CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

This is a well-engineered workflow skill: fully executable commands, a phased pipeline with real validation gates and bounded failure budgets, and disciplined delegation to shared reference files. The residual issues are token-efficiency — a few explanations of failure modes Claude would diagnose on its own — and a couple of large inline blocks that belong in reference files.

Suggestions

Trim the failure-classification table in Phase 3 (OOM → reduce batch size, ImportError → install package, etc.) to just the budget and reimplantation policy — Claude already knows how to diagnose these standard errors.

Move the ~50-line Codex review prompt template (including the scope-limits preamble) into a referenced file (e.g. references/code-review-prompt.md), keeping only the invocation and a one-line summary in Phase 2.5.

Relocate the dense reviewer-routing blockquote at the top of the body into the already-referenced reviewer-backends.md, leaving a single-line pointer in SKILL.md.

DimensionReasoningScore

Conciseness

The body is dense with operational policy that Claude cannot infer (routing thresholds, debug budgets, deletion rules, cost lifecycle), but contains a few over-explanations of things Claude already knows — e.g. "OOM → reduce batch size", "ImportError → install missing package" — and a long embedded scope-limits preamble in the review prompt, fitting the efficient-with-minor-trimmings anchor 4 rather than lean anchor 5.

4 / 5

Actionability

Guidance is copy-paste ready: a complete mcp__codex__codex call with model/config/prompt, exact `git clone` and `/run-experiment` / `/experiment-queue` invocations, a concrete auto-routing rule ("≥10 jobs" with a worked 36-job example), and full markdown templates for every output artifact — matching the fully-executable anchor.

5 / 5

Workflow Clarity

Phases 1–6 are clearly sequenced with explicit validation checkpoints and feedback loops: sanity-stage gate before full deployment, review-fix-resubmit loop (max 2 rounds), a bounded auto-debug budget (2 patches + 2 reimplements), an AUTO_DEPLOY=false deploy checkpoint, and success-criteria checks — matching the anchor-5 pattern despite this being a batch GPU deployment skill.

5 / 5

Progressive Disclosure

No bundle files ship with this skill, but the body consistently pushes detail to clearly-signaled one-level references ([reviewer-backends.md](../shared-references/...), compute-env-contract.md §5, output-versioning.md, skills/experiment-queue/SKILL.md) each with stated purpose. It stays at 4 rather than 5 because the ~50-line Codex review prompt template and the dense reviewer-routing blockquote are inlined where a reference file would serve better, and the shared-references paths fall outside this bundle.

4 / 5

Total

18

/

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: it states a concrete multi-step capability chain and includes an explicit, bilingual 'Use when' trigger list. Its only weaknesses are slightly incomplete capability coverage and one generic trigger term ("bridge") that creates minor conflict risk.

DimensionReasoningScore

Specificity

Lists several concrete pipeline actions — "Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results" — matching the several-specific-actions anchor, but notable capabilities (cross-model code review, ablation planning, result tracking) are absent, so it falls short of the comprehensive-coverage anchor 5.

4 / 5

Completeness

Explicitly answers both questions: the 'what' is the read-plan → implement → deploy → collect chain, and the 'when' is a literal "Use when user says ..." clause with concrete trigger phrases, matching the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Six natural trigger phrases are quoted verbatim — "implement experiments", "deploy the plan", "实现实验", "从计划到跑实验", "bridge", "has an experiment plan ready to execute" — covering English and Chinese synonyms plus a state-based trigger, which matches the comprehensive natural-terms anchor.

5 / 5

Distinctiveness Conflict Risk

The EXPERIMENT_PLAN.md / research-pipeline framing carves a clear niche distinct from generic experiment-running skills, but the bare trigger "bridge" is generic enough to risk minor overlap with other bridging/orchestration skills, matching the mostly-distinct-minor-overlap anchor.

4 / 5

Total

18

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

relative_links

Relative link issues: 5 suspicious

Warning

Total

13

/

16

Passed

Repository

wanshuiyin/Auto-claude-code-research-in-sleep

Path

skills/experiment-bridge/SKILL.md

Reviewed

Table of Contents

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.