aris-experiment-bridge

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

70%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A thorough, well-sequenced multi-phase workflow with strong validation and feedback loops. It loses points on conciseness for length/padding and on progressive disclosure for inlining large template blocks that could be split into reference files.

Suggestions

Tighten or relocate repeated template blocks (Phase 5 results summary, Phase 6 handoff, composition diagram) to cut length and reduce redundancy.

Move the large results-summary and compact-log markdown templates into a references/ file (e.g. RESULTS_TEMPLATE.md) and link one level deep, improving progressive disclosure.

Replace the high-level 'implement missing pieces' bullet list with at least one concrete minimal experiment-script skeleton to lift actionability.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-organized, but ~350 lines with some padded recap sections (e.g., repeated handoff/composition blocks, full ASCII diagrams) that could be tightened without losing clarity.	3 / 5
Actionability	Concrete commands and templates throughout (nvidia-smi query, codex review prompt block, results-summary markdown), though some experiment-script guidance remains high-level rather than executable.	4 / 5
Workflow Clarity	Clear phased sequence (Phase 0–6) with explicit validation checkpoints (compute guard, sanity check, code review) and a robust validate→diagnose→fix→retry feedback loop including escalation.	5 / 5
Progressive Disclosure	Well-structured into sections but entirely self-contained with no bundle files and references to sibling skills inline; long template blocks (e.g., Phase 5 results summary) could live in separate reference files.	3 / 5
	Total	15 / 20 Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: concise, concrete, with explicit bilingual trigger phrases and clear what/when structure. Slightly short of fully comprehensive action coverage, which keeps specificity at 4.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results' — but stops short of fully comprehensive coverage of all sub-steps.	4 / 5
Completeness	Clearly answers both 'what' (read plan, implement, deploy, collect results) and 'when' via an explicit 'Use when...' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including bilingual phrases ('实现实验', '从计划到跑实验') and explicit English variations like 'implement experiments', 'bridge', 'deploy the plan'.	5 / 5
Distinctiveness Conflict Risk	Niche 'Workflow 1.5 bridge between idea discovery and auto review' is clearly distinct from adjacent skills, with trigger phrases unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-experiment-bridge/SKILL.md
Commit: 4b35756

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.