Skillshop
Expert skills plus server-side checks for grant writing, home labs and AI agents
使うべきか
品質と安全性
検出事項(3)
- HIGH
- MEDIUMaudit_grant_proposal 内
- INFOaudit_grant_proposal 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"skillshop": {
"url": "https://skillshop.duckdns.org/mcp"
}
}
}リモートエンドポイント
https://skillshop.duckdns.org/mcpstreamable-httpできること
ツール一覧
ツール(9)
🟢list_skills
List every skill and paid check, with pack, price, and whether this caller can use it.
入力スキーマ
{
"type": "object",
"properties": {},
"title": "list_skillsArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "list_skillsDictOutput"
}🟢get_skill(name)
Load a skill's full instructions by name. Follow them for the current task.
入力スキーマ
{
"type": "object",
"properties": {
"name": {
"title": "Name",
"type": "string"
}
},
"required": [
"name"
],
"title": "get_skillArguments"
}出力スキーマ
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_skillOutput"
}🟢account
Show this caller's license status, unlocked packs and credit balance.
入力スキーマ
{
"type": "object",
"properties": {},
"title": "accountArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "accountDictOutput"
}🟢audit_handoff(record)
Check a task/handoff record against the agent-handoff protocol (paid, metered). record: {id, owner, state, revision, history[], artifact?, blocker?, delivery?, summary?} Returns ok, errors (protocol breaks), warnings (claims not yet supported by evidence), billing.
入力スキーマ
{
"type": "object",
"properties": {
"record": {
"additionalProperties": true,
"title": "Record",
"type": "object"
}
},
"required": [
"record"
],
"title": "audit_handoffArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "audit_handoffDictOutput"
}🟡audit_status_report(report)
Check a status update before it goes to a person: flags completion claims with no evidence, hedged results, and missing blockers (paid, metered; pairs with the free honest-status skill).
入力スキーマ
{
"type": "object",
"properties": {
"report": {
"title": "Report",
"type": "string"
}
},
"required": [
"report"
],
"title": "audit_status_reportArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "audit_status_reportDictOutput"
}⚪audit_grant_proposal(sections, requirements, request_amount)
Review a grant narrative the way a reviewer scores it (paid, metered). sections: {heading: text}. requirements: {required_sections: [..], word_limits: {heading: n}, total_word_limit: n}. request_amount: dollars requested. Returns findings by level (error/warning/nit): missing sections, word limits, unsourced need data, objectives that are not SMART, outputs posing as outcomes, no measurement plan, vague sustainability, request amount mismatch, vague words, placeholders.
入力スキーマ
{
"type": "object",
"properties": {
"sections": {
"additionalProperties": {
"type": "string"
},
"title": "Sections",
"type": "object"
},
"requirements": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"default": null,
"title": "Requirements"
},
"request_amount": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Request Amount"
}
},
"required": [
"sections"
],
"title": "audit_grant_proposalArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "audit_grant_proposalDictOutput"
}🟢audit_grant_budget(budget)
Check a grant budget's math and rules (paid, metered). budget: {lines: [{category, item, amount, justification, salary?, fte?, months?}], total_request, indirect?: {rate, base: 'tdc'|'mtdc', amount?}, max_indirect_rate?, fringe_rate?, match?: {required_ratio, amount}, participants?}. Checks totals, personnel and fringe math, indirect cap and base, match, missing justifications; returns cost per participant.
入力スキーマ
{
"type": "object",
"properties": {
"budget": {
"additionalProperties": true,
"title": "Budget",
"type": "object"
}
},
"required": [
"budget"
],
"title": "audit_grant_budgetArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "audit_grant_budgetDictOutput"
}🟡audit_compose(compose_yaml)
Review a docker-compose file for security and reliability (paid, metered): unpinned images, exposed databases/admin panels, plaintext secrets, Docker socket mounts, privileged containers, missing volumes, restart policies and health checks. Send the whole file as text.
入力スキーマ
{
"type": "object",
"properties": {
"compose_yaml": {
"title": "Compose Yaml",
"type": "string"
}
},
"required": [
"compose_yaml"
],
"title": "audit_composeArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "audit_composeDictOutput"
}🟢audit_backup_plan(datasets)
Check a backup plan against 3-2-1 with tested restores (paid, metered). datasets: [{name, copies: [{type: original|backup|snapshot|raid|sync, location, medium, offsite: bool, encrypted: bool, last_restore_test: 'YYYY-MM-DD'}]}]. Count the original as a copy.
入力スキーマ
{
"type": "object",
"properties": {
"datasets": {
"items": {
"additionalProperties": true,
"type": "object"
},
"title": "Datasets",
"type": "array"
}
},
"required": [
"datasets"
],
"title": "audit_backup_planArguments"
}出力スキーマ
{
"type": "object",
"additionalProperties": true,
"title": "audit_backup_planDictOutput"
}コミュニティ
エビデンス