research-pipeline
Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop) → Workflow 3 (paper writing, optional). Goes from a broad research direction all the way to a polished PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
92
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
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 skill description that clearly defines a multi-stage research pipeline with specific workflow steps, concrete outputs, and explicit bilingual trigger terms. It effectively communicates both what the skill does and when to use it, with minimal risk of conflicting with more narrowly scoped research skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions in a pipeline: idea discovery, implementation, auto review loop, and paper writing. Also specifies the output ('polished PDF') and references numbered workflows. | 3 / 3 |
Completeness | Clearly answers both 'what' (full research pipeline from idea discovery through implementation, review, and paper writing to polished PDF) and 'when' (explicit 'Use when' clause with specific trigger phrases). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms in both English and Chinese: '全流程', 'full pipeline', '从找idea到投稿', 'end-to-end research', 'complete autonomous research lifecycle'. These are terms users would naturally say when requesting this capability. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive as a full end-to-end research pipeline skill. The numbered workflow references (Workflow 1, 2, 3) and specific trigger terms like '全流程' and 'end-to-end research' clearly distinguish it from individual research sub-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 for a complex multi-stage research pipeline. Its strengths are excellent workflow clarity with explicit gates, feedback loops, and stop conditions, plus strong actionability with concrete commands and file paths at every stage. The main weakness is moderate verbosity — some explanations are repeated (AUTO_PROCEED behavior appears in multiple places) and a few sections could be tightened without losing clarity.
Suggestions
Consolidate the AUTO_PROCEED explanation — it's described in Constants, Gate 1, the warning box, and Key Rules. A single authoritative definition in Constants plus brief references elsewhere would save ~15 lines.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines) and includes some unnecessary elaboration (e.g., the detailed Gate 1 user interaction options, the 'Sweet spot' lifestyle tip, repeated explanations of AUTO_PROCEED behavior). However, most content is genuinely informative for orchestrating a complex multi-stage pipeline, so it's not egregiously verbose. | 2 / 3 |
Actionability | The skill provides concrete, executable commands at each stage (e.g., `/idea-discovery`, `/run-experiment`, `/auto-review-loop`, `/paper-writing`), specific file paths for inputs/outputs, exact gate logic with AUTO_PROCEED behavior, and detailed output templates. The guidance is copy-paste ready and leaves little ambiguity about what to do. | 3 / 3 |
Workflow Clarity | The 6-stage pipeline is clearly sequenced with explicit gates (Gate 1, Gate 2), validation checkpoints (code self-review in Stage 2, pre-writing checks in Stage 6), feedback loops (re-run Stage 1 on rejection, auto-review loop up to 4 rounds with score threshold), and clear stop conditions (round 4 cap, fail gracefully rule). The routing logic for small vs large batch is also well-specified. | 3 / 3 |
Progressive Disclosure | The skill serves as a clear orchestration overview that delegates to sub-workflows (`/idea-discovery`, `/auto-review-loop`, `/paper-writing`) and references shared protocols via links (output versioning, manifest, language). Content is appropriately split — each stage describes what it does and what it delegates, without inlining the sub-workflow details. References are one level deep and clearly signaled. | 3 / 3 |
Total | 11 / 12 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 — 9 / 11 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 | 9 / 11 Passed | |
- 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.