research-refine-pipeline
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly articulates what the skill does (chains two specific sub-skills into a pipeline producing a proposal and experiment roadmap), when to use it (with explicit trigger phrases including multilingual terms), and occupies a distinct niche. The inclusion of both English and Chinese trigger terms and multiple phrasings makes it robust for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists concrete actions: chains 'research-refine' and 'experiment-plan', transforms a vague research direction into a focused final proposal plus detailed experiment roadmap. These are specific, concrete outcomes. | 3 / 3 |
Completeness | Clearly answers both 'what' (chains research-refine and experiment-plan into an end-to-end workflow producing a focused proposal and experiment roadmap) and 'when' (explicit 'Use when' clause with multiple trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'one-shot pipeline', 'end-to-end', 'build a pipeline', 'generate both the method and experiment plan together', and even the Chinese term '串起来'. Good coverage of how users would naturally phrase this request. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it specifically describes a chained pipeline of two named sub-skills ('research-refine' and 'experiment-plan'), targeting the niche of end-to-end research-to-experiment workflows. Unlikely to conflict with either individual skill or unrelated skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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-structured orchestration skill that clearly sequences a multi-phase research pipeline with appropriate validation gates and concrete output templates. Its main strength is the clear workflow with explicit checkpoints (especially the Planning Gate) and good progressive disclosure to sibling skills. Minor redundancy between Phase 1 exit criteria and Phase 2 gate questions, plus some slightly verbose sections, prevent a perfect conciseness score.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy—Phase 2's gate check questions largely repeat the exit criteria from Phase 1. Some sections like the 'Composing with Other Skills' block and the overview could be tightened. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete file paths, specific output templates with markdown structure, clear phase-by-phase instructions, and exact criteria for gate checks. The Pipeline Summary template and user-facing summary are copy-paste ready. The guidance is specific enough to execute without ambiguity. | 3 / 3 |
Workflow Clarity | The five-phase workflow is clearly sequenced with explicit validation gates. Phase 0 includes a triage check for existing work, Phase 2 is a dedicated planning gate with crisp pass/fail criteria, and the core rule ('do not plan experiments on an unstable method') provides a clear feedback loop. The 'if in doubt, prefer re-running' guidance handles edge cases well. | 3 / 3 |
Progressive Disclosure | The skill serves as a clear orchestration overview, pointing to sibling skills (`../research-refine/SKILL.md`, `../experiment-plan/SKILL.md`) and shared protocols (output versioning, manifest, language) with one-level-deep references. Content is appropriately split—stage-specific details are deferred to the referenced skills. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
700fbe2
- 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.