evaluate-external-tool
Use when anyone proposes adopting an external AI tool, MCP server, agent pack or skill bundle into this repo — a shared link or list ("are these useful for…
Skill by andrei649
Chalk Labs
Need help deploying evaluate-external-tool?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/andrei649-evaluate-external-tool
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, 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/evaluate-external-tool
What's inside
- Skill name
evaluate-external-tool- Description
- Use when anyone proposes adopting an external AI tool, MCP server, agent pack or skill bundle into this repo — a shared link or list ("are these useful for us?", "integrate this", "add this MCP"), a GitHub/product URL, or a "N agents / N skills" pack. Also use before installing anything that writes to .claude/ or .mcp.json.
- License
- Apache-2.0
- Instructions
- 31 lines in SKILL.md · view on GitHub
Before installing
- Instructions call the network
Files (1)
- SKILL.md
SKILL.md (first lines)
# Before adopting anything external **Check the record first — this repo re-proposes tools it already rejected.** `docs/decisions/` and `docs/research/` hold prior verdicts. OpenMontage was evaluated and filed "no value" in June 2026 and re-proposed in September. Then, in order: 1. **Resolve the URL yourself.** Shared lists carry dead and wrong links. `graft.nanodevs.ai` was NXDOMAIN; three items on one list shared a single GitHub *profile* URL. Never describe a tool you could not fetch. `curl -s -H 'accept: application/dns-json' "https://dns.google/resolve?name=<host>&type=A"` — `Status: 3` means the domain does not exist. 2. **Ask what Nerva already has.** `docs/ARCHITECTURE.md` (module index), `docs/AI_CONTEXT.md` (tiered loading), `jarvis-load-context`, `scripts/backlog.py|ledger.py` (query-don't-load). Most "context for agents" tools duplicate these, untuned to this repo. "We already do this" is the expected answer. 3. **Check the install shape against governance.** Anything writing `.claude/settings.json`, `.claude/hooks/**` or `.mcp.json` runs code inside the loop that authorises unattended merges. That is an **owner decision**, never an adopt — see `selfdev-policy.json` and `AGENTS.md`. 4. **Local-first is a constraint, not a preference.** A tool whose value comes from shipping source to a vendor model contradicts the stated posture. Record the verdict in `docs/decisions/` so it is not re-litigated.
From andrei649/jarvis-hub, Apache-2.0.
More from andrei649/jarvis-hub
- 0.588score
jarvis-write-test
andrei649
Use when writing or fixing a pytest test in the jarvis hub (tests/test_*.py), or when a test fails on import/path/async-decorator issues.
SkillBFreshness: B★ 9Claude Code +9 - 0.585score
jarvis-load-context
andrei649
Use FIRST, before reading source, when starting any task in the jarvis hub repo — to load the right files instead of the ~2M-token raw repo.
SkillBFreshness: B★ 9Claude Code +9 - 0.583score
jarvis-add-plugin
andrei649
Use when adding a new third-party integration / plugin to the jarvis hub (agents/core/plugins/*), or wiring an external API an agent can call.
SkillBFreshness: B★ 9Claude Code +9 - 0.583score
jarvis-add-route
andrei649
Use when adding, moving, or removing an HTTP endpoint in the jarvis hub backend (agents/web.py or agents/core/routers/*).
SkillBFreshness: B★ 9Claude Code +9 - 0.583score
max
andrei649
Use when the owner says "Max" — alone, as a codename, in any casing ("max", "MAX", "run max", "continue max", "/max") — to start or continue the Nerva…
SkillBFreshness: B★ 9Claude Code +9 - 0.565score
brainstorming
andrei649
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
SkillBFreshness: B★ 9Claude Code +9 - 0.562score
writing-plans
andrei649
Use when you have a spec or requirements for a multi-step task, before touching code
SkillBFreshness: B★ 9Claude Code +9 - 0.562score
executing-plans
andrei649
Use when you have a written implementation plan to execute in a separate session with review checkpoints
SkillBFreshness: B★ 9Claude Code +9 - 0.562score
requesting-code-review
andrei649
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
SkillBFreshness: B★ 9Claude Code +9 - 0.558score
subagent-driven-development
andrei649
Use when executing implementation plans with independent tasks in the current session
SkillBFreshness: B★ 9Claude Code +9
Signals
- Stars
- 9
- Forks
- 1
- Open issues
- 30
- Last commit (this folder)
- Sep 11, 2026 (1 month ago)
- Last release
- Sep 2, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/andrei649/jarvis-hub
- Website
- www.andrei649.ro
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from andrei649
- 0.588score
jarvis-write-test
andrei649
Use when writing or fixing a pytest test in the jarvis hub (tests/test_*.py), or when a test fails on import/path/async-decorator issues.
SkillBFreshness: B★ 9Claude Code +9 - 0.585score
jarvis-load-context
andrei649
Use FIRST, before reading source, when starting any task in the jarvis hub repo — to load the right files instead of the ~2M-token raw repo.
SkillBFreshness: B★ 9Claude Code +9 - 0.583score
jarvis-add-plugin
andrei649
Use when adding a new third-party integration / plugin to the jarvis hub (agents/core/plugins/*), or wiring an external API an agent can call.
SkillBFreshness: B★ 9Claude Code +9 - 0.583score
jarvis-add-route
andrei649
Use when adding, moving, or removing an HTTP endpoint in the jarvis hub backend (agents/web.py or agents/core/routers/*).
SkillBFreshness: B★ 9Claude Code +9 - 0.583score
max
andrei649
Use when the owner says "Max" — alone, as a codename, in any casing ("max", "MAX", "run max", "continue max", "/max") — to start or continue the Nerva…
SkillBFreshness: B★ 9Claude Code +9 - 0.565score
brainstorming
andrei649
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
SkillBFreshness: B★ 9Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get evaluate-external-tool running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
evaluate-external-tool skill. Agent Mart. https://agentmart.dev/skills/andrei649-evaluate-external-tool (last updated 2026-10-24)