Add referenced last30days catalog entry

This commit is contained in:
Dotta
2026-06-04 20:01:25 +00:00
parent 1227bb8ead
commit bee2b25f5d
17 changed files with 1276 additions and 49 deletions
@@ -1,7 +1,7 @@
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { afterEach, describe, expect, it } from "vitest";
import { afterEach, describe, expect, it, vi } from "vitest";
import {
buildCatalogManifest,
formatCatalogManifest,
@@ -13,6 +13,7 @@ const tempDirs: string[] = [];
describe("skills catalog manifest", () => {
afterEach(async () => {
await Promise.all(tempDirs.splice(0).map((dir) => fs.rm(dir, { recursive: true, force: true })));
vi.unstubAllGlobals();
});
it("builds stable manifest entries from catalog skill directories", async () => {
@@ -59,6 +60,81 @@ describe("skills catalog manifest", () => {
expect(result.manifest.skills[0]!.contentHash).toMatch(/^sha256:[a-f0-9]{64}$/);
});
it("builds stable manifest entries from pinned GitHub references", async () => {
const packageDir = await createCatalogPackage();
const skillMarkdown = [
"---",
"name: Remote Research",
"description: Research recent discussion from a pinned upstream skill.",
"---",
"",
"Use this skill.",
"",
].join("\n");
const script = "print('hello')\n";
await writeReference(packageDir, "optional", "research", "remote-research", {
source: {
type: "github",
hostname: "github.com",
owner: "example",
repo: "remote-skill",
ref: "v1.0.0",
commit: "0123456789abcdef0123456789abcdef01234567",
path: "skills/remote-research",
},
files: ["SKILL.md", "scripts/**"],
recommendedForRoles: ["researcher"],
tags: ["research"],
});
const fetchMock = vi.fn(async (url: string) => {
if (url.includes("/git/trees/")) {
return new Response(JSON.stringify({
tree: [
{ path: "skills/remote-research/SKILL.md", type: "blob", size: Buffer.byteLength(skillMarkdown) },
{ path: "skills/remote-research/scripts/run.py", type: "blob", size: Buffer.byteLength(script) },
{ path: "README.md", type: "blob", size: 9 },
],
}), { status: 200 });
}
if (url.endsWith("/skills/remote-research/SKILL.md")) {
return new Response(skillMarkdown, { status: 200 });
}
if (url.endsWith("/skills/remote-research/scripts/run.py")) {
return new Response(script, { status: 200 });
}
return new Response("not found", { status: 404 });
});
vi.stubGlobal("fetch", fetchMock);
const result = await buildCatalogManifest({
packageDir,
generatedAt: "2026-05-26T00:00:00.000Z",
});
expect(result.errors).toEqual([]);
expect(result.manifest.skills[0]).toMatchObject({
id: "paperclipai:optional:research:remote-research",
key: "paperclipai/optional/research/remote-research",
path: "catalog/optional/research/remote-research",
trustLevel: "scripts_executables",
recommendedForRoles: ["researcher"],
tags: ["research"],
source: {
type: "github",
owner: "example",
repo: "remote-skill",
ref: "v1.0.0",
commit: "0123456789abcdef0123456789abcdef01234567",
path: "skills/remote-research",
},
});
expect(result.manifest.skills[0]!.files.map((file) => file.path)).toEqual([
"SKILL.md",
"scripts/run.py",
]);
expect(result.manifest.skills[0]!.contentHash).toMatch(/^sha256:[a-f0-9]{64}$/);
});
it("reports frontmatter, directory, uniqueness, and inventory errors together", async () => {
const packageDir = await createCatalogPackage();
await writeSkill(packageDir, "bundled", "Bad_Category", "duplicate", {
@@ -87,8 +163,8 @@ describe("skills catalog manifest", () => {
expect(result.errors).toEqual(
expect.arrayContaining([
expect.stringContaining("catalog/misc/SKILL.md is not under catalog/<bundled|optional>/<category>/<slug>/SKILL.md"),
expect.stringContaining("catalog/bundled/software-development/missing-skill is missing SKILL.md"),
expect.stringContaining("catalog/misc/SKILL.md is not under catalog/<bundled|optional>/<category>/<slug>/{SKILL.md,catalog-ref.json}"),
expect.stringContaining("catalog/bundled/software-development/missing-skill is missing SKILL.md or catalog-ref.json"),
expect.stringContaining("has invalid category"),
expect.stringContaining("frontmatter must include description"),
expect.stringContaining("key must be paperclipai/bundled/Bad_Category/duplicate"),
@@ -163,3 +239,19 @@ async function writeSkill(
await fs.writeFile(filePath, content, "utf8");
}
}
async function writeReference(
packageDir: string,
kind: "bundled" | "optional",
category: string,
slug: string,
descriptor: Record<string, unknown>,
) {
const skillDir = path.join(packageDir, "catalog", kind, category, slug);
await fs.mkdir(skillDir, { recursive: true });
await fs.writeFile(
path.join(skillDir, "catalog-ref.json"),
`${JSON.stringify(descriptor, null, 2)}\n`,
"utf8",
);
}
+350 -6
View File
@@ -4,6 +4,7 @@ import fs from "node:fs/promises";
import path from "node:path";
import {
asBoolean,
isPlainRecord,
asString,
asStringArray,
parseFrontmatterMarkdown,
@@ -14,23 +15,54 @@ import type {
CatalogSkillFile,
CatalogSkillFileKind,
CatalogSkillKind,
CatalogSkillSource,
CatalogTrustLevel,
} from "./types.js";
const CATALOG_PACKAGE_NAME = "@paperclipai/skills-catalog";
const CATALOG_SCHEMA_VERSION = 1;
const SKILL_ENTRYPOINT = "SKILL.md";
const CATALOG_REFERENCE_FILE = "catalog-ref.json";
const MAX_CATALOG_FILE_BYTES = 1024 * 1024;
const SLUG_PATTERN = /^[a-z0-9]+(?:-[a-z0-9]+)*$/;
const CATALOG_KINDS = new Set<CatalogSkillKind>(["bundled", "optional"]);
interface SkillCandidate {
interface BaseSkillCandidate {
kind: CatalogSkillKind;
category: string;
slug: string;
absolutePath: string;
}
type SkillCandidate =
| (BaseSkillCandidate & { source: "local" })
| (BaseSkillCandidate & { source: "reference"; descriptorPath: string });
interface ReferencedGitHubSourceDescriptor {
type: "github";
hostname?: string;
owner: string;
repo: string;
ref: string;
commit: string;
path: string;
}
interface ReferencedSkillDescriptor {
source: ReferencedGitHubSourceDescriptor;
files?: string[];
defaultInstall?: boolean;
recommendedForRoles?: string[];
requires?: string[];
tags?: string[];
}
interface GitHubTreeEntry {
path: string;
type: "blob" | "tree" | string;
size?: number;
}
interface BuildCatalogManifestOptions {
packageDir: string;
generatedAt?: string;
@@ -171,11 +203,23 @@ async function discoverSkillCandidates(packageDir: string, errors: string[]) {
if (!slugEntry.isDirectory()) continue;
const slug = slugEntry.name;
const skillDir = path.join(categoryDir, slug);
if (!existsSync(path.join(skillDir, SKILL_ENTRYPOINT))) {
errors.push(`${relativePackagePath(packageDir, skillDir)} is missing SKILL.md.`);
const hasLocalSkill = existsSync(path.join(skillDir, SKILL_ENTRYPOINT));
const descriptorPath = path.join(skillDir, CATALOG_REFERENCE_FILE);
const hasReference = existsSync(descriptorPath);
if (hasLocalSkill && hasReference) {
errors.push(`${relativePackagePath(packageDir, skillDir)} must contain either SKILL.md or ${CATALOG_REFERENCE_FILE}, not both.`);
continue;
}
candidates.push({ kind, category, slug, absolutePath: skillDir });
if (!hasLocalSkill && !hasReference) {
errors.push(`${relativePackagePath(packageDir, skillDir)} is missing SKILL.md or ${CATALOG_REFERENCE_FILE}.`);
continue;
}
candidates.push(
hasReference
? { kind, category, slug, absolutePath: skillDir, source: "reference", descriptorPath }
: { kind, category, slug, absolutePath: skillDir, source: "local" },
);
}
}
}
@@ -191,13 +235,13 @@ async function collectMisplacedSkillFiles(catalogDir: string, errors: string[])
await visit(absolutePath);
continue;
}
if (entry.name !== SKILL_ENTRYPOINT) continue;
if (entry.name !== SKILL_ENTRYPOINT && entry.name !== CATALOG_REFERENCE_FILE) continue;
const relativePath = toPosixPath(path.relative(catalogDir, absolutePath));
const parts = relativePath.split("/");
const kind = parts[0];
if (parts.length !== 4 || !CATALOG_KINDS.has(kind as CatalogSkillKind)) {
errors.push(`catalog/${relativePath} is not under catalog/<bundled|optional>/<category>/<slug>/SKILL.md.`);
errors.push(`catalog/${relativePath} is not under catalog/<bundled|optional>/<category>/<slug>/{SKILL.md,${CATALOG_REFERENCE_FILE}}.`);
}
}
}
@@ -210,6 +254,10 @@ async function buildCatalogSkill(
candidate: SkillCandidate,
errors: string[],
): Promise<CatalogSkill | null> {
if (candidate.source === "reference") {
return buildReferencedCatalogSkill(packageDir, candidate, errors);
}
const prefix = relativePackagePath(packageDir, candidate.absolutePath);
validateSlug("category", candidate.category, prefix, errors);
validateSlug("slug", candidate.slug, prefix, errors);
@@ -268,6 +316,268 @@ async function buildCatalogSkill(
};
}
async function buildReferencedCatalogSkill(
packageDir: string,
candidate: Extract<SkillCandidate, { source: "reference" }>,
errors: string[],
): Promise<CatalogSkill | null> {
const prefix = relativePackagePath(packageDir, candidate.absolutePath);
validateSlug("category", candidate.category, prefix, errors);
validateSlug("slug", candidate.slug, prefix, errors);
const descriptor = await readReferencedSkillDescriptor(candidate.descriptorPath, prefix, errors);
if (!descriptor) return null;
const id = `paperclipai:${candidate.kind}:${candidate.category}:${candidate.slug}`;
const key = `paperclipai/${candidate.kind}/${candidate.category}/${candidate.slug}`;
const source = buildCatalogSkillSource(descriptor.source, errors, `${prefix}/${CATALOG_REFERENCE_FILE}`);
if (!source) return null;
const files = await collectReferencedSkillFiles(source, descriptor.files ?? [SKILL_ENTRYPOINT], prefix, errors);
const skillMarkdown = await readReferencedFileText(source, SKILL_ENTRYPOINT, prefix, errors);
if (!skillMarkdown) return null;
const parsed = parseFrontmatterMarkdown(skillMarkdown);
if (!parsed.hasFrontmatter) {
errors.push(`${source.url}/${SKILL_ENTRYPOINT} must start with YAML frontmatter.`);
}
const name = asString(parsed.frontmatter.name);
if (!name) errors.push(`${source.url}/${SKILL_ENTRYPOINT} frontmatter must include name.`);
const description = asString(parsed.frontmatter.description);
if (!description) errors.push(`${source.url}/${SKILL_ENTRYPOINT} frontmatter must include description.`);
const explicitKey = asString(parsed.frontmatter.key);
if (explicitKey && explicitKey !== key) {
errors.push(`${source.url}/${SKILL_ENTRYPOINT} key must be ${key}.`);
}
const explicitSlug = asString(parsed.frontmatter.slug);
if (explicitSlug && explicitSlug !== candidate.slug) {
errors.push(`${source.url}/${SKILL_ENTRYPOINT} slug must be ${candidate.slug}.`);
}
const defaultInstall = asBoolean(descriptor.defaultInstall) ?? false;
const recommendedForRoles = readStringArrayField(descriptor.recommendedForRoles, "recommendedForRoles", prefix, errors);
const requires = readStringArrayField(descriptor.requires, "requires", prefix, errors);
const tags = readStringArrayField(descriptor.tags, "tags", prefix, errors);
if (!files.some((file) => file.path === SKILL_ENTRYPOINT && file.kind === "skill")) {
errors.push(`${prefix} referenced inventory does not contain SKILL.md.`);
}
if (!name || !description) return null;
return {
id,
key,
kind: candidate.kind,
category: candidate.category,
slug: candidate.slug,
name,
description,
path: toPosixPath(path.relative(packageDir, candidate.absolutePath)),
entrypoint: SKILL_ENTRYPOINT,
trustLevel: deriveTrustLevel(files),
compatibility: "compatible",
defaultInstall,
recommendedForRoles,
requires,
tags,
files,
contentHash: buildContentHash(files),
source,
};
}
async function readReferencedSkillDescriptor(
descriptorPath: string,
prefix: string,
errors: string[],
): Promise<ReferencedSkillDescriptor | null> {
let raw: unknown;
try {
raw = JSON.parse(await fs.readFile(descriptorPath, "utf8"));
} catch (error) {
errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} is missing or invalid JSON: ${errorMessage(error)}`);
return null;
}
if (!isPlainRecord(raw) || !isPlainRecord(raw.source)) {
errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} must include a source object.`);
return null;
}
const sourceRaw = raw.source;
if (asString(sourceRaw.type) !== "github") {
errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} source.type must be "github".`);
return null;
}
const owner = asString(sourceRaw.owner);
const repo = asString(sourceRaw.repo);
const ref = asString(sourceRaw.ref);
const commit = asString(sourceRaw.commit);
const sourcePath = asString(sourceRaw.path);
if (!owner || !repo || !ref || !commit || sourcePath === null) {
errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} GitHub source must include owner, repo, ref, commit, and path.`);
return null;
}
const descriptor: ReferencedSkillDescriptor = {
source: {
type: "github",
hostname: asString(sourceRaw.hostname) ?? "github.com",
owner,
repo,
ref,
commit,
path: sourcePath,
},
defaultInstall: asBoolean(raw.defaultInstall) ?? false,
files: asStringArray(raw.files ?? undefined) ?? undefined,
recommendedForRoles: asStringArray(raw.recommendedForRoles ?? undefined) ?? undefined,
requires: asStringArray(raw.requires ?? undefined) ?? undefined,
tags: asStringArray(raw.tags ?? undefined) ?? undefined,
};
if (raw.files !== undefined && !descriptor.files) errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} files must be an array of strings.`);
if (raw.recommendedForRoles !== undefined && !descriptor.recommendedForRoles) errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} recommendedForRoles must be an array of strings.`);
if (raw.requires !== undefined && !descriptor.requires) errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} requires must be an array of strings.`);
if (raw.tags !== undefined && !descriptor.tags) errors.push(`${prefix}/${CATALOG_REFERENCE_FILE} tags must be an array of strings.`);
return descriptor;
}
function buildCatalogSkillSource(
descriptor: ReferencedGitHubSourceDescriptor,
errors: string[],
prefix: string,
): CatalogSkillSource | null {
if (!/^[0-9a-f]{40}$/i.test(descriptor.commit)) {
errors.push(`${prefix} source.commit must be a 40-character Git commit SHA.`);
}
const sourcePath = normalizeReferencedPath(descriptor.path);
if (sourcePath === null) {
errors.push(`${prefix} source.path must be a portable path within the repository.`);
}
const hostname = descriptor.hostname ?? "github.com";
const url = `https://${hostname}/${descriptor.owner}/${descriptor.repo}/tree/${descriptor.ref}/${sourcePath ?? ""}`.replace(/\/$/, "");
if (errors.length > 0 && (!/^[0-9a-f]{40}$/i.test(descriptor.commit) || sourcePath === null)) return null;
return {
type: "github",
hostname,
owner: descriptor.owner,
repo: descriptor.repo,
ref: descriptor.ref,
commit: descriptor.commit,
path: sourcePath ?? "",
url,
};
}
async function collectReferencedSkillFiles(
source: CatalogSkillSource,
includePatterns: string[],
prefix: string,
errors: string[],
): Promise<CatalogSkillFile[]> {
const tree = await fetchGitHubTree(source, prefix, errors);
const sourceRoot = source.path ? `${source.path}/` : "";
const normalizedPatterns: string[] = [];
for (const pattern of includePatterns) {
const normalizedPattern = normalizeReferencedPath(pattern);
if (normalizedPattern === null) {
errors.push(`${prefix} referenced include path is invalid: ${pattern}`);
continue;
}
if (normalizedPattern) normalizedPatterns.push(normalizedPattern);
}
const files: CatalogSkillFile[] = [];
for (const entry of tree) {
if (entry.type !== "blob") continue;
if (!entry.path.startsWith(sourceRoot)) continue;
const relativePath = entry.path.slice(sourceRoot.length);
if (!normalizedPatterns.some((pattern) => referencedPathMatches(relativePath, pattern))) continue;
if ((entry.size ?? 0) > MAX_CATALOG_FILE_BYTES) {
errors.push(`${prefix}/${relativePath} exceeds ${MAX_CATALOG_FILE_BYTES} bytes.`);
continue;
}
const bytes = await fetchReferencedFileBytes(source, relativePath, prefix, errors);
if (!bytes) continue;
files.push({
path: relativePath,
kind: classifyCatalogFile(relativePath),
sizeBytes: bytes.byteLength,
sha256: sha256(bytes),
});
}
files.sort((a, b) => {
if (a.path === SKILL_ENTRYPOINT) return -1;
if (b.path === SKILL_ENTRYPOINT) return 1;
return a.path.localeCompare(b.path);
});
return files;
}
async function fetchGitHubTree(
source: CatalogSkillSource,
prefix: string,
errors: string[],
): Promise<GitHubTreeEntry[]> {
const url = `${githubApiBase(source.hostname)}/repos/${source.owner}/${source.repo}/git/trees/${source.commit}?recursive=1`;
try {
const response = await fetch(url, { headers: { accept: "application/vnd.github+json" } });
if (!response.ok) {
errors.push(`${prefix} failed to fetch GitHub tree: HTTP ${response.status}.`);
return [];
}
const body = await response.json() as { tree?: GitHubTreeEntry[]; truncated?: boolean };
if (body.truncated) errors.push(`${prefix} GitHub tree response was truncated.`);
return Array.isArray(body.tree) ? body.tree : [];
} catch (error) {
errors.push(`${prefix} failed to fetch GitHub tree: ${errorMessage(error)}.`);
return [];
}
}
async function readReferencedFileText(
source: CatalogSkillSource,
relativePath: string,
prefix: string,
errors: string[],
) {
const bytes = await fetchReferencedFileBytes(source, relativePath, prefix, errors);
return bytes ? bytes.toString("utf8") : null;
}
async function fetchReferencedFileBytes(
source: CatalogSkillSource,
relativePath: string,
prefix: string,
errors: string[],
): Promise<Buffer | null> {
const normalizedPath = normalizeReferencedPath(relativePath);
if (!normalizedPath) {
errors.push(`${prefix} referenced file path is invalid: ${relativePath}`);
return null;
}
const url = rawGitHubUrl(source, normalizedPath);
try {
const response = await fetch(url);
if (!response.ok) {
errors.push(`${prefix}/${normalizedPath} failed to fetch pinned GitHub file: HTTP ${response.status}.`);
return null;
}
return Buffer.from(await response.arrayBuffer());
} catch (error) {
errors.push(`${prefix}/${normalizedPath} failed to fetch pinned GitHub file: ${errorMessage(error)}.`);
return null;
}
}
async function collectSkillFiles(
packageDir: string,
skillDir: string,
@@ -433,6 +743,40 @@ function toPosixPath(input: string) {
return input.split(path.sep).join("/");
}
function normalizeReferencedPath(input: string) {
const normalized = input.replace(/\\/g, "/").replace(/^\/+/, "").replace(/\/+$/, "");
if (normalized === "") return "";
const parts = normalized.split("/");
if (parts.includes("") || parts.includes(".") || parts.includes("..") || path.posix.isAbsolute(normalized)) {
return null;
}
return normalized;
}
function referencedPathMatches(relativePath: string, pattern: string) {
if (pattern.endsWith("/**")) {
const directory = pattern.slice(0, -3);
return relativePath === directory || relativePath.startsWith(`${directory}/`);
}
return relativePath === pattern;
}
function githubApiBase(hostname: string) {
const normalized = hostname.toLowerCase();
return normalized === "github.com" || normalized === "www.github.com"
? "https://api.github.com"
: `https://${hostname}/api/v3`;
}
function rawGitHubUrl(source: CatalogSkillSource, relativePath: string) {
const fullPath = source.path ? `${source.path}/${relativePath}` : relativePath;
const encodedPath = fullPath.split("/").map((segment) => encodeURIComponent(segment)).join("/");
const normalized = source.hostname.toLowerCase();
return normalized === "github.com" || normalized === "www.github.com"
? `https://raw.githubusercontent.com/${source.owner}/${source.repo}/${source.commit}/${encodedPath}`
: `https://${source.hostname}/raw/${source.owner}/${source.repo}/${source.commit}/${encodedPath}`;
}
function isPathInside(parent: string, child: string) {
const relativePath = path.relative(parent, child);
return relativePath === "" || (!relativePath.startsWith("..") && !path.isAbsolute(relativePath));
+2
View File
@@ -7,7 +7,9 @@ export type {
CatalogSkill,
CatalogSkillFile,
CatalogSkillFileKind,
CatalogSkillGitHubSource,
CatalogSkillKind,
CatalogSkillSource,
CatalogTrustLevel,
CatalogValidationResult,
} from "./types.js";
@@ -1,6 +1,5 @@
import { describe, expect, it } from "vitest";
import { catalogManifest, catalogSkills, resolveCatalogSkillRef } from "./index.js";
import type { CatalogSkill } from "./types.js";
const EXPECTED_BUNDLED_KEYS = [
"paperclipai/bundled/docs/doc-maintenance",
@@ -15,6 +14,7 @@ const EXPECTED_OPTIONAL_KEYS = [
"paperclipai/optional/browser/agent-browser",
"paperclipai/optional/content/release-announcement",
"paperclipai/optional/product/design-critique",
"paperclipai/optional/research/last30days",
];
describe("shipped skills catalog", () => {
@@ -32,12 +32,14 @@ describe("shipped skills catalog", () => {
expect(optionalKeys).toEqual(EXPECTED_OPTIONAL_KEYS);
});
it("keeps every shipped skill free of executable scripts until script-bearing skills clear security review", () => {
// The real install-time security boundary (server assertCatalogSkillInstallable) blocks
// only "scripts_executables". Static assets (svg/html templates, e.g. the wireframe skill)
// carry the "assets" trust level and are installable, so they are allowed in the catalog.
it("keeps script-bearing shipped skills explicit so install stays audit-gated", () => {
// The real install-time security boundary audits materialized bytes and blocks
// hard-stop findings. Static assets (svg/html templates, e.g. the wireframe skill)
// carry the "assets" trust level and are installable.
const scriptBearing = catalogSkills.filter((skill) => skill.trustLevel === "scripts_executables");
expect(scriptBearing, formatViolations("script-bearing skills require security review", scriptBearing)).toEqual([]);
expect(scriptBearing.map((skill) => skill.key)).toEqual([
"paperclipai/optional/research/last30days",
]);
});
it("populates browse/search-relevant fields for every shipped skill", () => {
@@ -86,9 +88,3 @@ describe("shipped skills catalog", () => {
expect(resolveCatalogSkillRef(sample.slug)).toMatchObject({ key: sample.key });
});
});
function formatViolations(label: string, skills: CatalogSkill[]) {
if (skills.length === 0) return label;
const detail = skills.map((skill) => `${skill.key} (${skill.trustLevel})`).join(", ");
return `${label}: ${detail}`;
}
+14
View File
@@ -13,6 +13,19 @@ export interface CatalogSkillFile {
sha256: string;
}
export interface CatalogSkillGitHubSource {
type: "github";
hostname: string;
owner: string;
repo: string;
ref: string;
commit: string;
path: string;
url: string;
}
export type CatalogSkillSource = CatalogSkillGitHubSource;
export interface CatalogSkill {
id: string;
key: string;
@@ -31,6 +44,7 @@ export interface CatalogSkill {
tags: string[];
files: CatalogSkillFile[];
contentHash: string;
source?: CatalogSkillSource;
}
export interface CatalogManifest {