Messages Ops
affaan-m/ECC
Evidence-first live messaging workflow for ECC. An agent skill from affaan-m/ECC.
Verify server message endpoint context, endpoint type narrowing, plugin forwarding order, command observable emission, and Matter 1.6.0 comments on validation and state updates.
$ npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Luligu/matterbridge verify-server-endpoint-context --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Luligu/matterbridge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/verify-server-endpoint-context .claude/skills/verify-server-endpoint-context && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "verify-server-endpoint-context" agent skill from https://github.com/Luligu/matterbridge/tree/main/.agents/skills/verify-server-endpoint-context into .claude/skills/verify-server-endpoint-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-server-endpoint-context", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Luligu/matterbridge/tree/main/.agents/skills/verify-server-endpoint-contextType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Luligu/matterbridge verify-server-endpoint-context --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Luligu/matterbridge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/verify-server-endpoint-context .agents/skills/verify-server-endpoint-context && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "verify-server-endpoint-context" agent skill from https://github.com/Luligu/matterbridge/tree/main/.agents/skills/verify-server-endpoint-context into .agents/skills/verify-server-endpoint-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-server-endpoint-context", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Luligu/matterbridge verify-server-endpoint-context --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Luligu/matterbridge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/verify-server-endpoint-context .cursor/skills/verify-server-endpoint-context && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "verify-server-endpoint-context" agent skill from https://github.com/Luligu/matterbridge/tree/main/.agents/skills/verify-server-endpoint-context into .cursor/skills/verify-server-endpoint-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-server-endpoint-context", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Luligu/matterbridge.git --path .agents/skills/verify-server-endpoint-context--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Luligu/matterbridge verify-server-endpoint-context --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Luligu/matterbridge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/verify-server-endpoint-context .gemini/skills/verify-server-endpoint-context && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "verify-server-endpoint-context" agent skill from https://github.com/Luligu/matterbridge/tree/main/.agents/skills/verify-server-endpoint-context into .gemini/skills/verify-server-endpoint-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-server-endpoint-context", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Luligu/matterbridge verify-server-endpoint-contextInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Luligu/matterbridge.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/verify-server-endpoint-context .github/skills/verify-server-endpoint-context && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "verify-server-endpoint-context" agent skill from https://github.com/Luligu/matterbridge/tree/main/.agents/skills/verify-server-endpoint-context into .github/skills/verify-server-endpoint-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-server-endpoint-context", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Luligu/matterbridge verify-server-endpoint-context --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Luligu/matterbridge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/verify-server-endpoint-context .opencode/skills/verify-server-endpoint-context && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "verify-server-endpoint-context" agent skill from https://github.com/Luligu/matterbridge/tree/main/.agents/skills/verify-server-endpoint-context into .opencode/skills/verify-server-endpoint-context/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verify-server-endpoint-context", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
verify-server-endpoint-contextVerify server message endpoint context, endpoint type narrowing, plugin forwarding order, command observable emission, and Matter 1.6.0 comments on validation and state updates.
Verify Server Endpoint Context is an agent skill from Luligu/matterbridge. Verify server message endpoint context, endpoint type narrowing, plugin forwarding order, command observable emission, and Matter 1.6.0 comments on validation and state updates. v.1.1.4
Its SKILL.md is about 5.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Matterbridge plugin manager for Matter. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 857fd9b. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
npmFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Verify Server Endpoint Context loads about 5.1k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 2,134 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Luligu/matterbridge at commit 857fd9b, republished under its Apache-2.0 licence (© Luligu). 2,134 words, ~5,051 tokens.
.claude/skills/verify-server-endpoint-context/SKILL.md (or your agent's skills folder).Verify endpoint context in Matterbridge behavior server implementations.
Scope:
Checks:
Verify every textual log and throw message in scope starts with the exact name of its enclosing server class, optionally followed by a dot and the exact name of the enclosing command handler or method, then a colon and one space, and that the first letter of the text immediately following that prefix is lowercase. For example:
MatterbridgeBooleanStateConfigurationServer: requested;The optional method segment is intended for clusters whose handlers emit similar messages about the same subject, where the bare class name alone does not identify which command produced the line. For example:
MatterbridgeWebRtcTransportProviderServer.provideOffer: received;Verify every textual log and throw message in scope ends with this exact fragment:
(endpoint ${this.endpoint.maybeId}.${this.endpoint.maybeNumber})Treat calls to every log level as logs, including debug, info, notice, warn, error, and fatal, whether the logger is accessed through device.log, this.state.log, this.log, or another local reference.
Verify every error message created by a throw statement in scope follows the same prefix and suffix rules, including errors constructed directly in the throw and errors assigned to a variable before being thrown.
Follow local variables and simple helper methods when needed so multiline calls, template literals, and indirectly constructed error messages are not missed.
Do not accept a missing or abbreviated server name, text before the server name, a prefix that does not match the enclosing server class name exactly, a method segment that does not match the enclosing method name exactly, a method segment not separated from the server name by a single dot, a prefix whose colon and space separator is missing so the prefix runs into the message text, or an uppercase first letter immediately after the prefix's colon and space (for example MatterbridgeEnergyEvseServer: Disable charging is a violation; MatterbridgeEnergyEvseServer: disable charging is compliant, and MatterbridgeWebRtcTransportProviderServer.solicitOffer requires at least one stream is a violation because it has no colon and space separator; MatterbridgeWebRtcTransportProviderServer.solicitOffer: requires at least one stream is compliant).
Do not accept alternate endpoint formats, missing parentheses, a colon separator, endpoint.id, endpoint.number, messages containing only one endpoint component, or any text after the endpoint fragment's closing parenthesis.
Accept (endpoint ${endpointLabel}) only in a log written from a deferred callback (a timer, an un-awaited promise or similar) that can run after the command's behavior context has exited, where endpointLabel is a local const endpointLabel = \${this.endpoint.maybeId}.${this.endpoint.maybeNumber}`` captured synchronously before the deferral, with a comment explaining why. Report a label used in a synchronous log, a label built any other way, or a captured label without that comment as a violation.
Do not require the fragment in a log or thrown value that has no textual message, but report that case separately for manual review.
Ignore comments, JSDoc examples, tests, generated output, and imported server implementations.
Endpoint type narrowing:
Verify every server class in scope narrows the inherited endpoint getter once, as the first member of the class body, instead of asserting the type at each use:
/** The endpoint that owns this behavior. Narrowed to MatterbridgeEndpoint: this server is only ever added to a Matterbridge endpoint. */
declare readonly endpoint: MatterbridgeEndpoint;Behavior.endpoint is a getter returning Endpoint<EndpointType.Empty> and MatterbridgeEndpoint is a subtype of it, so the narrowing is accepted. declare emits no runtime code, so the inherited getter is untouched and the declaration is purely a type-level assertion.
Verify MatterbridgeEndpoint is imported as a type-only import, for example import type { MatterbridgeEndpoint } from '../matterbridgeEndpoint.js'. A value import creates an import cycle for every behavior that matterbridgeEndpointHelpers.ts imports.
Verify no this.endpoint as MatterbridgeEndpoint assertion remains in scope, including the endpoint property of the device.commandHandler.executeHandler(...) payload.
Verify a file-level /* oxlint-disable typescript/no-unsafe-type-assertion */ suppression is removed once the file contains no remaining type assertion. Keep it only when an unrelated assertion still requires it.
Report a missing declaration, a remaining as MatterbridgeEndpoint assertion, a value import of MatterbridgeEndpoint, or an obsolete assertion suppression as an endpoint type narrowing violation.
Plugin forwarding contract:
device.commandHandler.executeHandler(...) occurs immediately after the command-entry log.const device = this.endpoint.stateOf(MatterbridgeServer), followed by the command-entry log.info level, for example device.log.info(...). A command-entry log at debug, notice, warn, error, fatal, or any other level is not compliant.info. Logs outside the command-entry position may use any appropriate log level, but their messages must still satisfy the server-name prefix and endpoint suffix rules.info, missing forwarding call, non-awaited forwarding call, or any disallowed operation before forwarding completes as a plugin forwarding contract violation.CommandHandlers type of matterbridgeEndpointCommandHandler.ts, currently Chime, Camera AV Stream Management, Camera AV Settings User Level Management, WebRTC Transport Provider and WebRTC Transport Requestor. They reach the plugin only through the command observable, after validation, so they have no executeHandler(...) call; they must still log, validate and emit the command observable as required by the other sections. Do not report the missing forwarding call for these servers, and recheck the CommandHandlers type before applying the exemption to any other server.Command observable emission:
Verify every overridden Matter command handler in scope emits the command observable added by subscribeCommand() as the very last call of the handler:
this.endpoint.emitCommand(OnOff, 'offWithEffect', request, this.context);Pass the cluster as the ClusterType exported by @matter/types/clusters/<cluster>, for example OnOff or BooleanStateConfiguration. Do not accept <Cluster>.Cluster, a behavior type, a behavior id such as OnOffServer.id, or a cluster name string: the ClusterType form keeps the command name and the request payload checked against the cluster definition.
Pass the exact command name of the enclosing handler, the request payload, and this.context. Use {} as the payload for commands that take no request.
Verify the call goes through the narrowed this.endpoint. Do not accept the emitCommand helper imported from matterbridgeEndpointHelpers.ts in a behavior that module imports, because the value import closes an import cycle.
Verify the emission comes after the awaited plugin forwarding, after every validation, and after every state update, including after the await super.<command>() call when the handler delegates to the base implementation. No statement may follow it, except a final return of the command response in handlers that return one.
That return may only hand back the response: an object literal, or a value already computed before the emission, such as const response = await super.<command>(request); returned after emitting. It must not call methods, read or change state, log, or have any other side effect. Do not accept a try/finally block used only to defer the emission past the return; emit first, then return.
this.state.currentMode = request.newMode;
this.endpoint.emitCommand(OvenMode, 'changeToMode', request, this.context);
return { status: ModeBase.ModeChangeStatus.Success, statusText: 'Success' };Do not require an emission on a path that rejects the command with a Matter status error, discards it by cluster conformance, or returns early, for example the MATTERBRIDGE_CHIP_TEST branch that gates the plugin forwarder off. The observable reports commands that completed.
Report a missing emission, an emission that is not the last call (a final side-effect-free return of the command response is allowed), an emission placed before validation or state updates, a cluster passed in any form other than the ClusterType, a command name that does not match the enclosing handler, a missing this.context, or a direct helper import as a command observable emission violation.
Matter specification comments:
Verify every validation branch or guard and every state update that enforces Matter behavior has an immediately preceding single-line comment in this form:
// Matter 1.6.0 § <paragraph>: <short description of the normative rule enforced by this code>.Use the applicable paragraph from the authoritative Matter 1.6.0 specifications under chip/1.6.0/specs. Do not guess a paragraph number or copy a reference from unrelated code.
Read only the Markdown specifications (Matter-1.6-*-Specification.md, mainly Matter-1.6-Application-Cluster-Specification.md). Never open the .html, .pdf or _files copies. Locate a section with grep -n on its heading, for example grep -n '^#\+ 1\.5\.7\.4\.3\. ' chip/1.6.0/specs/Matter-1.6-Application-Cluster-Specification.md or grep -n '^#\+ .*Effect on Receipt' ..., then read only the lines of that section instead of the whole file.
Keep each comment concise and specific to the validation or state update immediately below it. State the observable requirement, including the required status code for validation failures when the specification defines one.
Add separate comments when adjacent state assignments enforce different normative requirements. Do not use one generic comment to cover multiple assignments with distinct effects.
Place validation and state-update comments both where the rule is implemented and immediately before each call to a helper that performs the validation or state update. At each call site, use the paragraph for that specific command rather than a combined reference covering other callers.
Accept a combined paragraph reference only when the same validation or state update implements the same rule for multiple commands, for example § 1.8.7.1.2 and § 1.8.7.2.2.
Do not accept method-level JSDoc, a distant block comment, a bare paragraph number, a comment without Matter 1.6.0, or a comment that describes implementation mechanics without explaining the specification rule.
Report a missing, misplaced, inaccurate, or incomplete specification comment as a Matter specification comment violation.
Compliant example from onOffServer.ts, showing the narrowed endpoint, the forwarding order and the trailing emission:
export class MatterbridgeOnOffServer extends OnOffServer.with(OnOff.Feature.Lighting) {
/** The endpoint that owns this behavior. Narrowed to MatterbridgeEndpoint: this server is only ever added to a Matterbridge endpoint. */
declare readonly endpoint: MatterbridgeEndpoint;
override async offWithEffect(request: OnOff.OffWithEffectRequest): Promise<void> {
const device = this.endpoint.stateOf(MatterbridgeServer);
device.log.info(
`MatterbridgeOnOffServer: switching device off with effect ${request.effectIdentifier} and variant ${request.effectVariant} (endpoint ${this.endpoint.maybeId}.${this.endpoint.maybeNumber})`,
);
await device.commandHandler.executeHandler('OnOff.offWithEffect', {
command: 'offWithEffect',
request,
cluster: OnOffServer.id,
attributes: this.state,
endpoint: this.endpoint,
context: this.context,
});
device.log.debug(`MatterbridgeOnOffServer: offWithEffect called (endpoint ${this.endpoint.maybeId}.${this.endpoint.maybeNumber})`);
// Matter 1.6.0 § 1.5.7.4.3: On receipt of OffWithEffect, when GlobalSceneControl is TRUE the server SHALL store its settings in the global scene, set GlobalSceneControl to FALSE, set OnOff to FALSE and OnTime to 0; otherwise it SHALL only set OnOff to FALSE.
await super.offWithEffect(request);
this.endpoint.emitCommand(OnOff, 'offWithEffect', request, this.context);
}
}Compliant validation and state update shape, adapted from booleanStateConfigurationServer.ts:
// Matter 1.6.0 § 1.8.7.1.2 and § 1.8.7.2.2: Reject the command with CONSTRAINT_ERROR if any requested alarm mode is unsupported.
if ([Boolean(alarms.visual && !this.state.alarmsSupported.visual), Boolean(alarms.audible && !this.state.alarmsSupported.audible)].some(Boolean)) {
throw new StatusResponseError(
`MatterbridgeBooleanStateConfigurationServer: requested alarm mode is not supported (endpoint ${this.endpoint.maybeId}.${this.endpoint.maybeNumber})`,
Status.ConstraintError,
);
}
override async suppressAlarm(request: BooleanStateConfiguration.SuppressAlarmRequest): Promise<void> {
const device = this.endpoint.stateOf(MatterbridgeServer);
device.log.info(
`MatterbridgeBooleanStateConfigurationServer: suppressing alarm ${debugStringify(request.alarmsToSuppress)}${nf} (endpoint ${this.endpoint.maybeId}.${this.endpoint.maybeNumber})`,
);
await device.commandHandler.executeHandler('BooleanStateConfiguration.suppressAlarm', {
command: 'suppressAlarm',
request,
cluster: BooleanStateConfigurationServer.id,
attributes: this.state as unknown as ClusterAttributeValues<(typeof BooleanStateConfiguration)['attributes']>,
endpoint: this.endpoint,
context: this.context,
});
// Matter 1.6.0 § 1.8.7.1.2: Reject the command with CONSTRAINT_ERROR if any requested alarm mode is unsupported.
this.#assertAlarmModesSupported(request.alarmsToSuppress);
// Matter 1.6.0 § 1.8.7.1.2: Reject suppression with INVALID_IN_STATE if a requested alarm mode is inactive or disabled.
this.#assertSuppressAlarmAllowed(request.alarmsToSuppress);
// Matter 1.6.0 § 1.8.7.1.2: Set each valid requested mode in AlarmsSuppressed while preserving modes already suppressed.
this.state.alarmsSuppressed = this.#mergeAlarmsSuppressed(request.alarmsToSuppress);
this.endpoint.emitCommand(BooleanStateConfiguration, 'suppressAlarm', request, this.context);
}Output requirements:
as MatterbridgeEndpoint assertion remains, the import is not type-only, or an assertion suppression is now obsolete.behaviors and devices.endpoint with the declare declaration and contains no as MatterbridgeEndpoint assertion, every command handler respects the plugin forwarding contract, every command handler emits its command observable as its last call using the ClusterType, and every Matter validation and state update has an accurate Matter 1.6.0 paragraph comment.: , append the exact endpoint fragment as the final message content, move awaited plugin forwarding before validation and state changes, add the declare readonly endpoint: MatterbridgeEndpoint; declaration and remove every as MatterbridgeEndpoint assertion and any assertion suppression it makes obsolete, add or move the this.endpoint.emitCommand(<ClusterType>, '<command>', <request>, this.context) call to the end of each command handler, add or correct concise Matter 1.6.0 paragraph comments immediately before validations and state updates, then re-run the full verification and report any remaining violations.Post-edit validation:
npm run format, npm run build, and npm run lint from the repository root.npm run test for the full test suite or npm run test -- <testfile> for a single relevant test file.© Luligu, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in .agents/skills/verify-server-endpoint-context of Luligu/matterbridge.
Open the folder on GitHubat commit 857fd9b
Verify Server Endpoint Context next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Verify Server Endpoint Context this skillLuligu/matterbridge | 983 | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | |
| Messages Opsaffaan-m/ECC | 275k | 1 repos | ~724 | Automated safety check: Pass | MIT | |
| Channel Message Flowsopenclaw/openclaw | 392k | 1 repos | ~306 | Automated safety check: Pass | MIT | |
| Commit Message Storytellergithub/awesome-copilot | 40k | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Exploring Endpoint Execution LogsPostHog/posthog | 40k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Agent Messagingdavila7/claude-code-templates | 32k | — | ~807 | Automated safety check: Pass | MIT |
affaan-m/ECC
Evidence-first live messaging workflow for ECC. An agent skill from affaan-m/ECC.
openclaw/openclaw
A skill your agent uses when running QA Lab channel message flow evidence.
github/awesome-copilot
Analyzes git diffs or staged changes and generates narrative commit messages that explain WHY a change was made, not just what changed — following Conventional Commits format.
PostHog/posthog
Explore and diagnose a PostHog endpoint's execution logs — error messages, failed runs, cache misses, slow runs, or unexpected row counts during endpoint invocations.
davila7/claude-code-templates
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP).
github/gh-aw
Add new safe-output message types and wire validation/rendering.
Luligu/matterbridge
Sync the matter.js fork, implement and test a fix or a new feature/enhancement, format, lint, commit, push, and open a PR against matter-js/matter.js.
Luligu/matterbridge
Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/.
Luligu/matterbridge
Verify that matterbridge and all Matterbridge workspace packages are aligned on the npm latest and dev tags.
Luligu/matterbridge
Verify that package, Docker build, test utility helper, docs update JSON files, and Docker workflow tags match the expected root version rules.
Luligu/matterbridge
Verify which coding agent is running and that it loaded the shared Matterbridge instructions, rules and skills from AGENTS.md and .agents/.
Verify server message endpoint context, endpoint type narrowing, plugin forwarding order, command observable emission, and Matter 1.6.0 comments on validation and state updates. Verify Server Endpoint Context is an agent skill from Luligu/matterbridge.0 comments on validation and state updates.
Run `npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a claude-code`. Or copy the skill folder (.agents/skills/verify-server-endpoint-context in Luligu/matterbridge) into .claude/skills/verify-server-endpoint-context in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a codex`. Or copy the skill folder (.agents/skills/verify-server-endpoint-context in Luligu/matterbridge) into .agents/skills/verify-server-endpoint-context in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Luligu/matterbridge --skill verify-server-endpoint-context -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verify-server-endpoint-context, .gemini/skills/verify-server-endpoint-context, .github/skills/verify-server-endpoint-context and .opencode/skills/verify-server-endpoint-context in your project.
Going by SKILL.md and its folder, Verify Server Endpoint Context needs the command-line tools its instructions call (npm).
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Verify Server Endpoint Context is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.1k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Verify Server Endpoint Context: Messages Ops (affaan-m/ECC, 275k stars), Channel Message Flows (openclaw/openclaw, 392k stars), Commit Message Storyteller (github/awesome-copilot, 40k stars) and Exploring Endpoint Execution Logs (PostHog/posthog, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Luligu (a GitHub user) maintains it in Luligu/matterbridge, which has 983 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on October 7, 2026.
Source: Luligu/matterbridge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.