yeaight7
- 117 skills
- 0 followers
- 7 hours ago last updated
- ▌ Agent Harness Design 2 · yeaight7Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an existing agent harness needs a quality review.
- ▌ Context Retrieval Loop 2 · yeaight7Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search pass missed the relevant file, or the file scope of a task is unclear.
- ▌ Context Retrieval Loop 3 · yeaight7Use when about to refactor, rename, or remove code, assessing dead code before deletion, or unsure of the blast radius of a change.
- ▌ Context Retrieval Loop 4 · yeaight7Use when about to write a new doc, README section, or ADR, updating existing documentation with unclear scope, or spawning a documentation subagent that needs file context.
- ▌ Bug Hunt · yeaight7Use when reproducing, isolating, and fixing a bug with the smallest safe change.
- ▌ Defuddle · yeaight7Use when the user provides a URL to a standard web page and clean Markdown extraction with Defuddle would reduce clutter and token cost.
- ▌ Graphify · yeaight7 bundleany input (code, docs, papers, images) → knowledge graph → clustered communities → HTML + JSON + audit report. Use when the user wants to build, inspect, or query a cross-file knowledge graph from code, docs, papers, images, or videos with upstream graphify.
- ▌ No Fluff · yeaight7Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "no fluff", "be concise", "use less tokens", or similar.
- ▌ Repo Map · yeaight7Use when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.
- ▌ Ask Codex · yeaight7Use when a Claude Code agent needs to delegate a question, subtask, or review to a local Codex instance.
- ▌ Pr Triage · yeaight7Use when open pull requests, stale branches, or review bottlenecks need prioritization from current repository state.
- ▌ Ask Claude · yeaight7Use when a Codex or generic local agent needs a focused second opinion from Claude CLI without MCP routing.
- ▌ Ask Gemini · yeaight7Use when a Codex or generic local agent needs a focused second opinion from Gemini CLI without MCP routing.
- ▌ JSON Canvas · yeaight7Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
- ▌ Relay Codex · yeaight7Use when another local agent needs a one-shot Codex CLI answer and interactive behavior is acceptable or controlled.
- ▌ Task Intake · yeaight7Use at the start of a new task -- before writing or editing code -- when the request is vague, the scope boundaries are unclear, or the acceptance criteria for "done" have not been stated.
- ▌ Context Docs · yeaight7Use when a subsystem needs persistent context for future agents or engineers -- its boundaries keep being rediscovered the hard way, invariants keep getting violated, or sessions repeatedly ask the same questions about it.
- ▌ Data Quality · yeaight7Use when adding or reviewing data quality tests for dbt models in warehouse-backed analytics projects. Covers dbt generic tests, singular tests (assert_*.sql), accepted-values macros, dbt_utils patterns, cross-system consistency tests, and warehouse-oriented validation. Use when writing data tests, creating assert_*.sql files, testing business logic, or validating referential integrity.
- ▌ Dbt Strategy · yeaight7Use when creating or modifying dimensional dbt models in warehouse-backed analytics projects. Covers a four-layer warehouse architecture (sources/staging/core/marts), naming conventions, no-alias SQL rule, surrogate-key and missing-record patterns, incremental strategies, deduplication, and common project macros. Use when building fact tables, dimension tables, staging models, writing SQL, or designing tests.
- ▌ Relay Claude · yeaight7Use when another local agent needs a one-shot Claude CLI answer without cross-turn relay memory.
- ▌ Relay Gemini · yeaight7Use when a persistent local Gemini ACP session should keep context across multiple advisory turns.
- ▌ Brainstorming · yeaight7Use when starting any creative work — creating features, building components, adding functionality, or modifying behavior — before any implementation begins.
- ▌ Dbt Preflight · yeaight7Use when a dbt change needs preflight before a PR, review, or merge -- changed models, snapshots, seeds, macros, or semantic YAML whose blast radius and test coverage are not yet known.
- ▌ Local RAG MCP · yeaight7 bundleUse when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.
- ▌ Model Routing · yeaight7Use when selecting a model for a new task or subagent, deciding whether to escalate after a failed attempt, or designing a multi-agent pipeline with mixed task complexity.
- ▌
- ▌ Writing Plans · yeaight7 bundleUse when you have a spec or requirements for a multi-step task, before touching code.
- ▌ API Doc Review · yeaight7Use when API documentation may have drifted from the implementation -- endpoints changed without a spec update, integration partners report mismatches, or a PR touches routes, params, or response shapes.
- ▌ Failure Triage · yeaight7Use when confronted with an unknown failure in CI or production, before committing to a deep debugging approach.
- ▌ Using Powerups · yeaight7Use when starting work in a repository with Agent Powerups installed, when a task may match a reusable local skill, command, workflow, hook recipe, AGENTS.md template, or MCP feature.
- ▌ Writing Skills · yeaight7Use when creating new skills, editing existing skills, or verifying skills work before deployment
- ▌ AI Slop Cleaner · yeaight7Use when a working code path feels bloated, noisy, or over-abstracted, when asked to clean up or deslop AI-generated code, or when a reviewer-only anti-slop pass is requested.
- ▌ MCP Risk Review · yeaight7Use when an MCP server is about to be enabled, added to agent config, or upgraded -- a staged server config is a candidate for activation, a third-party server is proposed from a registry, or an existing entry changes transport, credentials, or tool surface.
- ▌ Incident Readout · yeaight7Use when a bug fix or complex debugging session concludes and a blameless post-mortem summary is needed for human review.
- ▌ Ml Leakage Check · yeaight7Use when reviewing ML preprocessing or feature pipelines for target leakage -- validation metrics look suspiciously good, transformers are fitted before splitting, or features may not exist at prediction time.
- ▌ Readme Hardening · yeaight7Use when a README cannot be followed verbatim -- setup or test commands fail or are vague, environment requirements are unstated, or a new engineer or agent cannot bootstrap the project quickly.
- ▌ Tri Model Review · yeaight7Use when a request needs parallel external perspectives — combined backend and UI work, code review from multiple angles, or cross-validation where different models may disagree.
- ▌ Dead Code Removal · yeaight7Use when unused functions, classes, exports, or files need to be identified and safely deleted.
- ▌ Pr Review CI Loop · yeaight7Use when a pull request needs one bounded review and CI triage cycle with explicit approval before edits or remote writes.
- ▌ Risk Based Review · yeaight7Use when reviewing a PR or your own change plan and you need to decide how much scrutiny it deserves -- the diff touches auth, payments, crypto, migrations, or core shared code, or you are unsure where to focus limited review attention.
- ▌ CI Failure Readout · yeaight7Use when a CI pipeline has failed and the real error must be extracted from thousands of lines of noisy logs.
- ▌ Dependency Cleanup · yeaight7Use when package manifests carry unused or redundant third-party dependencies that slow builds, widen the security surface, or complicate updates.
- ▌ Environment Doctor · yeaight7Use when apx commands fail or assets are missing from listings, MCP servers fail to start, builds hit command-not-found or module-not-found errors, generated assets look stale, or setup works on one machine but not another.
- ▌ Handoff Discipline · yeaight7Use when ending a session, handing a task back to the user, or approaching the context limit with work unfinished -- the next session or engineer must be able to resume the work instantly.
- ▌ Hook Safety Review · yeaight7Use when a hook is about to be enabled or modified -- a hook recipe proposed for activation, a pre/post-tool or lifecycle hook added to agent settings, a git pre-commit hook added to a repo, or a third-party hook snippet pasted in from outside.
- ▌ MCP Server Builder · yeaight7 bundleDesign high-quality MCP servers around workflows, narrow schemas, context-aware outputs, and actionable errors. Use when building or reviewing MCP tools for real agent tasks.
- ▌ Agent Readable Docs · yeaight7Use when writing technical documentation that needs to be readable by both humans and AI models, converting existing docs to HADS format, validating a HADS document, or optimizing documentation for token-efficient AI consumption.
- ▌ Bigquery Cost Audit · yeaight7Use when reviewing BigQuery spend, query failure patterns, or scan inefficiencies -- identifying which jobs, users, or projects drive cost, or preparing optimization recommendations for a cost review.
- ▌ Change Impact Check · yeaight7Use before submitting a PR or considering a task done to evaluate the blast radius of your changes -- you touched a public signature, a shared utility, a schema, or added config and need to know what else is affected.
- ▌ Changelog Generator · yeaight7Use when preparing release notes or a changelog entry from commits, PRs, or diffs, summarizing a sprint or version range, or scanning a range for breaking changes before publishing.
- ▌ Context Compression · yeaight7 bundleUse when conversation context is bloated, constraints are being forgotten, or a compact handoff is needed before continuing work.
- ▌ Gh Address Comments · yeaight7Address actionable GitHub pull request review feedback. Use when the user wants to inspect unresolved review threads, requested changes, or inline review comments on a PR, then implement selected fixes.
- ▌ Using Git Worktrees · yeaight7Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
- ▌ Agent Harness Design · yeaight7Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an existing agent harness needs a quality review.
- ▌ Context Minimization · yeaight7Use when a task runs long and the context window is filling -- large files are being read whole, command output is flooding the transcript, or responses are getting verbose and slow.
- ▌ Dataset Split Review · yeaight7Use when reviewing how data is split into train/validation/test sets -- especially with time-series data, repeated entities (users, patients, sessions), or imbalanced targets.
- ▌ Log Driven Diagnosis · yeaight7Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.
- ▌ Minimal Reproduction · yeaight7Use when a bug must be isolated from a large application into a standalone, runnable script or single test case.
- ▌ Regression Bisecting · yeaight7Use when a bug was recently introduced but you don't know which commit caused it.
- ▌ Systematic Debugging · yeaight7 bundleUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
- ▌ AI Regression Testing · yeaight7Use when an agent has modified logic, API routes, or data-transformation code, a bug was just fixed and must not be reintroduced, or behavior must stay identical across execution paths such as sandbox versus production.
- ▌ Doc Consistency Check · yeaight7Use when documentation may have rotted against the code -- files were renamed or moved, scripts or env vars changed, or readers report commands and paths from the docs that no longer work.
- ▌ Incremental Migration · yeaight7Use when migrating APIs, libraries, or patterns across a large codebase and a single mega-commit would be too risky to review or merge.
- ▌ Memory Build Workflow · yeaight7Use when a user needs to build or refresh persistent graph memory from a mixed corpus and the right path may include graphify, incremental update, or helper conversion before ingestion.
- ▌ Memory Query Workflow · yeaight7Use when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.
- ▌ Receiving Code Review · yeaight7Use when receiving code review feedback, before implementing suggestions — requires technical verification and reasoned pushback, not performative agreement or blind implementation.
- ▌ Secret Leak Preflight · yeaight7Use when about to commit, push, or publish -- staged changes touch config or environment files, generated artifacts (relay sessions, logs, build output) are being added, or the session handled credentials even indirectly.
- ▌ Skill Authoring Guide · yeaight7 bundleCreate or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.
- ▌ Webapp Visual Testing · yeaight7Use when a browser-facing UI needs visual verification, a layout bug or visual regression is reported, accessibility of an interactive component needs checking, or a browser workflow must be exercised end-to-end.
- ▌ Agent Runtime Patterns · yeaight7 bundleUse when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.
- ▌ Build Fix Minimal Diff · yeaight7Use when a build, test, type check, or lint is failing — locally or in CI — and the fix must be the smallest safe diff with no opportunistic refactors or unrelated changes.
- ▌ Context Retrieval Loop · yeaight7Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search pass missed the relevant file, or the file scope of a task is unclear.
- ▌ Markitdown File Intake · yeaight7 bundleUse when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
- ▌ Metric Impact Analyzer · yeaight7Use when a change may affect metrics, semantic models, dashboards, reporting, or stakeholder-facing KPIs and you need to know whether business meaning or downstream BI assets change.
- ▌ Requesting Code Review · yeaight7 bundleUse when completing tasks, implementing major features, or before merging to verify work meets requirements.
- ▌ Requirements Clarifier · yeaight7Use when an implementation request is vague or underspecified and needs structured clarification before coding -- the user says "interview me", "ask me everything", "don't assume", or wants to avoid "that's not what I meant" outcomes from autonomous execution.
- ▌ Search Before Building · yeaight7Use when about to add a new helper, utility, or abstraction, a task sounds like a solved problem, a new external dependency is being considered, or custom code is proposed without checking what already exists.
- ▌ Agent Session Forensics · yeaight7 bundleUse when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.
- ▌ Deploy Pipeline Runbook · yeaight7Use when a release spans multiple systems or vendors, order of operations matters with rollback planned up front, or a failed step in one system could corrupt state in a downstream system.
- ▌ Red Team Eval Authoring · yeaight7 bundleUse when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
- ▌ Test Driven Development · yeaight7Use when implementing any feature or bugfix, before writing implementation code
- ▌ Flaky Test Investigation · yeaight7Use when tests pass and fail intermittently without code changes, or a test passes alone but fails in the full suite.
- ▌ Github CI Failure Triage · yeaight7 bundleUse when a GitHub PR shows failing checks and a clean failure readout is needed before changing any code.
- ▌ Hard Won Skill Extractor · yeaight7Use when a tricky bug, non-obvious workaround, hidden gotcha, or undocumented behavior took real debugging effort to discover and should be captured as a reusable learned skill.
- ▌ Managed Codebase Context · yeaight7 bundleUse when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
- ▌ Pre Release Verification · yeaight7Use when a release candidate needs final checks before tagging, publishing, or production deployment.
- ▌ Prompt Evaluation Runner · yeaight7 bundleUse when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
- ▌ Test Preserving Refactor · yeaight7Use when code needs restructuring and observable behavior must stay unchanged, with existing tests kept green at every step.
- ▌ Browser Automation Safety · yeaight7 bundleUse when validating rendered web pages, local dev servers, browser automation, screenshots, forms, auth sessions, or UI evidence with strict browser safety boundaries.
- ▌ Canonical Advisor Routing · yeaight7Use when routing a prompt to a local provider CLI for a second opinion, review, or plan -- you are about to call a provider directly, need the response saved for later, or want a single consistent way to invoke codex/gemini/claude.
- ▌ Filesystem MCP Guardrails · yeaight7 bundleUse when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.
- ▌ Parallel Execution Engine · yeaight7Use when latency matters and several independent tasks can run at once -- a bounded implementation or investigation that needs waves of concurrent workers, not a persistent completion loop or stage-based orchestration.
- ▌ SQL Business Logic Review · yeaight7Use when reviewing SQL that affects reporting, metrics, transformations, financial logic, product logic, or stakeholder-facing outputs -- especially when a query still runs fine but its business meaning may have drifted.
- ▌ Baseline Comparison Review · yeaight7Use when a new or more complex ML model is proposed and its value over simple baselines is not yet demonstrated -- before approving a new architecture or replacing an existing heuristic.
- ▌ Codebase Migration Batches · yeaight7Use when a wide refactor or migration is too large to ship as one change — API renames across many files, framework or config migrations, or mechanical codemod-backed refactors that need reviewable batches.
- ▌ Experiment Tracking Review · yeaight7Use when reviewing ML training code to confirm a run could be reconstructed later -- hyperparameters, metrics, data references, and artifacts logged, not just printed to stdout.
- ▌ Model Evaluation Reporting · yeaight7Use when writing or reviewing a model evaluation report -- accuracy is being quoted alone, or stakeholders need failure modes, segment performance, and business trade-offs made explicit.
- ▌ Persistent Completion Loop · yeaight7Use when a task must run to verified completion rather than best effort -- the user says "don't stop", "must complete", "finish this", or "keep going until done", or the work spans multiple iterations and needs reviewer sign-off before being called done.
- ▌ Release Readiness Protocol · yeaight7Use when preparing a versioned release and release metadata, validation, publish commands, and rollback plan must be checked before tagging.
- ▌ Reproducible Training Runs · yeaight7Use when reviewing or modifying ML training scripts that must produce identical results across runs or machines -- runs with the "same" config differ, or a past result must be reconstructed exactly.