Borrowing it
Nothing to install: this file belongs to radiantlogicinc/fastworkflow. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/radiantlogicinc/fastworkflow/main/.claude/skills/fastworkflow-intent-training-convergence/SKILL.mdgit clone --depth 1 https://github.com/radiantlogicinc/fastworkflowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-intent-training-convergence)<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-intent-training-convergence"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-intent-training-convergence.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/radiantlogicinc/fastworkflow/fastworkflow-intent-training-convergence"><img src="https://agentmods.dev/badge/skills/radiantlogicinc/fastworkflow/fastworkflow-intent-training-convergence.svg?style=web" alt="Reviewed on agentmods" width="80" height="15"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00212 | $0.07174 |
| Opus 5 | $0.00106 | $0.03587 |
| Sonnet 5 | $0.00042 | $0.01435 |
| Haiku 4.5 | $0.00021 | $0.00717 |
Grade C, and why
fastworkflow-intent-training-convergence scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
trap 'rm -rf "$TMP"' EXIT How it starts
The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fastWorkflow Intent Training Convergence
Growing intent-detection quality is a measurement problem before it is a data problem. Training reports an F1 around 0.94 on workflows whose real held-out routing accuracy is under 50%, and two "identical" runs disagree on a large fraction of held-out cases. Both facts have to be handled before a single utterance is added, or you will spend hours tuning against noise.
The package now measures the right things — fastworkflow/train/heldout_evaluation.py
scores routing and escalation on held-out data and fastworkflow train prints and writes
the result. Training uses a fixed seed and reuses fingerprinted utterances and DSPy
examples, so an unchanged run does not redraw its data. Read Phase 0 before believing a
delta, and always score the same hand-written benchmark cases.
This skill is the loop: establish the floor, grow the sample, test paired, stop when the
gain drops under the floor. Statistics conventions belong to
fastworkflow-proof-and-analysis-toolkit; this skill is the application of them to
utterance sizing.
When to use / when NOT to use
| Situation | Skill |
|---|---|
| Deciding whether to add seeds/personas, and how to tell if it worked | this skill |
| The McNemar / CI / pass^k math itself, pre-registration format | fastworkflow-proof-and-analysis-toolkit |
| Turning a hunch into an accepted or retired result | fastworkflow-research-methodology |
| How two-tier BERT, thresholds, and synthetic generation actually work | fastworkflow-nlu-pipeline-reference |
| The benchmark file's schema, field by field | docs/intent_benchmark_format.md |
| Training crashed, artifacts missing, env broken | fastworkflow-debugging-playbook |
What fastworkflow train does operationally |
fastworkflow-run-and-operate |
What the package gives you now (and what it still does not)
This skill was originally written against an app-side harness, because the package
offered nothing to measure with. Wave 1 of epic fix-551 moved most of it in-package.
Verified against the working tree 2026-08-02.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 480 lines · 212 tokens per session scan C 4b8d0805b3c1
fastworkflow-intent-training-convergence is a skill published in the GitHub repository radiantlogicinc/fastworkflow (52 stars, last pushed 4d ago), licensed Apache-2.0. It adds 212 tokens to every session and 7,174 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.