2,409 件 ・ 関連度順
概要と使いどころ
Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.
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。
Persistent compounding memory for AI agents. 5 default MCP tools: session_start, session_end, remember, recall, check. Full surface (18 tools) available with --full flag. Two-verb model: inhale (session_start) and exhale (session_end). Correction-first memory with decision trail tracking, watch_for warnings, palace rooms with salience scoring, cross-project insight matching, same-day journal merging, ambient recall hooks. Local markdown only. Zero cloud, zero telemetry, Obsidian-compatible. Optional Supabase backend: when configured via `ar setup supabase`, recall() uses pgvector cosine similarity on OpenAI/Voyage embeddings instead of keyword search — same API, semantic understanding. Gracefully degrades to local search if not configured.
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。
Verify that code changes are correct, safe, and ready to ship. Use this skill after implementing changes, before pushing or creating a PR. Also use when the user says "check", "verify", "review", "QA", "is this ready", or when you want to validate work done by the developer skill. Runs build, lint, and structural checks.
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。
Execute code changes following an approved plan or direct user instructions. Use this skill when the user says "implement", "code it", "go ahead", "execute the plan", or when transitioning from the planner skill after approval. Also use for direct coding tasks where the user provides clear, specific instructions. This skill writes clean, correct code respecting all project conventions.
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。
Run the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace, résumé styling, contract redlining + commenting, contract finalize via accept/reject + comment reply/resolve) and one authoring (T. S. Eliot poetry journal: multi-column, verse, footnotes, links, figure) — renders every result with Word, has opus judge them against ground-truth rubrics, measures each exercise's tool economy, token cost, wall-clock, and correctness (from transcripts for Claude, the exercise.json ledger for the local harness), and synthesizes a prioritized ergonomics report. Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.
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。
Judgment rules for locating the correct boundary of a requested change: staying inert outside it while completing every required site inside it. Use when scope is ambiguous, a diff touches neighboring surfaces, required dependent edits are unclear, or a proposed compatibility layer, migration, fallback, flag, abstraction, or parallel implementation may exceed the request.
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。
Proofread and correct text for grammar, spelling, punctuation, style, clarity, and consistency, with support for multiple style guides and readability analysis. Use when the user requests proofreading or provides relevant inputs for this workflow.
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。
Clean and preprocess datasets by handling missing values, removing duplicates, correcting types, resolving outliers, and enforcing validation schemas. Use when the user requests data cleaning or provides relevant inputs for this workflow.
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 datasets to answer defined questions through statistical methods, trend identification, hypothesis testing, and correlation analysis. Use when the user needs evidence-backed findings or decisions from data; use exploratory-data-analysis instead for open-ended first-pass profiling before questions are defined.
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。
Think and work like an expert Mammalogist. Use when a task calls for Mammalogist judgment. Reasons from mammalian life history and detectability-limited sampling through ASM MDD taxonomy, Sherman/camera-trap/SCR survey design, occupancy and SECR models, bat acoustic validation, and museum voucher discipline while treating trap heterogeneity, camera autocorrelation, closure violation, and WNS decontamination gaps as first-class failure modes.
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。
Think and work like an expert Laser Physicist. Use when a task calls for Laser Physicist judgment. Reasons from population inversion and threshold gain (g ≥ l/L + T), ABCD resonator stability (g₁g₂ in 0–1) and c/(2L) mode spacing, GVD/TOD dispersion management and time-bandwidth ΔtΔν ≈ 0.44, and Kerr/SPM nonlinear phase through Kerr-lens/SESAM mode-locking, CPA stretcher–amplifier–compressor with B-integral budgeting, QPM in PPLN/PPLKTP for SHG/OPA, FROG/SPIDER and Dazzler pulse shaping, M² caustics per ISO 11146, and IEC 60825 classification while treating thermal-lens drift out of the stability zone, autocorrelation-width-mistaken-for-pulse-width, uncompensated TOD wings and regen double-pulsing, and LMA-fiber mode instability and SRS/SBS above kW as first-class failure modes.
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。
Think and work like an expert Mathematical Modeler. Use when a task calls for Mathematical Modeler judgment. Reasons from nondimensionalization, conservation/positivity laws, and minimal-viable model structure through mechanistic ODE/PDE, stochastic, and agent-based formulations, profile-likelihood and Fisher-information identifiability, and Sobol/Morris sensitivity analysis, while treating sloppy unidentifiable parameters, structural model uncertainty, and out-of-regime extrapolation as first-class failure modes.
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。
Think and work like an expert Geographic Information Scientist (GIS). Use when a task calls for Geographic Information Scientist (GIS) judgment. Reasons from location, topology, scale, and positional uncertainty through PostGIS/GDAL pipelines, explicit EPSG/datum choices, kriging with cross-validated variograms, and ISO 19115/FGDC metadata while treating MAUP and ecological fallacy, Web Mercator area statistics, floating-point slivers and broken topology, and spatial-autocorrelation-inflated significance as first-class failure modes.
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。
Think and work like an expert Geotechnical Scientist. Use when a task calls for Geotechnical Scientist judgment. Reasons from Terzaghi effective stress, Mohr–Coulomb/CSSM, and consolidation/seepage through SPT/CPTU (Robertson SBT), triaxial/oedometer (ASTM D-series), Boulanger–Idriss liquefaction, Hoek–Brown/GSI rock mass, EC7 characteristic values, and PLAXIS/Slide2/RS2/GeoStudio workflows while treating sample disturbance, N-value correction chains, spatial variability, and LEM-vs-FEM mismatch as first-class failure modes.
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。
Think and work like an expert Glaciologist. Use when a task calls for Glaciologist judgment. Reasons from mass-budget closure (SMB, dynamic discharge, calving), Glen flow law, and subglacial effective pressure through WGMS/GlaMBIE stake networks, ICESat-2/CryoSat altimetry with firn and radar-penetration corrections, ITS_LIVE velocities, ApRES basal melt, RES/MCoRDS bed picks, RGI/BedMachine inventories, OGGM mountain-glacier projections, and PISM/ISSM ISMIP6/7 protocols while treating firn-compaction aliasing, DEM penetration bias, GRACE leakage/GIA, and tidal InSAR artifacts as first-class failure modes.
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。
Think and work like an expert Geodesist. Use when a task calls for Geodesist judgment. Reasons from coordinates as four-dimensional objects with epoch, velocity, and frame realization (ITRS vs. ITRF2020, WGS84) through GAMIT/GLOBK and Bernese PPP-AR, SBAS/PS-InSAR with GACOS atmospheric correction, IERS Conventions, and 14-parameter Helmert transforms while treating ITRF-realization switches, undocumented APC/ATX mismatches, monument motion, and unscreened seasonal loading as first-class failure modes.
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。
Think and work like an expert Embedded Systems Engineer. Use when a task calls for Embedded Systems Engineer judgment. Reasons from hardware timing, interrupt latency, memory maps, and deterministic WCET resource bounds through DWT CYCCNT and Saleae logic-analyzer timing proofs, SWD/JTAG (J-Link/OpenOCD) with CFSR/HFSR/BFAR fault decode, FreeRTOS/Zephyr respecting configMAX_SYSCALL_INTERRUPT_PRIORITY, MISRA C:2012 and ISO 26262 ASIL discipline, Nordic PPK2 power profiling, and MCUboot signed OTA while treating priority inversion, Cortex-M7 uncached-DMA D-cache incoherence, CAN bus-off, I2C NACK storms, and brownout-during-flash-write NVS corruption as first-class failure modes.
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。
Think and work like an expert Evolutionary Biologist. Use when a task calls for Evolutionary Biologist judgment. Reasons from coalescent demography, MSC gene-tree discordance, and selection–drift nulls; runs IQ-TREE/BEAST/ASTRAL/ANGSD workflows while treating LBA, rogue taxa, batch effects, and uncorrected genome scans as first-class failure modes.
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。
Think and work like an expert Electronic Materials Engineer. Use when a task calls for Electronic Materials Engineer judgment. Reasons from band alignment, defect chemistry, and process–structure–property links; correlates Hall, C–V (Dit), XRD/RSM, SIMS, and ALD/MOCVD/sputtering recipes while treating dopant activation vs. chemical dose, high-κ trap charging, and reliability (NBTI/TDDB) as first-class failure modes.
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。
Think and work like an expert Entomologist. Use when a task calls for Entomologist judgment. Reasons from tagmata, Comstock-Needham venation, and tarsal formula through trap-guild sampling (Malaise, pitfall, pan, light), host–parasitoid ecology, ICZN vouchers and genitalia keys, BOLD/GBIF/COL/iNaturalist triage, IUCN invertebrate caveats, CITES/COSE permits, Taylor/GLMM on the correct EU, and EIL/ET with IRAC MoA rotation while treating teneral, dimorphic, and cryptic mis-IDs as first-class failure modes.
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。
Think and work like an expert Crop Scientist. Use when a task calls for Crop Scientist judgment. Reasons from genotype-by-environment-by-management interaction, yield-component partitioning, and phenology-gated critical periods through MET stability analysis (AMMI, Finlay-Wilkinson, GGE biplots), mixed models (ASReml-R, lme4), N-response curves (quadratic-plateau, MRTN), and crop models (APSIM, DSSAT) while treating pseudo-replicated subsamples, single-site yield champions, uncorrected harvest moisture, and weather-during-anthesis confounding as first-class failure modes.
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。
Think and work like an expert Database Systems Researcher. Use when a task calls for Database Systems Researcher judgment. Reasons from storage hierarchy, concurrency semantics, query-optimization theory, and declared workload models through TPC-C/H, YCSB, and JOB benchmarks, Jepsen/Elle correctness checkers, and perf/blktrace/fio profiling while treating cardinality-estimation plan regressions, tail-latency spikes under skew, unfair fsync-disabled speedups, and benchmark-trick wins as first-class failure modes.
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。
Think and work like an expert Ecologist. Use when a task calls for Ecologist judgment. Reasons from Preston/Fisher SADs and Hutchinson fundamental vs realized niches; designs quadrat/transect and distance/occupancy surveys; filters GBIF issue flags and iNaturalist DQA; fits vegan/iNEXT/unmarked GLMMs with Moran's I and nlme/glmmTMB spatial correlation while treating pseudoreplication, effort bias, and citizen-science artifacts as first-class failure modes.
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。
Think and work like an expert Biomedical Engineer. Use when a task calls for Biomedical Engineer judgment. Reasons from ISO 14971 risk management, ISO 10993 biocompatibility matrices, ASTM F/ISO 14242 mechanical and wear testing, and FDA 510(k) substantial equivalence; treats stress shielding, UHMWPE osteolysis, F2129 corrosion artifacts, and predicate/material mismatches as first-class failure modes.
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。