'elf' 검색 결과

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build GSAP JavaScript animations for web apps — timelines, scroll-driven motion, SVG draw/morph/path effects, and React integration with useGSAP. Load when the user asks to animate with GSAP, add ScrollTrigger, draw SVG paths with GSAP, morph SVG shapes, sequence page animations, or wire GSAP in React/Next/Vue. Also triggers on "GSAP timeline", "DrawSVG", "MotionPath", "gsap.context", or "scroll animation library". Not for self-contained README/GitHub SVG files.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Orchestrator for agent harness work — the setup that makes AI agents follow project rules and improve when they fail. FIRES PROACTIVELY when agents misbehave, repeat mistakes, ignore instructions, skip skills, or when AGENTS.md exists but docs/harness/manifest.json is missing. Also triggers on: harness engineering, agent scaffold, agent keeps failing, agent not following instructions, make agents reliable, agents going off rails, agent forgot context, improve agent setup, self-improving agents, agents keep making mistakes, why is my agent bad, agent quality, agent setup broken, agents ignore skills, same mistake again, fix agent behavior, tune agent instructions, set up agent infrastructure, after project setup agents still bad. Routes bootstrap vs evolution. Not multi-agent topology — agent-builder.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs. Includes built-in bias mitigation for position bias, length bias, and self-enhancement bias. Load when the user asks to score an output, judge a response, evaluate against a rubric, compare two outputs, do direct scoring, run pairwise comparison, or says "rate this", "which response is better", "score this against the rubric", "judge this output", "LLM as judge this". Sub-skill of eval-output orchestrator.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost. Plain-language primer plus free-tier-first backend selection (Langfuse, Phoenix, LangSmith, Braintrust) and OpenTelemetry/OpenInference instrumentation. Load when the user asks to add observability, add tracing, instrument my agents, see what my agent is doing in production, set up Langfuse or Phoenix or LangSmith, debug why my agent gave a bad answer, or track LLM cost per request. Also fires when agent-system-architecture or setup-evaluation requires an observability plan for an agent-chain product. NOT for tracing the coding agent itself — that is run-trace. Precondition for runtime-learning-loop.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generate user-facing or internal release notes and changelogs. Load when the user prepares a release, tags a version, or wants to summarize recent progress. Also triggers on "write a changelog", "prepare release notes", "what's new in this version", "summarize my commits", or "create a release summary". Auto-triggered by library-skill after major repo changes (new skills added, skills renamed, structure changes). Applicable to any project, including this skill library itself.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turn a one-line objective into a step-by-step construction plan any coding agent can execute cold. Each step has a self-contained context brief — a fresh agent in a new session can pick up any step without reading prior steps.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design spec with 98 rules for building CLI tools that AI agents can safely use. Covers structured JSON output, error handling, input contracts, safety guardrails, exit codes, and agent self-description.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Turns Hi-C/Micro-C FASTQ into a deduplicated, filtered .pairs file with pairtools and decides whether the library worked. Covers the bwa mem -SP5M / bwa-mem2 / chromap --preset hic alignment idiom (mates mapped as independent single-end reads), pairtools parse vs parse2 and the walks-policy choice (5unique pairwise vs all for Pore-C/Micro-C concatemers), pair-type classification (keep UU and rescued UC), dedup (PCR vs optical/by-tile), select by pair_type/MAPQ/distance, restriction-fragment handling (restrict, Arima dual-enzyme, Micro-C/DNase fragment-free), and allele-specific phasing (pairtools phase to two coolers). The library-QC decision uses % long-range cis as the one-number quality metric, trans as the noise floor, orientation balance as fragment-map-free dangling-end/self-circle QC, and % duplicates as a complexity proxy. Use when processing Hi-C/Micro-C/Omni-C reads into pairs, judging library quality, handling multi-enzyme or restriction-agnostic protocols, or generating allele-specific contacts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Comprehensive quality control for CLIP-seq libraries (eCLIP, iCLIP, iCLIP2, PAR-CLIP) covering library complexity (preseq), FRiP, IDR replicate reproducibility, read-distribution metagene, SMInput vs IgG control rationale, rRNA / snoRNA contamination, fragment-length distribution, and ENCODE-compliance thresholds. Use when assessing whether a CLIP library passed, deciding lenient vs stringent peak thresholds, comparing replicates with IDR rescue and self-consistency ratios, or distinguishing failed IP from over-amplified library.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Performs structure-based virtual screening using AutoDock Vina, SMINA, GNINA (CNN scoring), and DiffDock-L hybrid workflows with explicit choice rules across rigid vs flexible docking, cross-docking vs self-docking, binding-site detection (P2Rank, fpocket), receptor preparation (PDB2PQR, PROPKA), ligand preparation (meeko, OpenBabel), and ultralarge-library screening (ZINC22, Enamine REAL). Use when screening chemical libraries against a protein target to find candidate binders, ranking docking poses, or selecting a docking workflow for a specific scenario.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Assesses ChIP-seq quality across antibody specificity, fragmentation, enrichment, replicate concordance, and library complexity. Computes FRiP, NSC/RSC (phantompeakqualtools), library complexity (NRF/PBC1/PBC2), deepTools plotFingerprint (JS distance, AUC, synthetic JS), ChIPQC, IDR with ENCODE Nself/Nt rules, and detects hyper-ChIPable artifacts. Use when validating an antibody, diagnosing failed peak calls, deciding whether to proceed with downstream analysis, grading against ENCODE thresholds, or auditing replicate concordance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when an owner-operator (1099 or LLC/S-corp) asks how to lower their tax bill, what they can deduct, per diem treatment, depreciation choices (Section 179, bonus, MACRS), quarterly estimated payments, S-corp salary vs distributions, retirement plan options (SEP-IRA, Solo 401(k)), or recordkeeping requirements. Covers federal income tax + self-employment tax basics; not state-specific.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill when an owner-operator (single CDL driver, single operating authority) needs to comply with random testing. Covers consortium membership, pool size requirements, and self-employed driver rules.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill to run an internal audit before FMCSA does. Covers what to check, common gaps, and remediation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Decision-theoretic framework for agents embedded within the environments they model and act upon

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

An innate exploratory drive that guarantees no graph node remains permanently invisible to an agent population. After a warm-up period (step > 3), each agent fires a coverage scan with probability |unseen_nodes| / |all_nodes|. When triggered, the agent teleports directly to the globally unseen node with the highest belief uncertainty, works it, and returns control to the normal action-selection loop. Probability is self-annealing: it starts near 1.0 when almost everything is unseen and decays toward 0.0 as coverage saturates, requiring no manual schedule. The mechanism is "innate" (hard-coded into the agent step loop) as distinct from the "adaptive" EFE path, which requires local neighbors and learned precision weights. Together they form a two-layer exploration architecture: adaptive for locally-guided foraging, innate for topological completeness.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Principled action selection for autonomous agents using Expected Free Energy (EFE) under the Active Inference framework. Each candidate action is scored as G(n) = w_prag * (-E[p_n] * damping) + w_epist * (-Var[p_n] * novelty(n)), where agent beliefs are maintained as per-node Beta distributions and updated via Bayesian observation. Selection is a softmax over -gamma * G, making exploration an automatic consequence of uncertainty rather than a hardcoded epsilon. Precision weights w_prag and w_epist self-adapt via surprise history, shifting the agent between exploitation and exploration regimes without any manually tuned schedule.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Operationalizing an expungement website — user intake flows, document generation pipelines, court filing integrations, payment processing, state-by-state workflow variations, customer support for sensitive populations, and the handoff between automated systems and human legal review. Activate on 'expungement operations', 'legal tech SaaS', 'court filing integration', 'document automation pipeline', 'expungement business', 'legal service workflow', 'multi-state legal operations'. NOT for expungement law itself (use national-expungement-expert), web design (use legal-tech-web-design), or legal document drafting (use recovery-app-legal-terms).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Classify every destructive/gated action an agent body can attempt (git, filesystem, network, shell, github) into block/approve/allow tiers, and audit whether the pre-tool and post-tool governance backing that classification is real: blocked actions proven zero-side-effect by a negative fixture, every denial backed by a receipt and a transcript event, every block-tier denial paired with a safe alternative, and no unmanaged or same-UID body ever marked "contained." Use when building or reviewing Agent Harbor's C5 governance gate (destructive git blocker, approval request/result, denial receipts), gating a new tool surface before it can run destructive commands, or auditing whether an existing "destructive-action blocked" claim actually has evidence behind it. NOT for proving an existing sandbox boundary actually contains an adversary once an action is isolated (use sandboxed-adversarial-test-harness), deciding where in a DAG to place a human review node or designing the approval UX itself (use human-gate-designer), or designing the general work-receipt schema across an entire agent task (use agent-work-receipt-designer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert in developer tool documentation as a product. Activate on: docs site, getting started guide, API reference, developer documentation, Docusaurus, Mintlify, Nextra, ReadMe, migration guide, troubleshooting page, docs information architecture, documentation testing, llms.txt. NOT for: marketing copy (use seo-content-blogging), API design itself (use api-architect), general technical writing (use technical-writer).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert in cluttering -- the lesser-known fluency disorder characterized by rapid/irregular speech rate, excessive disfluencies, and frequent ADHD comorbidity. Covers differential diagnosis from stuttering, assessment protocols, therapy approaches (rate control, self-monitoring, pragmatic awareness), technology-assisted intervention, and AI tools for people who clutter. Activate on 'cluttering', 'rapid speech disorder', 'speech rate too fast', 'speech disfluency not stuttering', 'disorganized speech', 'ADHD speech problems', 'cluttering vs stuttering', 'speech intelligibility', 'mazed speech', 'telescoping words'. NOT for stuttering-only treatment (overlap is common but they are distinct), hearing disorders, or voice disorders (pitch, resonance).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design and build mathematically rigorous, high-density, interactive data graphics and streaming telemetry visualizations following Mike Bostock's D3.js and Observable methodologies. Use when crafting custom SVG/Canvas charts, reactive streaming time-series, multi-dimensional brush-and-link coordinates, small multiples, or topological swarm graphs. NOT for generic dashboard template clones, basic spreadsheet charts, or off-the-shelf low-effort wrapper libraries.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design RL simulation sandboxes, trajectory datasets, QLoRA/LoRA adaptation plans, eval harnesses, and rollback unhooks for agents learning specific coding behaviors beyond the base model. Use when building or reviewing tool-use training loops, offline trajectories, reward functions, self-improvement harnesses, or Port Daddy agent behavior curricula. NOT for generic ML tutorials, full model training operations, or production deployment without eval gates and safety unhooks.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.