New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Convex Insights

by openclaw in openclaw/clawhub

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

MITAuto-check passedMobile

Install Convex Insights

skills CLI
$ npx skills add openclaw/clawhub --skill convex-insights -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install openclaw/clawhub convex-insights --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/openclaw/clawhub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/convex-insights .claude/skills/convex-insights && rm -rf skills-src

Use ~/.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/

Facts

Skill name
convex-insights
GitHub stars
9.5k
Used in
1 other repo
Token cost
~1.1k tokens
SKILL.md length
593 words
Files
1
Skills in repo
55
Repo updated
First seen
Licence
MIT

At a glance

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

  • Works in 7 steps: GUARD: deploy-guard step 0-1 — identify… → DISCOVER before you query — never guess… → PICK ONE OF THREE VIEWS and fetch the… → …
  • Mobile work in your project
  • SKILL.md covers Workflow and Rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Convex Insights is an agent skill from openclaw/clawhub. Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Mobile. It works with Model Context Protocol. The repository describes itself as: Skill + Plugin Registry for OpenClaw. The licence is MIT.

When your agent uses it

  • Mobile work in your project

Example prompts

  • “/convex-insights”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. GUARD: deploy-guard step 0-1 — identify + announce which deployment is being read. Reading logs/insights is read-only; never enable prod…
  2. DISCOVER before you query — never guess identifiers. Use functionSpec to list the real function names and status for the…
  3. PICK ONE OF THREE VIEWS and fetch the raw window, then filter locally
  4. SCOPE by fetching a bounded recent window (a sensible --history count) and filtering client-side to the function/status/requestId asked…
  5. ANSWER with (a) the one-line finding, (b) the evidence (counts + one representative stack/log line), and (c) WHEN POSSIBLE an…
  6. CROSS-CHECK deploy causality when asked 'did my deploy break this': compare the failure onset (from the log timestamps) against the…
  7. HAND OFF, don't fix here: a perf/cost cause → convex-advisor (which owns those fixes); a code defect → convex-reviewer/convex-authz; a…

What it can do on your machine

Read from SKILL.md and the folder at commit d044664. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Convex Insights loads about 1.1k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 593 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from openclaw/clawhub at commit d044664, republished under its MIT licence (© openclaw). 593 words, ~1,131 tokens.

Download SKILL.mdSave it as .claude/skills/convex-insights/SKILL.md (or your agent's skills folder).
name
convex-insights
description
Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.
<!-- GENERATED from convex-agents content/capabilities/convex-insights.json — do not edit by hand. -->

Query logs + health in natural language

The deployment already records what happened; the agent just has to ask well. This capability is a disciplined wrapper over the official Convex MCP's read tools (logs, insights, functionSpec, status) that turns operational questions into narrow, evidence-returning queries and hands back answers a human can one-click verify in the dashboard. The discipline is copied from the observability MCP surface that works best in the wild: discover fields before querying, three views not fifteen tools, token-frugal output, and a dashboard deep link on every answer.

Workflow

  1. GUARD: deploy-guard step 0-1 — identify + announce which deployment is being read. Reading logs/insights is read-only; never enable prod mutation flags for an insights pass.
  2. DISCOVER before you query — never guess identifiers. Use functionSpec to list the real function names and status for the deployment/version. Note the tool limits up front: logs takes only --history <n> (a COUNT, not a time window), --success, --jsonl, --prod, --deployment — there is NO server-side status/function/requestId/time filter; insights has no function filter and is cloud dev/prod + user-auth only. So you fetch a recent window and filter CLIENT-SIDE.
  3. PICK ONE OF THREE VIEWS and fetch the raw window, then filter locally:
    • failures view → logs --history <n> --jsonl, then locally keep failures + group by function + error message, returning counts + the first stack per group. Answers 'what's erroring', 'what failed after deploy'.
    • health view → insights (cloud only): the typed 72h read-limit / OCC events. Surface + rank them, but hand perf/cost ROOT-CAUSING and fixes to convex-advisor — emit those as pointer findings, do not own the perf-fix framing here.
    • trace view → logs --history <n> --jsonl then locally filter to one requestId/function to read the full execution. Answers 'why did THIS call fail'.
  4. SCOPE by fetching a bounded recent window (a sensible --history count) and filtering client-side to the function/status/requestId asked about; when the window is large, aggregate (counts by function/message) rather than dumping lines.
  5. ANSWER with (a) the one-line finding, (b) the evidence (counts + one representative stack/log line), and (c) WHEN POSSIBLE an agent-constructed dashboard deep link (dashboard.convex.dev, the deployment's Logs/Functions view) for human verification — no tool returns the link, so build it from the deployment name + function; never a raw log dump as the answer.
  6. CROSS-CHECK deploy causality when asked 'did my deploy break this': compare the failure onset (from the log timestamps) against the deployment version from status; correlate, don't assert.
  7. HAND OFF, don't fix here: a perf/cost cause → convex-advisor (which owns those fixes); a code defect → convex-reviewer/convex-authz; a live error to react to going forward → monitor/sentinel. Emit findings on the bus (specs/finding.schema.json) — primarily observability, with perf/cost as pointer findings to advisor — so a composite pass can pick them up.
Show full SKILL.md (145 more words)Show less

Rules

  • Discover real function/field names (functionSpec/status) before filtering — never guess identifiers, never return a confusing empty result for a name the app doesn't have.
  • logs and insights have NO server-side status/function/requestId/time-window filter (logs takes only a --history COUNT; insights is cloud-only) — fetch a bounded recent window and filter CLIENT-SIDE; say so rather than implying params that don't exist.
  • One of three views per question (failures / health / trace) — don't fan out into many speculative tool calls.
  • No tool returns a dashboard link — construct it from the deployment name + function when possible for human verification; never answer with a raw log dump.
  • Read-only always: an insights pass runs no mutation and never enables prod mutation flags (deploy-guard discipline).
  • Stay a reader and defer perf/cost fixes to convex-advisor: emit primarily observability, route perf/cost as POINTER findings so advisor uniquely owns the perf-fix framing; forward-looking reaction goes to monitor/sentinel.

© openclaw, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/convex-insights of openclaw/clawhub.

Open the folder on GitHubat commit d044664

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in openclaw/clawhub, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Convex Insights 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.

Convex Insights compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Convex Insights this skillopenclaw/clawhub9.5k1 repos~1.1kAutomated safety check: PassMIT
Marionette Flutter Drive Appleancodepl/marionette_mcp482—~11kAutomated safety check: PassApache-2.0
Deep Linksstacklok/toolhive-studio170—~1.6kAutomated safety check: NotesApache-2.0
Asc Aso AuditCamilleScholtz/swmpc2395 repos~2.6kAutomated safety check: PassEUPL-1.2
Use Appclaw Agent CLIappclawhq/AppClaw116—~775Automated safety check: PassApache-2.0
Maui Devflow Uitestsnalu-development/nalu245—~2.3kAutomated safety check: PassCustom licence

Similar skills

  • Marionette Flutter Drive App

    leancodepl/marionette_mcp

    Set up and drive a running Flutter app (debug or profile) with Marionette — an AI agent's hands and eyes for the app.

    482 GitHub stars~11k tokensUpdated 4 days ago
    MobileAuto-check passed

  • Deep Links

    stacklok/toolhive-studio

    Deep links in ToolHive Studio. An agent skill from stacklok/toolhive-studio.

    170 GitHub stars~1.6k tokensUpdated today
    MobileAuto-check: notes

  • Asc Aso Audit

    CamilleScholtz/swmpc

    Run an offline ASO audit on canonical App Store metadata under ./Store and surface keyword gaps using Astro MCP.

    239 GitHub starsUsed in 5 repos~2.6k tokens
    MobileAuto-check passed

  • Use Appclaw Agent CLI

    appclawhq/AppClaw

    Use the appclaw-agent CLI to directly open, inspect, and interact with a mobile app via terminal commands — without writing a YAML flow.

    116 GitHub stars~775 tokensUpdated 1 mo ago
    MobileAuto-check passed

  • Maui Devflow Uitests

    nalu-development/nalu

    How to write, run and debug automated UI tests for the Nalu.Maui component libraries using .NET MAUI DevFlow (in-app agent + Driver + CLI + MCP).

    245 GitHub stars~2.3k tokensUpdated 4 days ago
    MobileAuto-check passed

  • Add Theme Icons

    r0adkll/Campfire

    Add new AppTheme.Icon entries by pulling Icons8 icons (Arcade style by default) and converting them to Compose ImageVectors via the Valkyrie CLI.

    140 GitHub stars~1.2k tokensUpdated yesterday
    MobileAuto-check passed

More from openclaw/clawhub

All 55 skills in this repo

  • Axiom Alerting Management

    openclaw/clawhub

    Creates and manages Axiom monitors and notifiers end to end through the v2 API, with scripts for each CRUD operation and a recommended create-validate-tune workflow.

    9.5k GitHub stars~2.1k tokensUpdated yesterday
    Auto-check passed

  • Axiom Dashboard Builder

    openclaw/clawhub

    Designs and deploys Axiom dashboards through the API, choosing chart types and writing APL or metrics queries, with templates and migration notes for Splunk and Grafana.

    9.5k GitHub stars~4.9k tokensUpdated yesterday
    Auto-check passed

  • Axiom Cost Control

    openclaw/clawhub

    Finds unused data in Axiom by analyzing query patterns, then deploys a cost dashboard and ingest monitors to keep spend under the contract limit.

    9.5k GitHub stars~1.7k tokensUpdated yesterday
    Auto-check passed

  • Axiom Metrics Query

    openclaw/clawhub

    Explores and queries OpenTelemetry metrics in Axiom MetricsDB, listing datasets, metrics and tags first and picking the right aggregation for each metric's type.

    9.5k GitHub stars~2.6k tokensUpdated yesterday
    Auto-check passed

  • Axiom SRE Investigator

    openclaw/clawhub

    Investigates incidents and production problems with hypothesis-driven debugging, queries Axiom observability data when available, and keeps secrets out of commands and output.

    9.5k GitHub stars~7.1k tokensUpdated yesterday
    Auto-check passed

  • Axiom Eval Writer

    openclaw/clawhub

    Scaffolds evaluation suites for the Axiom AI SDK: eval files, scorers, flag schemas and axiom.config.ts, generated from plain descriptions of an AI capability.

    9.5k GitHub stars~4.1k tokensUpdated yesterday
    Auto-check: warnings

Works with

Categories

Questions about Convex Insights

What does Convex Insights do?

Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link. Convex Insights is an agent skill from openclaw/clawhub. Query a running Convex app's logs + health in natural language (official MCP): failures, slow/expensive functions, deploy causality — scoped, evidence-backed, with a dashboard deep link.

When should I use Convex Insights?

Convex Insights fits situations like: mobile work in your project.

How do I install Convex Insights in Claude Code?

Run `npx skills add openclaw/clawhub --skill convex-insights -a claude-code`. Or copy the skill folder (.agents/skills/convex-insights in openclaw/clawhub) into .claude/skills/convex-insights in your project. Claude Code loads it when a task matches its description.

How do I install Convex Insights in Codex?

Run `npx skills add openclaw/clawhub --skill convex-insights -a codex`. Or copy the skill folder (.agents/skills/convex-insights in openclaw/clawhub) into .agents/skills/convex-insights in your project. Codex loads it when a task matches its description.

Can I use Convex Insights in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openclaw/clawhub --skill convex-insights -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/convex-insights, .gemini/skills/convex-insights, .github/skills/convex-insights and .opencode/skills/convex-insights in your project.

What does Convex Insights need to run?

SKILL.md names no scripts, command-line tools or credentials: Convex Insights is instructions for the agent only.

Does Convex Insights access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Convex Insights safe to install?

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.

What licence does Convex Insights use?

Convex Insights is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Convex Insights use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Convex Insights?

Skills that share tags, products or a category with Convex Insights: Marionette Flutter Drive App (leancodepl/marionette_mcp, 482 stars), Deep Links (stacklok/toolhive-studio, 170 stars), Asc Aso Audit (CamilleScholtz/swmpc, 239 stars) and Use Appclaw Agent CLI (appclawhq/AppClaw, 116 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Convex Insights?

openclaw (a GitHub organization) maintains it in openclaw/clawhub, which has 9,500 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on October 8, 2026.

Source: openclaw/clawhub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.