find-skills
Helps agents discover and load the right CHERENKOV skill for any task — API testing, HITL review, MCP setup, certification, and more.
Skill by moaidmoatasem
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/moaidmoatasem-find-skills
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend, testing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/find-skills
What's inside
- Skill name
find-skills- Description
- Helps agents discover and load the right CHERENKOV skill for any task — API testing, HITL review, MCP setup, certification, and more.
- License
- Apache-2.0
- Instructions
- 67 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Find Skills ## Purpose This meta-skill helps you (or an AI agent) find the right CHERENKOV skill for a task. When someone asks "how do I generate tests?", "what skill handles performance?", or "is there a skill for Jira?", consult this index first. ## Skill Index | Task | Skill | Key command | |------|-------|-------------| | Generate API tests from an OpenAPI spec | `api-test-generation` | `cherenkov generate` | | Verify tests against a live server | `verify` | `cherenkov verify` | | Audit test suite quality (6 gates) | `check-suite` | `cherenkov check-suite` | | Issue a signed conformance certificate | `certify` | `cherenkov certify` | | Review uncertain tests with a human | `hitl-review` | `cherenkov hitl list` | | Self-heal failing tests (suggest-only) | `self-healing` | `cherenkov generate` | | Export ejected tests to a standalone repo | `eject-standalone` | `cherenkov eject` | | Set up CHERENKOV MCP server | `mcp-integration` | `cherenkov mcp serve` | | Drive CHERENKOV from Open Interpreter | `open-interpreter` | `bash scripts/setup_oi.sh` | | K6 load testing via MCP | `k6-perf` | MCP `run_k6_perf` | | Performance baseline + regression tracking | `perf-baseline` | `cherenkov perf` | | Visual screenshot regression | `visual-regression` | `cherenkov visual` | | Visual diff baselines via MCP | `visual-diff` | MCP `visual_diff_baseline` | | Governance KPI panel + model certification | `governance-certification` | `cherenkov governance` | | Export to Jira (suggest-only) | `jira-exporter` | MCP `export_jira_ticket` | | Query RAG index for historical context | `rag-query` | MCP `query_rag_index` | | MENA compliance scan | `mena-compliance` | MCP `scan_mena_compliance` | | Alibaba OCR code review (Gate 7b) | `ocr-review` | `cherenkov ocr review` | | Fix Snyk vulnerabilities (app code) | `snyk-remediation` | reads `agent_memory/snyk-findings.md` | | Session sync + token tracking | `sync-driven-dev` | `python scripts/agent_sync.py before` | ## How to load a skill In Claude Code, skills live at `skills/<name>/SKILL.md`. Load one by reading the file before starting the task: ```bash # Claude Code reads this automatically when you invoke the /skill-name command # Or explicitly: Read skills/verify/SKILL.md ``` Via the skills CLI (compatible with vercel-labs/skills format): ```bash # Install all cherenkov skills into your agent's skills directory npx skills add moaidmoatasem/cherenkov-qa # Or install a single skill npx skills add moaidmoatasem/cherenkov-qa --skill verify ``` ## Discovery tips - **"I want to generate tests"** → `api-test-generation` - **"I want to check conformance"** → `verify` - **"I want to certify an API"** → `certify` - **"Something is failing"** → `self-healing` - **"I use Claude Desktop / Cursor / Open Interpreter"** → `mcp-integration` - **"I want to export to Jira"** → `jira-exporter` - **"I need to fix a security issue"** → `snyk-remediation` - **"I want to track performance"** → `perf-baseline` or `k6-perf` - **"I want visual regression"** → `visual-regression` ## References - `skills/` — all skill files in this directory - `CLAUDE.md` — project norms and entry points - `HANDOVER.md` — current gate/phase status (always check this first)
From moaidmoatasem/cherenkov-qa, Apache-2.0.
More from moaidmoatasem/cherenkov-qa
- 0.583score
session-loop
moaidmoatasem
Work the Cherenkov-QA queue one item at a time, with no orchestrator.
SkillAFreshness: A★ 1Claude Code +9 - 0.544score
sync-driven-dev
moaidmoatasem
Session sync protocol for tracking token costs, loading pre-computed context, and persisting decisions across agent sessions.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
check-suite
moaidmoatasem
Audit an existing Playwright test suite for CHERENKOV quality gates — meaningfulness, spec alignment, and assertion strength.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
eject-standalone
moaidmoatasem
Strip CHERENKOV metadata from generated tests, producing a standalone vanilla Playwright suite with zero tool dependency.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
agentic-exploration
moaidmoatasem
Drive a real browser through plain-language scenarios and judge semantic pass/fail live, feeding failures into the HITL queue.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
governance-certification
moaidmoatasem
Surface QA KPIs and certify model capability tiers against a gold set using RAG-Triad metrics.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
hitl-review
moaidmoatasem
Manage the Human-In-The-Loop review queue for tests with uncertain verdicts (confidence 0.7–0.9).
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
api-test-generation
moaidmoatasem
Generate Playwright API tests from an OpenAPI spec through the INGEST→PLAN→GENERATE→REVIEW pipeline.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
ocr-review
moaidmoatasem
Run Alibaba Open Code Review as Gate 7b in the 8-gate pipeline on generated Playwright tests.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
open-interpreter
moaidmoatasem
Drive CHERENKOV conformance checks via Open Interpreter using the cherenkov MCP tools.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
self-healing
moaidmoatasem
Diagnose test failures and suggest fixes without auto-editing test code (D7 invariant enforced).
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
certify
moaidmoatasem
Issue a signed CHERENKOV conformance certificate after a clean verify run, proving API spec-vs-server fidelity.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 24
- Last commit (this folder)
- Aug 8, 2026 (2 months ago)
- Last release
- Aug 2, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/moaidmoatasem/cherenkov-qa
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from moaidmoatasem
- 0.583score
session-loop
moaidmoatasem
Work the Cherenkov-QA queue one item at a time, with no orchestrator.
SkillAFreshness: A★ 1Claude Code +9 - 0.544score
sync-driven-dev
moaidmoatasem
Session sync protocol for tracking token costs, loading pre-computed context, and persisting decisions across agent sessions.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
agentic-exploration
moaidmoatasem
Drive a real browser through plain-language scenarios and judge semantic pass/fail live, feeding failures into the HITL queue.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
check-suite
moaidmoatasem
Audit an existing Playwright test suite for CHERENKOV quality gates — meaningfulness, spec alignment, and assertion strength.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
eject-standalone
moaidmoatasem
Strip CHERENKOV metadata from generated tests, producing a standalone vanilla Playwright suite with zero tool dependency.
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
ocr-review
moaidmoatasem
Run Alibaba Open Code Review as Gate 7b in the 8-gate pipeline on generated Playwright tests.
SkillBFreshness: B★ 1Claude Code +9
Cite this page
find-skills. Agent Mart. https://agentmart.dev/skills/moaidmoatasem-find-skills (last updated 2026-10-24)