CtrlK
BlogDocsLog inGet started
Tessl Logo

stream-react-native

Use when creating, building, or integrating Stream Chat, Stream Video, or Stream Feeds in React Native Community CLI or Expo apps - new RN/Expo Chat / Video / Feeds apps from scratch, existing-app integration, stream-chat-react-native, stream-chat-expo, @stream-io/video-react-native-sdk, @stream-io/feeds-react-native-sdk, useCreateFeedsClient, StreamFeeds, StreamFeed, activity feed, timeline feed, notification feed, for-you feed, useFeedActivities, useActivityComments, reactions, comments, follows, migration/setup, channel list, message list, MessageComposer, attachment picker, image/file attachments, media picker, audio messages, threads, thread list, video call, livestream, audio room, ringing, CallContent, ParticipantView, React Navigation, Expo Router, theming, offline support, push notifications, and Chat / Video / Feeds UI customization. Not for Moderation review UI.

71

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable router with a clear mandatory workflow and verification checkpoints, but it is held back by repeated reference enumeration and, more importantly, by routing its core execution tracks to module files (RULES.md, builder.md, sdk.md, credentials.md) that are not present in the bundle.

Suggestions

Bundle (or inline the essential parts of) the missing core modules RULES.md, builder.md, sdk.md, and credentials.md so the Track A/B/D navigation targets actually resolve; this directly lifts progressive_disclosure.

De-duplicate the reference-file list: it appears in the product-classifier table, the Reference layout section, and the Track C list — consolidate to a single canonical listing referenced by the other sections.

Trim the nine one-line Project-signals status examples to the three or four most representative cases to tighten conciseness without losing the pattern.

DimensionReasoningScore

Conciseness

The body mostly avoids explaining concepts Claude already knows and leans on tables, but the six reference files are enumerated three times (product-classifier table, Reference layout, Track C list) and the nine one-line status examples could be condensed; this matches the mostly-efficient-but-could-be-tightened anchor rather than the every-token-earns-its-place level 3.

2 / 3

Actionability

Provides a fully executable, copy-paste bash probe (Project signals), exact package-to-product mappings (e.g. Feeds: "@stream-io/feeds-react-native-sdk + @react-native-community/netinfo"), and concrete wiring steps ("add Reanimated/Worklets Babel plugin as the last plugin, wrap the entry point with GestureHandlerRootView, place OverlayProvider and Chat"), meeting the executable-commands anchor; it is not level 2 because the guidance is specific and runnable rather than pseudocode or vague direction.

3 / 3

Workflow Clarity

Clear mandatory sequence (Step 0 "mandatory first - never skip" -> Step 0.5 credentials -> Project signals -> Tracks A/B/C/D with A1-A5 and B1-B4 phase tables) plus explicit verification checkpoints (A5/B4 Verify, "Do not render a connected ... UI until credentials or a token-provider plan are resolved") and ask-and-wait feedback loops, matching the clear-sequence-with-validation anchor.

3 / 3

Progressive Disclosure

The design is well-signaled and one-level-deep, and all references/*.md paths (Chat/Video/Feeds setup + blueprints + DOCS) resolve to real bundle files, but the core execution modules the overview names as primary destinations — RULES.md, builder.md, sdk.md, and credentials.md — are absent from the actual bundle, so promised navigation breaks for tracks A/B/D; against the actual bundle structure this is the references-present-but-incomplete anchor rather than a clean level 3.

2 / 3

Total

10

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a strong, explicit trigger-rich statement that clearly defines both what the skill does and when to use it, with concrete capabilities and a distinct Stream React Native niche reinforced by negative scope. It fully meets the top anchor on all four dimensions.

DimensionReasoningScore

Specificity

Lists many concrete actions and capability areas — "creating, building, or integrating", "new RN/Expo Chat / Video / Feeds apps from scratch", "migration/setup", "channel list, message list, MessageComposer, attachment picker ... theming, offline support, push notifications, and Chat / Video / Feeds UI customization" — matching the score-3 anchor of multiple specific concrete actions, far beyond merely naming a domain.

3 / 3

Completeness

Opens with an explicit "Use when creating, building, or integrating ..." trigger (the when) and states the what (creating/building/integrating Stream Chat/Video/Feeds in RN CLI or Expo apps plus UI customization), satisfying the score-3 anchor of clearly answering both what AND when with explicit triggers; the present "Use when" clause avoids the cap at 2.

3 / 3

Trigger Term Quality

Strong coverage of natural terms a user would say — "Stream Chat", "Stream Video", "Stream Feeds", "React Native", "Expo", "video call", "livestream", "audio room", "channel list", "message list", "threads", "push notifications" — alongside SDK package names; matches the good-coverage anchor. It is not level 2 because common natural variations are well represented, not just a few relevant keywords.

3 / 3

Distinctiveness Conflict Risk

Highly specific niche anchored by distinct package names (stream-chat-react-native, @stream-io/video-react-native-sdk, @stream-io/feeds-react-native-sdk) and explicit negative scope ("Not for Moderation review UI"), making conflict with other skills unlikely per the clear-niche anchor.

3 / 3

Total

12

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 18 missing

Warning

Total

13

/

16

Passed

Repository
GetStream/agent-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.