Source profileQuality 66/100Review permissions

hikariming/ghfind/skills/ghfind-score/SKILL.md

ghfind-score

Score any GitHub account 0-100 for real contribution value and trustworthiness, detect bot/farmed activity, compare two developers, and discover top developers by language/org/project. Use when asked to vet, rate, or judge a GitHub user, check if an account is real or farmed, or find strong developers. Backed by ghfind.com's deterministic open-source engine via a public no-auth REST API and MCP server.

Source repository stars: 154
Declared platforms: 0
Static risk flags: 2
Last source update: 2026-07-28
Source checked: 2026-07-28

Decision Compatibility Install Workflow Permissions Evidence Source

Decision brief

What it does—and where it fits

ghfind rates any GitHub account from 0 to 100 for real contribution value and trustworthiness using a fully deterministic, open-source engine (no LLM in the scoring core — the same inputs always produce the same score). It also detects AI/bot/farmed contribution, compares develo…

Best for

Vet a GitHub account before hiring, sponsoring, or merging a PR.
Decide whether an account's activity is genuine or farmed (template-PR spam,
Get a reproducible, auditable score instead of eyeballing stars/followers.

Not for

Tasks that require unconfirmed production actions or broad system permissions.
Environments where the pinned source and install steps cannot be inspected.

Compatibility matrix

Platform support, with evidence labels

Platform	Status	Evidence	What to check
Codex	Not declared	No explicit evidence	Portability before use
Claude Code	Not declared	No explicit evidence	Portability before use
Cursor	Not declared	No explicit evidence	Portability before use
Gemini CLI	Not declared	No explicit evidence	Portability before use

Open the compatibility checker

Installation

Inspect first. Install second.

The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

Source-detected install commandSource

npx skills add https://github.com/hikariming/ghfind --skill "skills/ghfind-score"

Safe inspection promptEditorial

Inspect the Agent Skill "ghfind-score" from https://github.com/hikariming/ghfind/blob/d6bde537e9e2b4624c5a335d6d02311cc1dee6fa/skills/ghfind-score/SKILL.md at commit d6bde537e9e2b4624c5a335d6d02311cc1dee6fa. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

Workflow

What the source asks the agent to do

01
How to call it (no authentication required)
Deterministic score for one account:
Deterministic score for one account:Full evidence payload (metrics, top repos, recent PRs, red flags):Other endpoints: GET /api/leaderboard, GET /api/developers?type=language|org|repo&value=..., GET /api/search-users?q=..., POST /api/vs-verdict {"a":"...","b":"..."}.
02
When to use this skill
Vet a GitHub account before hiring, sponsoring, or merging a PR.
Vet a GitHub account before hiring, sponsoring, or merging a PR.Decide whether an account's activity is genuine or farmed (template-PR spam,Get a reproducible, auditable score instead of eyeballing stars/followers.
03
MCP server
Streamable HTTP MCP server at https://ghfind.com/mcp exposing the tools scoreuser, scanuser, compareusers, getleaderboard, searchusers. Server card: https://ghfind.com/.well-known/mcp/server-card.json
Streamable HTTP MCP server at https://ghfind.com/mcp exposing the tools scoreuser, scanuser, compareusers, getleaderboard, searchusers. Server card: https://ghfind.com/.well-known/mcp/server-card.json
04
Notes
The score reflects an account's public GitHub footprint only; private-org
The score reflects an account's public GitHub footprint only; private-orgScoring is deterministic; only the optional roast text is LLM-written.Engine is open source (AGPL): https://github.com/hikariming/ghfind

Permission review

Static risk signals and limitations

Network access

medium · line 22

The documentation includes network, browsing, or remote request actions.

curl -s https://ghfind.com/api/score/{username}

Sends data out

high · line 28

The documentation includes sending, uploading, or posting data to a remote service.

curl -s -X POST https://ghfind.com/api/scan \

Network access

medium · line 28

The documentation includes network, browsing, or remote request actions.

curl -s -X POST https://ghfind.com/api/scan \

Evidence record

Why each signal appears

EvidenceSourceComputedTestedEditorial

Signal	Value	Evidence type	Meaning
Quality score	66/100	Computed	Documentation, specificity, maintenance, and trust rules
Repository stars	154	Source	Repository attention, not individual Skill quality
Compatibility	0 platforms	Source	Declared in the catalog source record
Usage guide	automated source guide	Editorial	Generated or reviewed according to the visible evidence level

Pinned source

Provenance and original SKILL.md

Repository: hikariming/ghfind
Skill path: skills/ghfind-score/SKILL.md
Commit: d6bde537e9e2b4624c5a335d6d02311cc1dee6fa
License: AGPL-3.0
Collected: 2026-07-28
Default branch: main

View the original SKILL.md

ghfind — GitHub developer value & trust scoring

When to use this skill

Vet a GitHub account before hiring, sponsoring, or merging a PR.
Decide whether an account's activity is genuine or farmed (template-PR spam, star inflation, contributions to repos it doesn't own).
Get a reproducible, auditable score instead of eyeballing stars/followers.
Compare two developers, or discover top developers in an ecosystem.

How to call it (no authentication required)

Deterministic score for one account:

curl -s https://ghfind.com/api/score/{username}

Full evidence payload (metrics, top repos, recent PRs, red flags):

curl -s -X POST https://ghfind.com/api/scan \
  -H 'Content-Type: application/json' \
  -d '{"username":"{username}"}'

Other endpoints: GET /api/leaderboard, GET /api/developers?type=language|org|repo&value=..., GET /api/search-users?q=..., POST /api/vs-verdict {"a":"...","b":"..."}.

Full API contract: https://ghfind.com/openapi.json · Agent docs: https://ghfind.com/llms.txt

MCP server

Streamable HTTP MCP server at https://ghfind.com/mcp exposing the tools score_user, scan_user, compare_users, get_leaderboard, search_users. Server card: https://ghfind.com/.well-known/mcp/server-card.json

Notes

The score reflects an account's public GitHub footprint only; private-org work is invisible to it, so a low score is not a factual claim about a person.
Scoring is deterministic; only the optional roast text is LLM-written.
Engine is open source (AGPL): https://github.com/hikariming/ghfind

Alternatives

Compare before choosing

Computed 10042,015

coreyhaines31/marketingskills

ab-testing

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program

Computed 1007

event4u-app/agent-config

design-intelligence

Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.

Computed 1007

event4u-app/agent-config

existing-ui-audit

Use BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for the ui directive set.

Computed 1007

event4u-app/agent-config

testing-anti-patterns

Use BEFORE writing/changing tests, adding mocks, or test-only methods on production classes — vs mocking-the-mock, production pollution, partial mocks, and overfit/tautological assertions