agentleFS
DevinoSolutionsDevinoSolutions/claude-plugins/skills/reporting-snapvisor-usage/SKILL.md

reporting-snapvisor-usage

Skill0 starsChanged 9 days agoMITView on GitHub

Reports SnapVisor account activity and access: builds and screenshots per period, busiest projects, daily, weekly, or monthly trends, members, and pending invites. Use when the user asks 'how many builds did we run this month', 'how many screenshots did we use', 'which projects are busiest', 'show usage trends', 'who is on the team', or 'which invites are pending'. Read-only.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Operations listed by name: call them directly, for example snapvisor:listBuilds.

    line 16
  2. Very specific:

    If the connection lists the operations by name instead (the per-tool surface), call them directly without the external_ prefix.

    line 24
  3. Very specific:

    Call external_getMe to get the account slug.

    line 35
  4. Very specific:

    If a call throws SCOPE_MISSING or a 403, the connection lacks that scope (member lists need account:admin).

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Generated from plugins/snapvisor/skills/reporting-snapvisor-usage/SKILL.md by scripts/sync-skills.mjs. Edit the plugin copy, then run the script. -->

SnapVisor usage report

Turn the account's analytics and membership into a short, factual report.

Connecting and calling the tools

Every operation in this skill comes from the snapvisor MCP server, the SnapVisor connector. The server defaults to Code Mode, so the operations below are written as the external_* functions you call inside snapvisor:execute_typescript. On a server set to the per-tool surface, the same operation is listed as snapvisor:<name> without the external_ prefix, for example snapvisor:listBuilds.

  • Only snapvisor:search_tools and snapvisor:execute_typescript listed (Code Mode, the default): call snapvisor:search_tools first, then call each tool inside snapvisor:execute_typescript as external_<tool> (for example external_listBuilds); the program must return its result. Scopes, confirmations and gates are identical on both surfaces.
  • Operations listed by name: call them directly, for example snapvisor:listBuilds.
  • "Tool not found": switch to the Code Mode route instead of retrying the direct call. If snapvisor:search_tools does not return the tool either, its OAuth scope was not granted; the user reconnects SnapVisor and approves that scope.
  • No snapvisor tools at all: SnapVisor is not connected yet. Follow the setup-snapvisor skill.

Tools you will use

The snapvisor MCP server has two tools: snapvisor:search_tools (call it first, for example with analytics, member, project) and snapvisor:execute_typescript (run a short program calling the declared external_* functions; the program must return its result).

If the connection lists the operations by name instead (the per-tool surface), call them directly without the external_ prefix.

Operations this skill uses (confirm with snapvisor:search_tools):

  • external_getMe: the accounts this connection can reach, with their slug and whether MCP access is included.
  • external_getAccountAnalytics: build and screenshot counts for an account, from a date (optional to), grouped by day, week or month, optionally for named projects.
  • external_listProjects: the account's projects.
  • external_listAccountMembers and external_listAccountInvites: members with their level, and pending invites. These need the account:admin scope.

Workflow

  1. Call external_getMe to get the account slug. If the connection reaches several accounts, ask which one.
  2. Agree the window (default: the current calendar month, grouped by week).
  3. In one program, fetch external_getAccountAnalytics and external_listProjects with await Promise.all. Add the member and invite lists if the user asked about the team.
  4. Report totals for the window, the trend per period in a small table, and the per-project split when available. For the team, list members by level and pending invites with their dates.

Code Mode pattern

const me = await external_getMe({});
const accountSlug = me.accounts[0].slug;
const [analytics, projects] = await Promise.all([
  external_getAccountAnalytics({ accountSlug, from: "2026-09-01", groupBy: "week" }),
  external_listProjects({ accountSlug }),
]);
return { analytics, projects };

If a call throws SCOPE_MISSING or a 403, the connection lacks that scope (member lists need account:admin). Say which scope is missing and that the user can reconnect with it.

Rules

  • Report only numbers the operations returned. Do not estimate costs or compare against other teams.
  • This skill only reads. Never call external_updateAccount, external_setAccountMemberLevel, external_removeAccountMember, external_createAccountInvites, or external_cancelAccountInvite from it. Do not invite, remove, or change members from here; those changes belong in the SnapVisor app or in an explicit request the user confirms.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.