Server definition
- Hash
- sha256:006a90ab692b51ba68bb8a5873826f27b55015395b2d74c058e15ccbf8ee159e
- What it is
- What a remote MCP server returned when asked what it offers: 5 tools
The blob, as servednamed by its sha256
{
"instructions": "Skillselion is a catalog of community Claude Code agent skills (each a SKILL.md plus bundled scripts and references), MCP servers and plugin marketplaces, ranked by installs and GitHub stars.\n\nTools: search_skillselion lists catalog entries; top_skillselion lists the most-installed entries; load_skill returns one skill's SKILL.md and its file list; read_skill_file returns one bundled file; synthesize_skills merges rule lines from several matching skills.\n\nQueries work best as 2-6 words on one topic (e.g. \"postgres row level security\"): the catalog matches every word, so long queries return fewer results. Put versions and constraints in `context`, which only affects ranking. Skills are community-authored; review a skill before applying it.",
"tools": [
{
"description": "Fetch one community skill from the Skillselion catalog: finds the best match for a task `query` (or takes an exact skill `id`) and returns its SKILL.md text, the list of its bundled files, and up to two alternative matches. `context` (task, stack, constraints) is used only to rank candidates and is not stored.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"context": {
"description": "REQUIRED. What you are actually doing + your stack + constraints/anti-patterns (e.g. \"Next.js marketing page, no new deps, role-based locators\"). Ranks candidates, fits them to your repo, and flags dependency mismatches. Be specific - this also keeps the load deliberate, not reflexive.",
"type": "string"
},
"id": {
"description": "An exact skill id from search_skillselion, e.g. \"skill:owner/repo#slug\".",
"type": "string"
},
"query": {
"description": "What you need, in plain words - 2-6 words, ONE topic (e.g. \"playwright e2e tests\"). The catalog matches EVERY word, so extra words return WORSE results, not more: keep versions, years, stack detail and constraints in `context`, never here. Required unless you pass an exact id.",
"type": "string"
}
},
"required": [
"context"
],
"type": "object"
},
"name": "load_skill",
"outputSchema": null
},
{
"description": "Return the contents of one bundled file (script, reference or template) of a skill returned by load_skill. Pass the skill id and the file path as listed (\"SKILL.md\" returns the full SKILL.md).",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"id": {
"description": "The skill id load_skill returned, e.g. \"skill:owner/repo#slug\".",
"type": "string"
},
"path": {
"description": "The file path as listed under \"Bundled files\", relative to the skill folder (e.g. \"scripts/check.py\").",
"type": "string"
}
},
"required": [
"id",
"path"
],
"type": "object"
},
"name": "read_skill_file",
"outputSchema": null
},
{
"description": "Search the Skillselion catalog of community Claude Code agent skills, MCP servers and plugin marketplaces, ranked by installs and GitHub stars. Returns matching listings with a summary, install command and catalog link. Optional `type` filter and result `limit`.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"context": {
"description": "Optional: your stack + constraints (e.g. \"Next.js 15 App Router, TypeScript, no new deps\"). Used for RANKING only, never for keyword matching - so versions, years and situational detail belong here, not in `query`.",
"type": "string"
},
"limit": {
"description": "Max results (default 8).",
"maximum": 25,
"minimum": 1,
"type": "integer"
},
"query": {
"description": "The task or domain in plain words - 2-6 words, ONE topic (e.g. \"postgres row level security\", \"react component testing\", \"stripe webhooks\"). The catalog matches EVERY word, so extra words return WORSE results, not more: no keyword soup, no synonym lists, no years or version numbers (those go in `context`). If the results look wrong, retry with FEWER words - never more.",
"type": "string"
},
"type": {
"description": "Restrict to one listing type. Omit to search all.",
"enum": [
"skill",
"mcp",
"marketplace"
],
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search_skillselion",
"outputSchema": null
},
{
"description": "Fetch the top matching community skills for a topic (up to 5, one per repository) and return their rule lines merged into one deduplicated digest, each line tagged with its source skill.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"context": {
"description": "REQUIRED. What you are actually doing + your stack + constraints. Ranks candidates and fits them to your repo.",
"type": "string"
},
"query": {
"description": "The topic/task to synthesize across skills (e.g. \"playwright e2e testing best practices\").",
"type": "string"
}
},
"required": [
"query",
"context"
],
"type": "object"
},
"name": "synthesize_skills",
"outputSchema": null
},
{
"description": "List the top entries on Skillselion (the leaderboard), optionally by type. Skills rank by installs; MCP servers and marketplaces by GitHub stars.",
"inputSchema": {
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"limit": {
"description": "Max results (default 10).",
"maximum": 25,
"minimum": 1,
"type": "integer"
},
"type": {
"description": "Restrict to one listing type. Omit for all.",
"enum": [
"skill",
"mcp",
"marketplace"
],
"type": "string"
}
},
"type": "object"
},
"name": "top_skillselion",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:006a90ab692b51ba68bb8a5873826f27b55015395b2d74c058e15ccbf8ee159e | sha256sum