# Send Research Paper Quality Filter to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "quality-filter-research", "name": "Research Paper Quality Filter", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/nomorecoding/quality-filter-research", "canonicalUrl": "https://clawhub.ai/nomorecoding/quality-filter-research", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/quality-filter-research", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=quality-filter-research", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "README.md", "SKILL.md", "_meta.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "quality-filter-research", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-08T05:13:47.116Z", "expiresAt": "2026-05-15T05:13:47.116Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=quality-filter-research", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=quality-filter-research", "contentDisposition": "attachment; filename=\"quality-filter-research-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "quality-filter-research" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/quality-filter-research" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/quality-filter-research", "downloadUrl": "https://openagent3.xyz/downloads/quality-filter-research", "agentUrl": "https://openagent3.xyz/skills/quality-filter-research/agent", "manifestUrl": "https://openagent3.xyz/skills/quality-filter-research/agent.json", "briefUrl": "https://openagent3.xyz/skills/quality-filter-research/agent.md" } } ``` ## Documentation ### Quality Filter Skill This skill provides systematic quality filtering for academic papers with a rigorous scoring system and complete audit trail for research workflows. ### Capabilities Relevance Scoring: Evaluates paper relevance based on title and abstract keywords Quality Assessment: Assesses technical quality and experimental rigor Comprehensive Logging: Maintains detailed records of all filtering decisions Manual Recall Support: Preserves filtered papers for potential human review Local File Storage: Saves all results to organized directory structure ### Relevance Scoring (Max 3 points) Strong Match (+3): Title contains "music" or "song" keywords Medium Match (+2): Title contains "audio" + "generation" Weak Match (+1): Title has weak but related keywords Negative Scoring: Abstract verification can subtract points (-1 to -3) ### Quality Assessment (Max 3 points) High Quality (+3): Complete experiments, multiple baselines, strong results Medium Quality (+2): Experiments present but limited baseline comparison Low Quality (+1): Limited technical contribution or incomplete evaluation ### Pass Threshold Minimum Score: 6/10 points required to pass filtering Strong Relevance Override: Papers with clear "music/song generation" focus may pass with lower scores ### Workflow Integration This skill integrates with the broader research workflow: Input: Raw paper list from arXiv search Processing: Applies scoring system to each paper Output: Categorizes papers as "passed" or "filtered" Audit Trail: Maintains complete record for manual recall ### Local File Storage Main Log: research/{domain}/quality_filtering/quality_filtering_log.md Append Mode: All results appended to single comprehensive file Directory Structure: Automatically created if missing ### Log Structure Each filtering session includes: Session Header: Date, domain, search parameters Scoring Standards: Detailed criteria used Individual Paper Results: Title, authors, score breakdown, decision Summary Statistics: Pass/fail counts, score distribution Manual Recall Section: List of filtered papers available for human review ### Usage Examples # Filter music generation papers quality_filter --domain "music_generation" --papers "[paper_list]" --date "2026-02-28" # Filter with custom threshold quality_filter --domain "speech_audio" --threshold 5 --papers "[paper_list]" ### Files Created research/{domain}/quality_filtering/quality_filtering_log.md (append mode) Directory structure automatically created if missing ### Audit Trail Requirements All filtering decisions must include: Complete score breakdown (relevance + quality components) Clear pass/fail rationale Preservation of filtered papers for manual recall Timestamp and session context ## Trust - Source: tencent - Verification: Indexed source record - Publisher: nomorecoding - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-08T05:13:47.116Z - Expires at: 2026-05-15T05:13:47.116Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/quality-filter-research) - [Send to Agent page](https://openagent3.xyz/skills/quality-filter-research/agent) - [JSON manifest](https://openagent3.xyz/skills/quality-filter-research/agent.json) - [Markdown brief](https://openagent3.xyz/skills/quality-filter-research/agent.md) - [Download page](https://openagent3.xyz/downloads/quality-filter-research)