1,229 件 ・ 関連度順
概要と使いどころ
[omh] Recurring lessons worth promoting: turn repeated project or cross-project lessons into atomic, confidence-scored instinct candidates with scoped promotion and export boundaries. Use when the user says: instinct-ledger, instinct ledger, project instincts, project-scoped instincts, project scoped instincts, global instincts, instinct review, instinct candidate.
日本語の概要は準備中です。原文の説明を表示しています。
Analyze Stockbee-style Day 1 Episodic Pivot candidates from earnings, guidance raises, M&A, FDA/regulatory approvals, analyst actions, major contracts, product launches, short-squeeze catalysts, or theme/story events. Scores catalyst quality together with gap/range expansion, volume shock, neglect/revaluation context, liquidity, and risk to the EP-day low. Use when the user asks for EP candidates, episodic pivots, Day 1 catalyst trades, game-changing news reactions, delayed EP watchlists, or handoffs into PEAD monitoring.
日本語の概要は準備中です。原文の説明を表示しています。
Build a Stockbee-style setup model book from momentum-burst screener candidates, then update 3-day and 5-day forward outcomes with MFE/MAE, stop-hit status, outcome tags, and cohort statistics. Use when the user wants to study Stockbee Momentum Burst examples, track failed candidates, build setup fluency, review A/B setup quality, or convert screener outputs into a learning loop rather than immediate trade signals.
日本語の概要は準備中です。原文の説明を表示しています。
Use when the user asks to "pick a launch date", "plan the launch window", or "set the embargo and lift time"; produces a candidate-window comparison table (conflict / tailwind / risk per window) built from industry-event cycles and the competitor launch calendar, a launch-week vs rolling-release format call, store-review buffer padding (labeled Estimated), and an embargo window definition (lift moment + timezone) submitted to the launch registry as a candidate. Not for judging the cultural moment itself — use trend-spotter; not for launch-day execution — use launch-day-conductor. 发布择时/发布窗口/竞品日历/禁运期窗口/审核缓冲
日本語の概要は準備中です。原文の説明を表示しています。
SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
日本語の概要は準備中です。原文の説明を表示しています。
Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened tests and false completion claims, and delivers an evidence-based verdict (VERIFIED / VERIFIED WITH CAVEATS / REFUTED). Use after any agent or model claims work is complete - "/fable-judge", "judge this work", "verify what it did", "did that actually work?". Also runs the fable-method trap suite against a skill or model via "/fable-judge suite TARGET".
日本語の概要は準備中です。原文の説明を表示しています。
Geolocate or chronolocate a photo with tool-verified reasoning (where was this taken / when was it taken / photo geolocation / geo-guessing). Given one or more photos, intake.py does metadata, OCR and reverse image search (Baidu/Yandex) in one command; clues and candidates go on a candidate board (board.py) that ranks them and gives the next step; clues.py looks up calling codes, driving side, plates and area codes from region packs; for satellite and street view the machine ranks first and you look only at the top few (CLIP in sat_scan.py, DINOv2+SIFT in match.py); plus sun and shadow math, OSM Overpass and DEM skylines. Every conclusion is checked against real data; output is coordinates + error radius, evidence images and tiered confidence. Use when the user shares a photo and asks where was this taken / geolocate this / when was this taken / 这是哪 / 在哪拍的 / 帮我定位这张照片 / 网络迷踪 / 图寻 / 几点拍的.
日本語の概要は準備中です。原文の説明を表示しています。
DiDi ride-hailing service skill. Supports taxi booking, price estimation, route planning (driving/transit/walking/cycling), order management, driver location tracking, and scheduled rides. Use when user expresses any transportation need including ride-hailing, route queries, or commuting.
日本語の概要は準備中です。原文の説明を表示しています。
Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation. **Trigger when user asks to:** - Migrate or convert PostgreSQL tables to hypertables - Execute hypertable migration with minimal downtime - Plan blue-green migration for large tables - Validate hypertable migration success - Configure compression after migration **Prerequisites:** Tables already identified as candidates (use find-hypertable-candidates first if needed) **Keywords:** migrate to hypertable, convert table, Timescale, TimescaleDB, blue-green migration, in-place conversion, create_hypertable, migration validation, compression setup Step-by-step migration planning including: partition column selection, chunk interval calculation, PK/constraint handling, migration execution (in-place vs blue-green), and performance validation queries.
日本語の概要は準備中です。原文の説明を表示しています。
Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit findings, or a critique you did not write yourself, especially when the reviewer is a model or when the volume is too large to check by feel.
日本語の概要は準備中です。原文の説明を表示しています。
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
日本語の概要は準備中です。原文の説明を表示しています。
Drive structured autoresearch iteration after evo:discover and the baseline commit. Use when the user invokes /evo:optimize or asks to try ideas, try variants, run experiments, use available GPUs, improve the current best/frontier, continue an evo search, or compare candidate changes in an evo workspace. The orchestrator plans and spawns optimization subagents; candidate edits/runs belong to those subagents. Width is set via subagents=N (1 for serial workloads, larger for parallel); the loop's structural value applies at any width.
日本語の概要は準備中です。原文の説明を表示しています。
Build boolean and X-ray search strings to source candidates. Use when asked to build a boolean search, source candidates on LinkedIn/Google, write an X-ray search, or find people with specific skills. Produces ready-to-paste boolean strings (with synonyms, must-haves, and exclusions), X-ray variants for LinkedIn/GitHub, and a refinement plan to widen or narrow the result set.
日本語の概要は準備中です。原文の説明を表示しています。
Search Ashby public job boards (no key needed) and read/write the Ashby ATS: candidates, jobs, applications. Trigger phrases: ashby, job board, candidates, hiring, job search.
日本語の概要は準備中です。原文の説明を表示しています。
Detect hardcoded sensitive data (API keys, access tokens, private keys, passwords, etc.) in publicly accessible code — frontend JavaScript, mobile apps, client-side bundles, and HTML templates. Uses a three-phase approach: recon (find secret candidates), batched verify (confirm real secrets in public code paths, 3 candidates each), and merge (consolidate batch results). Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/hardcodedsecrets-results.md. Use when asked to find hardcoded secrets, leaked API keys, or exposed credentials.
日本語の概要は準備中です。原文の説明を表示しています。
Detect Insecure Direct Object Reference (IDOR) vulnerabilities in a codebase using a three-phase approach: recon (find candidates), batched verify (check authorization in parallel subagents, 3 candidates each), and merge (consolidate batch results). Checks endpoints for missing ownership or authorization checks on user-supplied identifiers. Requires sast/architecture.md (run sast-analysis first). Outputs findings to sast/idor-results.md. Use when asked to find IDOR or authorization bypass bugs.
日本語の概要は準備中です。原文の説明を表示しています。
Use when picking the next Spark expression to implement natively in Comet, or when asked whether a specific codegen-dispatched expression is worth a native Rust implementation. Scores the candidate on how likely a native path can be 100% Spark-compatible and how much throughput or allocation it would save versus the JVM codegen dispatcher, records the verdict in the per-expression audit log so disqualified candidates are not re-litigated, and files a GitHub issue for the recommendation.
日本語の概要は準備中です。原文の説明を表示しています。
Identity verification via phone/email OTP and AML screening using Didit API
日本語の概要は準備中です。原文の説明を表示しています。
Nominates and assesses CRISPR off-target sites genome-wide. Enumerates candidate sites by mismatch and bulge tolerance with Cas-OFFinder/CRISPRitz, ranks them with the published CFD score (SpCas9-only, relative ranker) or MIT/CRISTA/energy models, runs variant-aware screening against gnomAD/individual genomes (CRISPRme), and frames the empirical genome-wide discovery assays (GUIDE-seq, CIRCLE-seq, CHANGE-seq, DISCOVER-seq, Digenome-seq) and high-fidelity nuclease choice (HiFi Cas9, Sniper-Cas9, eSpCas9, SpCas9-HF1). Use when assessing guide RNA specificity, choosing among candidate guides, screening a therapeutic guide against population variation, or planning empirical off-target validation. Distinguishes predicted vs detected vs validated. On-target activity scoring and deaminase (Cas-independent) base/prime-editor off-targets are separate skills.
日本語の概要は準備中です。原文の説明を表示しています。
Rank and prioritize neoantigen/epitope candidates by likely T-cell response using NeoFox feature annotation, PRIME2.0, BigMHC-IM, the Łuksza/Balachandran fitness model (agretopicity + foreignness), and pVACtools tiering. Encodes the field's hard truths that immunogenicity is the least-solved layer (dedicated scores ~AUROC 0.6-0.7, modest PPV), that scores are valid only for RANKING within one patient (never absolute go/no-go or cross-patient), that DAI has anchor-inflation and WT-denominator traps, and that stacking weak correlated scores into one number is a red flag. Use when ordering a candidate list for a vaccine. Binding lives in mhc-binding-prediction; calling in neoantigen-prediction.
日本語の概要は準備中です。原文の説明を表示しています。
Predict peptide-MHC class I binding and natural presentation with MHCflurry, NetMHCpan-4.1, and MixMHCpred to nominate candidate CD8 T-cell epitopes. Covers the binding-affinity (BA) vs eluted-ligand (EL/presentation) distinction, why %Rank beats raw nM for cross-allele work, the MS abundance bias that misranks low-expression neoantigens, allele-coverage inequity, and length bias. Use when scanning a protein or peptide set for class I epitopes, scoring neoantigen candidates, or choosing a binding predictor. For CD4/HLA class II see mhc-class-ii-prediction.
日本語の概要は準備中です。原文の説明を表示しています。
Maps GWAS-implicated loci to candidate effector (causal) genes by integrating variant-to-gene (V2G) features via Open Targets L2G (Mountjoy 2021), MAGMA gene-based association (de Leeuw 2015), FUMA SNP2GENE, cS2G combined SNP-to-gene scores (Gazal 2022), Polygenic Priority Scores (PoPS, Weeks 2023), FLAMES, INQUISIT, DEPICT, and enhancer-gene predictors (ABC, ENCODE-rE2G). Use when narrowing a GWAS lead locus to a candidate causal gene, picking between proximity, eQTL-based, and similarity-based prioritizers, integrating multi-evidence streams (fine-mapping, colocalization, ABC enhancer-gene, distance, chromatin), reconciling discordant L2G vs PoPS calls, prioritizing tissue-specific eQTL evidence, or triangulating across at least three independent lines of evidence for a publication-grade effector-gene nomination.
日本語の概要は準備中です。原文の説明を表示しています。
Runs LiveKit agent simulations and acts on the results. Use when the user says "run my simulations", "regression test my agent before deploying", "run the scenarios", "use lk agent simulate", "did my agent pass", "why did this scenario fail", "run simulations in CI", "test the audio pipeline", "check turn-taking and interruptions", or wants to check whole-conversation behavior before shipping. Covers text and audio mode and what each catches, running against a local or deployed agent, degraded-audio flags, automating a pre-release run, and triaging failures with list, view and export. For writing the scenarios use writing-livekit-scenarios. Not the default for a bare "test my agent", which goes to debugging-livekit-agents. Use this skill when the user names simulations, scenarios, a run, CI, or shipping.
日本語の概要は準備中です。原文の説明を表示しています。
Compare several Japanese NLP libraries, models, or datasets for a keyword (a specific tool name, or a function/task like '形態素解析') across a handful of criteria chosen for that comparison, rendered as a ○/△/✕ table. Use when the user wants a side-by-side comparison of multiple Japanese NLP tools/libraries/datasets, not just the single best one. Trigger phrases include 'X と Y と Z を比較して', '形態素解析ライブラリを比較', 'MeCab と Sudachi どっちがいい', 'どのツールを使うべき', 'compare japanese tokenizers', 'mecab vs sudachi vs janome', 'which embedding model should I use', '日本語NERライブラリの比較表', 'pros and cons of japanese OCR tools'. For a single ranked list use search; for alternatives to one specific tool (or contribution candidates) without a multi-axis table, use discover.