Source

coval-ai/coval-external-skills

32 skills · 1.1K combined installs

Skills from this source

#
Skill
Source
8W Activity
Installs
1
onboard Interactively set up a first Coval AI evaluation. Guides users through installing the CLI, connecting an agent, creat…
coval-ai/coval-external-skills
55
2
watch-run Monitor a Coval run's progress with live updates. Use when user wants to check run status or wait for completion.
coval-ai/coval-external-skills
53
3
build-test-suite Build a complete test suite with test set and test cases for evaluating an AI agent. Guides through test set type sel…
coval-ai/coval-external-skills
52
4
get-results Retrieve and analyze simulation results from a Coval run. Use when user wants to review evaluation outcomes or debug …
coval-ai/coval-external-skills
52
5
launch-run Launch a Coval evaluation run against an AI agent. Use when user wants to start an evaluation, test an agent, or run …
coval-ai/coval-external-skills
52
6
build-dashboard Build or improve a Coval dashboard with metric visualizations backed by real data. Creates new dashboards from scratc…
coval-ai/coval-external-skills
51
7
configure-metrics Select and configure evaluation metrics for an AI agent. Guides through metric selection using use-case recommendatio…
coval-ai/coval-external-skills
51
8
design-persona Design and create a simulation persona for testing an AI agent. Guides through use case selection, voice and language…
coval-ai/coval-external-skills
51
9
download-audio Download audio recordings from Coval voice simulations. Use when user wants to listen to or analyze call recordings.
coval-ai/coval-external-skills
51
10
quick-eval Full evaluation workflow - launch a run, watch progress, and summarize results. Use for end-to-end agent testing.
coval-ai/coval-external-skills
51
11
coval-resources Comprehensive overview of ALL Coval platform resources, their hierarchy, relationships, API endpoints, and ID formats…
coval-ai/coval-external-skills
50
12
review-llm-annotations-and-improve-prompt Calculate agreement between human ground truth and machine labels for a text LLM judge metric, then analyze transcrip…
coval-ai/coval-external-skills
50
13
setup-agent Set up and connect a new Coval agent for evaluation. Guides through agent type selection, endpoint configuration, sys…
coval-ai/coval-external-skills
49
14
huggingface-import Import datasets from HuggingFace and convert them to Coval test sets. Use when the user wants to create test cases fr…
coval-ai/coval-external-skills
47
15
migrate-bluejay Migrate configuration from Bluejay voice AI testing platform to Coval. Use when customer says "migrate from bluejay",…
coval-ai/coval-external-skills
45
16
configure-trace-metrics Recommend, create, preview, and attach Coval trace-based metrics from OpenTelemetry spans. Use when a user has Coval …
coval-ai/coval-external-skills
39
17
debug-traces Troubleshoot Coval OpenTelemetry trace ingestion, missing trace UI, sparse traces, bad simulation or conversation cor…
coval-ai/coval-external-skills
39
18
optimize-trace-observability Improve Coval trace quality after basic ingestion works. Use when traces are sparse, missing useful STT/LLM/TTS/tool …
coval-ai/coval-external-skills
39
19
setup-tracing Configure an AI agent to send OpenTelemetry traces to Coval. Use when a user wants to add Coval tracing, instrument a…
coval-ai/coval-external-skills
38
20
analyze-audio-quality-report Analyze a Coval audio-quality testing report from runs across different voice, speaking-style, volume, interruption, …
coval-ai/coval-external-skills
30
21
run-audio-quality-testing End-to-end Coval audio-quality testing workflow. Launches one run per audio-robustness scenario against the same voic…
coval-ai/coval-external-skills
30
22
run-accent-testing End-to-end Coval accent testing workflow. Creates one persona per accent (each using a distinct accent voice and mirr…
coval-ai/coval-external-skills
29
23
analyze-accent-report Analyze a Coval accent testing report from runs across different speaker accents. Use when a user provides a Coval re…
coval-ai/coval-external-skills
28
24
distill-test-set Turn a large dataset (an existing oversized Coval test set, an export of past conversations, or a CSV/JSON of cases) …
coval-ai/coval-external-skills
24
25
personas-from-artifacts Derive a SET of simulation personas for an agent from product artifacts — backend payloads, UI screenshots, journey/p…
coval-ai/coval-external-skills
23
26
analyze-adversarial-report Analyze a Coval adversarial / red-team testing report and turn it into an agent-hardening plan. Use when a user provi…
coval-ai/coval-external-skills
21
27
consult-sofia Delegate a read-only Coval evaluation, simulation, monitoring, product-how-to, or troubleshooting subtask to Sofia th…
coval-ai/coval-external-skills
12
28
add-widget Add a chart, table, or text widget to a Coval dashboard. Use when user says "add a widget", "add a chart", "add a met…
coval-ai/coval-external-skills
2
29
create-dashboard Create a new Coval dashboard and populate it with metric widgets. Use when user says "create a dashboard", "build a d…
coval-ai/coval-external-skills
2
30
list-dashboards List all Coval dashboards with filtering and pagination. Use when user says "list dashboards", "show my dashboards", …
coval-ai/coval-external-skills
2
31
manage-dashboard Get, update, or delete a Coval dashboard. Use when user says "get dashboard", "rename dashboard", "delete dashboard",…
coval-ai/coval-external-skills
2
32
manage-widgets List, get, update, or delete widgets in a Coval dashboard. Use when user says "list widgets", "show widgets", "update…
coval-ai/coval-external-skills
2