Skills
18,283 skills, most installed first.
Browse
debug-issuetirth8205Systematically debug issues using graph-powered code navigationexplore-codebasetirth8205Navigate and understand codebase structure using the knowledge graphrefactor-safelytirth8205Plan and execute safe refactoring using dependency analysisreview-changestirth8205Perform a structured code review using change detection and impactreview-deltatirth8205Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.review-prtirth8205Review a PR or branch diff using the knowledge graph for full structural context. Outputs a structured review with blast-radius analysis.create-colleaguetitanwingsDistill a colleague into an AI Skill. Auto-collect Feishu/DingTalk data, generate Work Skill + Persona, with continuous evolution. | 把同事蒸馏成 AI Skill，自动采集飞书/钉钉数据，生成 Work + Persona，支持持续进化。thinking-bounded-rationalitytjboudreauxUse when search or investigation could run forever. Set an explicit good-enough threshold first, then stop at the first option that clears it.thinking-circle-of-competencetjboudreauxUse when a specific claim may lack grounding. Check evidence boundary, size wrongness cost, then answer, fetch, or abstain — never confabulate.thinking-cynefintjboudreauxWhen the right response mode is unclear, classify the cause-effect domain first; decompose disorder.thinking-effectuationtjboudreauxUnder genuine uncertainty with no reliable forecast, inventory means, cap downside at affordable loss, act for commitments, and let goals emerge from controllable moves.thinking-first-principlestjboudreauxWhen a constraint is treated as fixed, separate physics from convention, keep only independently supported primitives, and rebuild the simplest solution that satisfies real constraints.thinking-five-whys-plustjboudreauxWhen a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.thinking-jobs-to-be-donetjboudreauxDeciding what to build or why adoption fails. Recover the progress users hire a solution for under a circumstance, then rank by outcome and competing workarounds.thinking-kepner-tregoetjboudreauxUse when a selective defect needs IS/IS-NOT difference analysis or a consequential option choice needs must/want weighting and adverse-consequence comparison.thinking-lindy-effecttjboudreauxUse when longevity of a non-perishable option matters. Treat survival duration as a remaining-life prior, then check domain drift before favoring the proven.thinking-map-territorytjboudreauxWhen a claim, doc, test, metric, or assumption conflicts with observed behavior, stop theorizing from the map and verify the live code or data; let territory overrule.thinking-margin-of-safetytjboudreauxWhen provisioning, setting a limit, or committing an estimate under uncertainty, size a buffer to residual error and the cost of breach—not to the optimistic edge.thinking-model-combinationtjboudreauxWhen one mental model leaves a material blind spot on a multi-domain or high-stakes problem, sequence complementary models with named roles and a conflict rule.thinking-model-routertjboudreauxWhen unsure which thinking skill fits, map domain and problem type, then return NONE or one primary skill by default (at most three complementary).thinking-oodatjboudreauxUse under time pressure when the situation is still changing and you must act before certainty — cycle Observe→Orient→Decide→Act on ~70% confidence, then re-observe.thinking-opportunity-costtjboudreauxBefore committing scarce time, people, or money, name the best forgone use of those resources and the value delta of the chosen path versus that alternative.thinking-pre-mortemtjboudreauxBefore committing to a plan or launch, assume it already failed and reason backward through concrete causes — convert failure paths into mitigations, gates, and stop checks.thinking-probabilistictjboudreauxUse when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.thinking-red-teamtjboudreauxFor authorized security review of code, auth, or APIs you control, model the attacker, map the attack surface, and report only findings with a reproducible exploit path and verified mitigation.thinking-reversibilitytjboudreauxBefore heavy deliberation, classify the decision as cheap or costly to undo; decide two-way doors fast and stage one-way doors to preserve options.thinking-scientific-methodtjboudreauxWhen a symptom has several plausible causes, rank falsifiable hypotheses and run the cheapest discriminating observation first; prefer least-assumptive survivors only after evidence fit.thinking-second-ordertjboudreauxWhen a change has effects past the immediate fix—incentives, scale, feedback—trace consequence chains with timing and probability before committing.thinking-socratictjboudreauxWhen a request is vague, assumption-laden, or "obvious," ask the few load-bearing questions that expose hidden requirements before building or committing.thinking-steel-manningtjboudreauxBefore rejecting a proposal or reflexively agreeing, build the strongest faithful opposing case, state agreement conditions, then update or reaffirm.thinking-systemstjboudreauxWhen behavior is emergent across components—fixes elsewhere break, loops/delays dominate—map boundary, stocks/flows, feedback, archetypes, then rank leverage.thinking-theory-of-constraintstjboudreauxWhen throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.thinking-thought-experimenttjboudreauxWhen a real test is too rare, large, or irreversible, run a controlled counterfactual: isolate one variable, fix conditions, trace the mechanistic chain, and bound what the result implies.thinking-triztjboudreauxWhen two design requirements seem mutually exclusive, name the contradiction, separate conflicting states, then invent a concrete no-compromise resolution.thinking-via-negativatjboudreauxUse when the reflex is to add a feature, layer, or process. Prefer removing harmful or nonessential elements first, with an irreversibility guard before deletion.skill-creatortldrawGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an AI agent's capabilities with specialized knowledge, workflows, or tool integrations.write-docstldrawWriting SDK documentation for tldraw. Use when creating new documentation articles, updating existing docs, or when documentation writing guidance is needed. Applies to docs in apps/docs/content/.write-e2e-teststldrawWriting Playwright E2E tests for tldraw. Use when creating browser tests, testing UI interactions, or adding E2E coverage in apps/examples/e2e or apps/dotcom/client/e2e.write-exampletldrawWriting examples for the tldraw SDK examples app. Use when creating new examples, adding SDK demonstrations, or writing example code in apps/examples.write-issuetldrawReference standards for writing and maintaining GitHub issues in the tldraw repository. Use as supporting guidance when another skill or workflow needs issue title, body, type, label, or triage standards.write-prtldrawReference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.write-unit-teststldrawWriting unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.qmdtobiSearch local markdown knowledge bases, notes, docs, and wikis with QMD. Use when users ask to find notes, retrieve documents, inspect a wiki, answer from indexed markdown, or set up QMD access.releasetobiManage releases for this project. Validates changelog, installs git hooks, and cuts releases. Use when user says "/release", "release 1.0.5", "cut a release", or asks about the release process. NOT auto-invoked by the model.ui-audittommygeocoAI skill for automated UI audits. Evaluate interfaces against proven UX principles for visual hierarchy, accessibility, cognitive load, navigation, and more. Based on Making UX Decisions by Tommy Geoco.xgboost-lightgbmtondevrelIndustry-standard gradient boosting libraries for tabular data and structured datasets. XGBoost and LightGBM excel at classification and regression tasks on tables, CSVs, and databases. Use when working with tabular machine learning, gradient boosting trees, Kaggle competitions, feature importance analysis, hyperparameter tuning, or when you need state-of-the-art performance on structured data.agent-performance-engineertony363Expert performance engineer specializing in system optimization, bottleneck identification, and scalability engineering. Masters performance testing, profiling, and tuning across applications, databases, and infrastructure with focus on achieving optimal response times and resource efficiency.zimage-generationtoolsaiGenerate high-quality images using ModelScope's Z-Image API. Use this skill when the user wants to generate images using the specific Z-Image model or ModelScope API they provided. Trigger words: 'Zimage', 'ModelScope', 'generate zimage'.Skills-Security-Checktoolsai通過靜態和AI檢查技能 Skills 安全風險、潛在威脅。當使用者請求檢查技能，掃描技能的時候啟動技能評測評估功能。Detect Skill vulnerabilities using static and AI checks. Automatically activate evaluation upon scan requests.uikit-maxtornikegomareliComprehensively reviews UIKit code for best practices on modern APIs, architecture, and performance. Use when reading, writing, or reviewing UIKit-based iOS projects, including UIViewController, UITableView, UICollectionView, Auto Layout, or programmatic UI code. Also use when migrating legacy UIKit patterns to modern equivalents. Do not use for SwiftUI-only projects or Combine-only logic with no UIKit dependency.