Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add OpenDCAI/Dataflow-LoopAI --skill curating-dataflow-pipeline-skillsgit clone --depth 1 https://github.com/OpenDCAI/Dataflow-LoopAIWrote 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/opendcai/dataflow-loopai/curating-dataflow-pipeline-skills)<a href="https://agentmods.dev/skills/opendcai/dataflow-loopai/curating-dataflow-pipeline-skills"><img src="https://agentmods.dev/badge/skills/opendcai/dataflow-loopai/curating-dataflow-pipeline-skills/github.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/opendcai/dataflow-loopai/curating-dataflow-pipeline-skills"><img src="https://agentmods.dev/badge/skills/opendcai/dataflow-loopai/curating-dataflow-pipeline-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00036 | $0.00974 |
| Opus 5 | $0.00018 | $0.00487 |
| Sonnet 5 | $0.00007 | $0.00195 |
| Haiku 4.5 | $0.00004 | $0.00097 |
Grade A, and why
curating-dataflow-pipeline-skills scanned grade A with 0 findings 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Curate Proven DataFlow Pipeline Skills
Use this skill only after reviewing-dataflow-pipeline has produced a complete
review with decision release. Ordinary passing pipelines are not
automatically worth preserving.
Before writing a skill, read the installed skill-creator skill completely and
follow it. If skill-creator is unavailable, do not improvise the skill
structure; report the missing dependency. Read the complete reference example
at example/complete-math-reasoning-sft-skill
when creating the first curated skill or when the required evidence layout is
unclear.
Promotion gate
A candidate is eligible only when all conditions hold:
- review total is at least 90 and no redline is present;
- D2, D3, D4, and D6 raw scores are each at least 3;
- review evidence includes numbers and sample IDs;
- trial artifacts cover at least three records per selected source dataset;
- at least five official benchmark examples were used;
- pipeline source, trial input/output, benchmark samples, and review reports are complete and contain no secrets.
If any condition fails, record not_promoted in the DataFlow run summary and
do not create or update a skill.
Match the task type
Derive a task fingerprint from benchmark/task family, required capabilities, training record shape, reasoning policy, source schema families, answer format, and major operator-chain purpose. Dataset names alone do not define a type.
Search only curated skills named dataflow-pattern-*. Never rewrite
generating-dataflow-pipeline, reviewing-dataflow-pipeline, this curator, or
skill-creator.
- No matching task fingerprint: create a new
dataflow-pattern-<type>skill. - Matching skill exists: compare the candidate with its currently recommended case using the same rubric and comparable evidence.
- Incomparable evidence: append nothing and report
comparison_inconclusive.
Replacement rule
Do not replace a recommendation merely because the total score is higher. The candidate may become recommended only when it has no regression in redlines, D2, D3, D4, or D6; supports at least the same task/schema coverage; and has a strictly better supported tradeoff in quality, coverage, robustness, or cost. Quality takes precedence over runtime cost.
What ships with it
7 files 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.
- example/complete-math-reasoning-sft-skill/examples/gsm8k-reasoning-v1/benchmark_samples.jsonl 1.1 KB
- example/complete-math-reasoning-sft-skill/examples/gsm8k-reasoning-v1/case_report.md 2.4 KB
- example/complete-math-reasoning-sft-skill/examples/gsm8k-reasoning-v1/pipeline_review.json 922 B
- example/complete-math-reasoning-sft-skill/examples/gsm8k-reasoning-v1/pipeline.py 3.5 KB runs code
- example/complete-math-reasoning-sft-skill/examples/gsm8k-reasoning-v1/trial_input.jsonl 869 B
- example/complete-math-reasoning-sft-skill/examples/gsm8k-reasoning-v1/trial_output.jsonl 1.5 KB
- example/complete-math-reasoning-sft-skill/SKILL.md 1.6 KB
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 · 104 lines · 36 tokens per session scan A d37d218247c9
curating-dataflow-pipeline-skills is a skill published in the GitHub repository OpenDCAI/Dataflow-LoopAI (24 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 974 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
loopx-change-quality
Qualify the exact final diff for a LoopX-managed goal. Use when goal policy enables changequalityqualification, before a non-trivial delivery or merge, and when producing or repairing an exact-scope quality receipt. The workflow is language-neutral, permits at most one policy-authorized safe-fix pass, and never grants…
install-openviking-memory
Install and configure the OpenViking long-term memory plugin for OpenClaw via natural conversation. Once installed, the plugin automatically captures facts from chats and recalls relevant context before each reply (auto-capture + auto-recall, cross-session). Covers prerequisites, install through OpenClaw's plugin…
knowledge-distillation
Compile one or more OpenViking knowledge bases or document collections into topic-organized, evidence-grounded high-level knowledge, including cross-source findings, trends, changes, drivers, comparisons, implications, and uncertainties. Use with ov compile when the user asks to distill or synthesize a knowledge base…
council-review
Multi-model validation council — auto-validate plans, architecture changes, and PRs via validate-plan/review before executing.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.