layered-design
layered-design
【设计与创意】Web and App implementation guide for Layered Design. Trigger when user wants multiple depth levels, floating panels, and overlapping content.
THE SKILLS DIRECTORY
探索全部技能.
一个技能，一个新的可能。找到适合你的 AI 工作流。
orchestrate
orchestrate
【开发与工程】Coordinate focused subagents on substantial work, keep their ownership non-overlapping, and integrate verified results. Use for large-scope Codex tasks; keep trivial work with the coordinator.
devtu-docs-quality
devtu-docs-quality
【文档与办公】TOP PRIORITY skill — find and immediately fix or remove every piece of wrong, outdated, or redundant information in ToolUniverse docs. Wrong code, broken links, incorrect counts, and overlapping instructions must be fixed or removed — never left in place. Runs five phases: (D) static method scan, (C) static tool-call check, (A) automated validation, …
bio-copy-number-cnv-annotation
bio-copy-number-cnv-annotation
【数据与研究】Annotate copy number variant segments with overlapping genes, dosage-sensitivity scores, cancer driver databases, population frequencies, and clinical-variant content. Covers bedtools/pybedtools interval intersection, AnnotSV comprehensive annotation and ranking, ClinGen haploinsufficiency/triplosensitivity scoring, gnomAD-SV/DGV frequency filtering,…
bio-pathway-enrichment-visualization
bio-pathway-enrichment-visualization
【设计与创意】Turns an enrichResult or gseaResult from clusterProfiler/enrichplot into a figure that collapses or shows gene-set redundancy, using dotplot, barplot, cnetplot, emapplot, treeplot, ridgeplot, gseaplot2, and upsetplot. Covers why a default top-20 GO dotplot is one biological theme drawn twenty times (the DAG/nesting guarantees redundant overlapping te…
bio-rna-quantification-featurecounts-counting
bio-rna-quantification-featurecounts-counting
【效率与协作】Count reads per gene from aligned BAM files using Subread featureCounts. Use when turning STAR/HISAT2 BAMs into a gene-level count matrix for DESeq2/edgeR, deciding library strandedness, handling paired-end fragment counting, choosing how to treat multi-mapping and multi-overlapping reads, or diagnosing a low assignment rate from the summary file.
bio-motif-search
bio-motif-search
【数据与研究】Find sequence motifs, degenerate IUPAC patterns, and transcription-factor binding sites in DNA/RNA using Biopython and regex, including position weight matrix (PWM/PSSM) scoring. Use when locating regulatory elements, counting overlapping motif occurrences, scanning for binding-site matches above a significance threshold, or reading motif matrices fr…
jeo-skill
jeo-skill
【设计与创意】Browse, group, relate, and selectively install the jeo-skills catalog through the lightweight `jeo-skill` CLI. Use when the user wants skills organized by web, infrastructure, game, creative media, CLI tools, AI/agents, engineering, research, business, or utilities; needs a frontend/backend/game-audio/game-VFX subcategory; wants overlapping skills co…
skill-standardization
skill-standardization
【开发与工程】Standardize and validate SKILL.md files against the Agent Skills specification (agentskills.io). Use when creating or rewriting a skill, auditing an existing skill for spec compliance, sharpening trigger descriptions, canonicalizing overlapping skills into a canonical skill plus compatibility alias, or checking whether derived discovery surfaces (`sk…
auditing-game-screen-readability
auditing-game-screen-readability
【设计与创意】Audits what a running game's screen shows at the moments that matter, by capturing frames at gameplay events and at forced coincidences and checking them for overlapping or occluded text, indicators too faint, too small, or too brief to read, HUD elements whose meaning an isolated reader cannot name, and labels no decision depends on. Use when a game…
trueskill-rank
trueskill-rank
【开发与工程】Domain-agnostic TrueSkill batch ranking via LLM-as-judge. Ranks any list of text items using overlapping subsets dispatched to Codex Spark workers. Swappable rubrics. Use when you need to rank, score, curate, or sort a collection by quality.
audit-skill-conflicts
audit-skill-conflicts
【开发与工程】Read-only audit of a skill pack for contradictory directives, overlapping triggers, stale cross-refs, and context bloat. Use when "audit my skills", "conflicting skills", "wrong skill triggered", or after adding a batch. Authoring → meta-skill-creator.
correlating-threat-campaigns
correlating-threat-campaigns
【数据与研究】Correlates disparate security incidents, IOCs, and adversary behaviors across time and organizations to identify unified threat campaigns, attribute them to common threat actors, and extract shared indicators for improved detection. Use when multiple incidents exhibit overlapping indicators, when sector-wide attack campaigns require cross-organizatio…
regulomedb-database
regulomedb-database
【数据与研究】Query RegulomeDB v2 REST API to score variants for regulatory function and retrieve overlapping evidence (TF binding, histone marks, DNase peaks, eQTLs, motifs). Score single rsID/position, batch lists, region searches, and full annotations. Scores range 1a (strongest: eQTL+TF+DNase+motif) to 7 (none). Use for GWAS hit prioritization, regulatory vari…
remap-database
remap-database
【数据与研究】Query ReMap 2022 TF ChIP-seq peak database via REST API and BED downloads. Retrieve TF peaks overlapping a region (chr:start-end), peaks near a gene, TFs by species, peaks filtered by biotype (promoter, enhancer), and BED files for a TF-cell type pair. Use for TF co-occupancy, regulatory annotation, and TF binding atlases. Use jaspar-database for PWM…
technical-debt-assessment
technical-debt-assessment
【数据与研究】Use when auditing a Salesforce org for technical debt: dead code, unused automations, overlapping Flow and Apex triggers, deprecated features, configuration complexity, and legacy patterns. Triggers: technical debt review, org health check, dead code analysis, automation overlap, deprecated features, complexity audit. NOT for implementing the fixes i…
multi-agent-brainstorming
multi-agent-brainstorming
【设计与创意】Use this skill when a design or idea requires higher confidence, risk reduction, or formal review. This skill orchestrates a structured, sequential multi-agent design review where each agent has a strict, non-overlapping role. It prevents blind spots, false confidence, and premature convergence.
ai-roi-audit
ai-roi-audit
【开发与工程】Audit whether the organisation's AI spend actually paid — measured against baselines, not vendor math or vibes. Use when a CFO asks what the AI tools returned, when renewing AI contracts, when consolidating overlapping AI subscriptions, or to build the measurement plan before the next spend. Produces an ROI audit with per-tool verdicts (keep/consolid…
18 / 72