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
Advisory
Suggest reviewing before use
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 the skill's purpose as a chained pipeline of two specific sub-skills, provides explicit 'Use when' triggers including both English and Chinese terms, and is highly distinctive due to its specific workflow composition. The description is concise yet comprehensive, covering what the skill does, what it produces, and when to invoke it.
| 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 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', 'method and experiment plan together', '串起来', and 'vague research direction to focused final proposal'. These cover both English and Chinese user phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive: it specifically describes chaining two named sub-skills ('research-refine' and 'experiment-plan') into a pipeline, which clearly differentiates it from either individual skill or generic research/planning 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 decision points. Its main strength is the clear workflow with explicit gate checks between method refinement and experiment planning. Minor redundancy between Phase 1 exit criteria and Phase 2 gate questions is the primary weakness, but overall the content is actionable, well-organized, and appropriately scoped.
| 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 bullet points could be tightened, though overall it respects Claude's intelligence and avoids explaining obvious concepts. | 2 / 3 |
Actionability | The skill provides concrete file paths, specific output templates (PIPELINE_SUMMARY.md with exact markdown structure), clear phase-by-phase instructions, and explicit decision criteria (e.g., when to reuse vs re-run). The large file handling fallback is a specific, executable instruction. The user-facing summary template is copy-paste ready. | 3 / 3 |
Workflow Clarity | The five-phase workflow is clearly sequenced with explicit validation gates—Phase 0 triages whether to skip ahead, Phase 1 has clear exit criteria, Phase 2 is a dedicated gate check before proceeding, and the core rule ('do not plan experiments on an unstable method') provides a strong feedback loop. The 'if in doubt, prefer re-running' guidance handles error recovery well. | 3 / 3 |
Progressive Disclosure | The skill clearly references sibling skills (`../research-refine/SKILL.md`, `../experiment-plan/SKILL.md`) with the instruction to read them 'only when needed.' The composing section at the bottom provides clean navigation. Content is appropriately split—stage-specific details live in their respective skills while this file focuses on orchestration. | 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
dc00dfb
- 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.