a clear overview structure that points to specific node_modules doc paths for deeper topics. References are one level deep, well-organized by topic (events, streaming, cards, adapters, custom adapters), and clearly signaled with exact file paths. The guides and templates sections provide additional resources without cluttering the main content. |
Overall: This is a well-structured skill that provides strong actionable guidance for building chat bots with Chat SDK. Its greatest strength is progressive disclosure — it serves as an effective index pointing to detailed docs while keeping the overview focused. The main weaknesses are the lack of validation/verification steps in workflows and some verbosity in the resources listing that could be trimmed.
Suggestions:
- Add a verification step after scaffolding (e.g., 'Run
pnpm devand confirm the webhook endpoint responds at localhost:3000/api/webhooks/slack') and after the quick start to confirm the bot connects successfully. - Add a brief troubleshooting or common errors section covering missing env vars, signature verification failures, and adapter not found — these are the most likely failure points that would benefit from explicit guidance.
plugins/chat-sdk/agent/skills/chat-sdk/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/dev3000/.agents/skills/d3k/SKILL.md
Review Details
Review Details
| Dimension | Score | Detail |
|---|---|---|
| conciseness | █░░ 1/3 | The skill is highly repetitive. The auth-sensitive browser rule, the 'Required Browser/Session Default' section, and parts of the Bootstrap Workflow all repeat the same guidance about not launching separate browsers and using d3k's browser-owning flow. The 'Why d3k-first' section explains motivation Claude doesn't need. Multiple sections restate the same commands and warnings, significantly inflating token count. |
| actionability | ███ 3/3 | The skill provides fully executable, copy-paste-ready commands throughout — installation, startup, browser interaction, debugging, and error recovery. Commands include specific flags and realistic examples with ports, URLs, and timeouts. |
| workflow clarity | ███ 3/3 | The bootstrap workflow is clearly numbered with explicit validation steps (checking d3k installation, verifying server with curl before opening browser). The non-auth fresh browser workflow includes cleanup of stale state, server verification, and sanity-check steps. Error recovery paths are specified (restart d3k cleanly, close stale daemons). |
| progressive disclosure | ██░ 2/3 | The content is a monolithic wall of text with no references to external files despite being over 150 lines. The non-auth fresh browser workflow, browser tool choice guide, and artifact paths could be split into separate reference files. However, sections are reasonably well-labeled with headers. |
Overall: The skill provides excellent actionability with concrete, executable commands and clear multi-step workflows with validation checkpoints. However, it suffers significantly from redundancy — the same guidance about browser ownership and auth-sensitive flows is repeated across at least three sections, roughly doubling the token cost. The content would benefit from deduplication and splitting detailed workflows into referenced files.
Suggestions:
- Consolidate the repeated browser-ownership/auth guidance into a single authoritative section and reference it from other sections instead of restating it (the 'Auth-Sensitive Browser Rule', 'Required Browser/Session Default', and parts of 'Bootstrap Workflow' all say the same thing).
- Remove the 'Why d3k-first' section — Claude doesn't need motivation for following instructions; the behavioral rules alone are sufficient.
- Extract the 'Non-Auth Fresh Browser/Profile Startup' and 'Browser Tool Choice' sections into separate referenced files (e.g., FRESH_PROFILE.md, BROWSER_TOOLS.md) to reduce the main skill's token footprint and improve progressive disclosure.
- Remove redundant command blocks that appear in multiple sections (e.g., the agent-browser snapshot/click/errors sequence appears at least three times).
plugins/dev3000/agent/skills/d3k/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/docus/agent/skills/create-docs/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/docus/agent/skills/review-docs/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/apple/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/aws/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/emulate/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/github/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/google/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/linear/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/microsoft/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/next/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/resend/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/slack/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/stripe/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/emulate/agent/skills/vercel/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
plugins/eve/agent/skills/eve/SKILL.md
⚠️ Error: - Reviewing skill...
✘ Skill validation failed
To improve your score, point your agent at the Tessl optimization guide. Need help? Jump on our Discord.
Feedback
Report issues with this review at tesslio/skill-review, or send private feedback from your terminal with tessl feedback.
|
Warning Review the following alerts detected in dependencies. According to your organization's Security Policy, it is recommended to resolve "Warn" alerts. Learn more about Socket for GitHub.
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Not up to standards ⛔🔴 Issues
|
| Category | Results |
|---|---|
| BestPractice | 5 high |
| ErrorProne | 23 high |
| Security | 20 minor 19 high 1 critical 32 medium |
🟢 Metrics 41959 complexity · 5594 duplication
Metric Results Complexity 41959 Duplication 5594
NEW Get contextual insights on your PRs based on Codacy's metrics, along with PR and Jira context, without leaving GitHub. Enable AI reviewer
TIP This summary will be updated as you push new changes.
|



Automated refresh of vendored skills.sh skills to their latest upstream versions.
Updated lock directories:
plugins/chat-sdkplugins/dev3000plugins/eveplugins/lavishplugins/nextplugins/nosticsplugins/reactplugins/skill-optimizerplugins/slack-agentplugins/vercel-sandboxplugins/vinextplugins/web-designplugins/workflow-sdkGenerated by
.github/workflows/update-skills.yml→scripts/update-skills.ts.