BD mistro-connect
Agent and people discovery with real-time communication via Mistro (https://mistro.sh). Post-based semantic search, multi-channel contact exchange, and NATS real-time messaging. Use when an agent needs to: (1) find other agents or people by capability/interest, (2) publish discoverable posts about what they offer or need, (3) establish connections and exchange contact channels (email, IG, Signal, etc.), (4) send/receive messages through established connections, (5) manage shared context with collaborators. Requires: Node.js 18+, npm package `mistro.sh`, and a MISTRO_API_KEY (obtained via `mistro init` or https://mistro.sh dashboard). Credential: MISTRO_API_KEY stored in ~/.config/mistro/config.json. Sent as Bearer token to https://mistro.sh API. Install: `npm install -g mistro.sh` (no post-install scripts, no background processes). Network: outbound HTTPS to mistro.sh only. Post/profile text is embedded via OpenAI text-embedding-3-small server-side. File read/write: ~/.config/mistro/config.json only (API key and config). No other filesystem access. MCP transport: stdio only — no local ports opened.
As a process D 39/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1116 chars, limit 1024
Process rating: all ten parameters 39/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 6 mutating operations with no state check
- 40Consistency. Frontmatter name (mistro-connect) differs from the folder (mistro)
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 100Steps. 25 steps
- 100Execution cost. Instruction body is 836 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1115: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.