← all publishers

yeaight7

@yeaight7 source repo

117 published skills · page 1 of 2

  1. Agent Harness Design 2 · yeaight7
    Use 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.
    0
    installs
  2. Context Retrieval Loop 2 · yeaight7
    Use 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.
    0
    installs
  3. Context Retrieval Loop 3 · yeaight7
    Use when about to refactor, rename, or remove code, assessing dead code before deletion, or unsure of the blast radius of a change.
    0
    installs
  4. Context Retrieval Loop 4 · yeaight7
    Use 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.
    0
    installs
  5. Bug Hunt · yeaight7
    Use when reproducing, isolating, and fixing a bug with the smallest safe change.
    0
    installs
  6. Defuddle · yeaight7
    Use when the user provides a URL to a standard web page and clean Markdown extraction with Defuddle would reduce clutter and token cost.
    0
    installs
  7. Graphify · yeaight7 bundle
    any 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.
    0
    installs
  8. No Fluff · yeaight7
    Ultra-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.
    0
    installs
  9. Repo Map · yeaight7
    Use when the task is to understand an unfamiliar codebase, locate key entry points, or summarize architecture before editing.
    0
    installs
  10. Ask Codex · yeaight7
    Use when a Claude Code agent needs to delegate a question, subtask, or review to a local Codex instance.
    0
    installs
  11. Pr Triage · yeaight7
    Use when open pull requests, stale branches, or review bottlenecks need prioritization from current repository state.
    0
    installs
  12. Ask Claude · yeaight7
    Use when a Codex or generic local agent needs a focused second opinion from Claude CLI without MCP routing.
    0
    installs
  13. Ask Gemini · yeaight7
    Use when a Codex or generic local agent needs a focused second opinion from Gemini CLI without MCP routing.
    0
    installs
  14. JSON Canvas · yeaight7
    Create 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.
    0
    installs
  15. Relay Codex · yeaight7
    Use when another local agent needs a one-shot Codex CLI answer and interactive behavior is acceptable or controlled.
    0
    installs
  16. Task Intake · yeaight7
    Use 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.
    0
    installs
  17. Context Docs · yeaight7
    Use 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.
    0
    installs
  18. Data Quality · yeaight7
    Use 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.
    0
    installs
  19. Dbt Strategy · yeaight7
    Use 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.
    0
    installs
  20. Relay Claude · yeaight7
    Use when another local agent needs a one-shot Claude CLI answer without cross-turn relay memory.
    0
    installs
  21. Relay Gemini · yeaight7
    Use when a persistent local Gemini ACP session should keep context across multiple advisory turns.
    0
    installs
  22. Brainstorming · yeaight7
    Use when starting any creative work — creating features, building components, adding functionality, or modifying behavior — before any implementation begins.
    0
    installs
  23. Dbt Preflight · yeaight7
    Use 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.
    0
    installs
  24. Local RAG MCP · yeaight7 bundle
    Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.
    0
    installs
  25. Model Routing · yeaight7
    Use 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.
    0
    installs
  26. Safe Refactor · yeaight7
    Use when code needs restructuring without changing observable behavior.
    0
    installs
  27. Writing Plans · yeaight7 bundle
    Use when you have a spec or requirements for a multi-step task, before touching code.
    0
    installs
  28. API Doc Review · yeaight7
    Use 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.
    0
    installs
  29. Failure Triage · yeaight7
    Use when confronted with an unknown failure in CI or production, before committing to a deep debugging approach.
    0
    installs
  30. Using Powerups · yeaight7
    Use 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.
    0
    installs
  31. Writing Skills · yeaight7
    Use when creating new skills, editing existing skills, or verifying skills work before deployment
    0
    installs
  32. AI Slop Cleaner · yeaight7
    Use 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.
    0
    installs
  33. MCP Risk Review · yeaight7
    Use 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.
    0
    installs
  34. Incident Readout · yeaight7
    Use when a bug fix or complex debugging session concludes and a blameless post-mortem summary is needed for human review.
    0
    installs
  35. Ml Leakage Check · yeaight7
    Use 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.
    0
    installs
  36. Readme Hardening · yeaight7
    Use 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.
    0
    installs
  37. Tri Model Review · yeaight7
    Use 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.
    0
    installs
  38. Dead Code Removal · yeaight7
    Use when unused functions, classes, exports, or files need to be identified and safely deleted.
    0
    installs
  39. Pr Review CI Loop · yeaight7
    Use when a pull request needs one bounded review and CI triage cycle with explicit approval before edits or remote writes.
    0
    installs
  40. Risk Based Review · yeaight7
    Use 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.
    0
    installs
  41. CI Failure Readout · yeaight7
    Use when a CI pipeline has failed and the real error must be extracted from thousands of lines of noisy logs.
    0
    installs
  42. Dependency Cleanup · yeaight7
    Use when package manifests carry unused or redundant third-party dependencies that slow builds, widen the security surface, or complicate updates.
    0
    installs
  43. Environment Doctor · yeaight7
    Use 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.
    0
    installs
  44. Handoff Discipline · yeaight7
    Use 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.
    0
    installs
  45. Hook Safety Review · yeaight7
    Use 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.
    0
    installs
  46. MCP Server Builder · yeaight7 bundle
    Design 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.
    0
    installs
  47. Agent Readable Docs · yeaight7
    Use 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.
    0
    installs
  48. Bigquery Cost Audit · yeaight7
    Use 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.
    0
    installs
  49. Change Impact Check · yeaight7
    Use 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.
    0
    installs
  50. Changelog Generator · yeaight7
    Use 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.
    0
    installs
  51. Context Compression · yeaight7 bundle
    Use when conversation context is bloated, constraints are being forgotten, or a compact handoff is needed before continuing work.
    0
    installs
  52. Gh Address Comments · yeaight7
    Address 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.
    0
    installs
  53. Using Git Worktrees · yeaight7
    Use 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
    0
    installs
  54. Agent Harness Design · yeaight7
    Use 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.
    0
    installs
  55. Context Minimization · yeaight7
    Use 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.
    0
    installs
  56. Dataset Split Review · yeaight7
    Use when reviewing how data is split into train/validation/test sets -- especially with time-series data, repeated entities (users, patients, sessions), or imbalanced targets.
    0
    installs
  57. Log Driven Diagnosis · yeaight7
    Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.
    0
    installs
  58. Minimal Reproduction · yeaight7
    Use when a bug must be isolated from a large application into a standalone, runnable script or single test case.
    0
    installs
  59. Regression Bisecting · yeaight7
    Use when a bug was recently introduced but you don't know which commit caused it.
    0
    installs
  60. Systematic Debugging · yeaight7 bundle
    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
    0
    installs
  61. AI Regression Testing · yeaight7
    Use 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.
    0
    installs
  62. Doc Consistency Check · yeaight7
    Use 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.
    0
    installs
  63. Incremental Migration · yeaight7
    Use when migrating APIs, libraries, or patterns across a large codebase and a single mega-commit would be too risky to review or merge.
    0
    installs
  64. Memory Build Workflow · yeaight7
    Use 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.
    0
    installs
  65. Memory Query Workflow · yeaight7
    Use when a graph already exists and the user needs retrieval, tracing, explanation, or gap detection from graph memory before reopening the full corpus.
    0
    installs
  66. Receiving Code Review · yeaight7
    Use when receiving code review feedback, before implementing suggestions — requires technical verification and reasoned pushback, not performative agreement or blind implementation.
    0
    installs
  67. Secret Leak Preflight · yeaight7
    Use 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.
    0
    installs
  68. Skill Authoring Guide · yeaight7 bundle
    Create or refactor high-quality skills with lean frontmatter, progressive disclosure, and optional bundled helpers. Use when authoring reusable agent workflows.
    0
    installs
  69. Webapp Visual Testing · yeaight7
    Use 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.
    0
    installs
  70. Agent Runtime Patterns · yeaight7 bundle
    Use when optimizing agent runtime loops, card packs, MCP session lifecycle, tool-call count, or multi-agent orchestration patterns.
    0
    installs
  71. Build Fix Minimal Diff · yeaight7
    Use 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.
    0
    installs
  72. Context Retrieval Loop · yeaight7
    Use 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.
    0
    installs
  73. Markitdown File Intake · yeaight7 bundle
    Use when the user provides a MarkItDown-supported file or URL and converting it to Markdown first will make inspection easier, cheaper, or more reliable.
    0
    installs
  74. Metric Impact Analyzer · yeaight7
    Use 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.
    0
    installs
  75. Requesting Code Review · yeaight7 bundle
    Use when completing tasks, implementing major features, or before merging to verify work meets requirements.
    0
    installs
  76. Requirements Clarifier · yeaight7
    Use 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.
    0
    installs
  77. Search Before Building · yeaight7
    Use 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.
    0
    installs
  78. Agent Session Forensics · yeaight7 bundle
    Use when diagnosing agent session history, interrupted tool loops, missing tool results, timing bottlenecks, or subagent trace correlation.
    0
    installs
  79. Deploy Pipeline Runbook · yeaight7
    Use 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.
    0
    installs
  80. Red Team Eval Authoring · yeaight7 bundle
    Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
    0
    installs
  81. Test Driven Development · yeaight7
    Use when implementing any feature or bugfix, before writing implementation code
    0
    installs
  82. Flaky Test Investigation · yeaight7
    Use when tests pass and fail intermittently without code changes, or a test passes alone but fails in the full suite.
    0
    installs
  83. Github CI Failure Triage · yeaight7 bundle
    Use when a GitHub PR shows failing checks and a clean failure readout is needed before changing any code.
    0
    installs
  84. Hard Won Skill Extractor · yeaight7
    Use 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.
    0
    installs
  85. Managed Codebase Context · yeaight7 bundle
    Use when connecting to a managed codebase-context MCP/session service, checking stale maps, or safely using MCP-provided repository context.
    0
    installs
  86. Pre Release Verification · yeaight7
    Use when a release candidate needs final checks before tagging, publishing, or production deployment.
    0
    installs
  87. Prompt Evaluation Runner · yeaight7 bundle
    Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
    0
    installs
  88. Test Preserving Refactor · yeaight7
    Use when code needs restructuring and observable behavior must stay unchanged, with existing tests kept green at every step.
    0
    installs
  89. Browser Automation Safety · yeaight7 bundle
    Use when validating rendered web pages, local dev servers, browser automation, screenshots, forms, auth sessions, or UI evidence with strict browser safety boundaries.
    0
    installs
  90. Canonical Advisor Routing · yeaight7
    Use 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.
    0
    installs
  91. Filesystem MCP Guardrails · yeaight7 bundle
    Use when designing or reviewing filesystem MCP access, path boundaries, allowed roots, method allowlists, and safe local file operations.
    0
    installs
  92. Parallel Execution Engine · yeaight7
    Use 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.
    0
    installs
  93. SQL Business Logic Review · yeaight7
    Use 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.
    0
    installs
  94. Baseline Comparison Review · yeaight7
    Use 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.
    0
    installs
  95. Codebase Migration Batches · yeaight7
    Use 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.
    0
    installs
  96. Experiment Tracking Review · yeaight7
    Use 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.
    0
    installs
  97. Model Evaluation Reporting · yeaight7
    Use 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.
    0
    installs
  98. Persistent Completion Loop · yeaight7
    Use 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.
    0
    installs
  99. Release Readiness Protocol · yeaight7
    Use when preparing a versioned release and release metadata, validation, publish commands, and rollback plan must be checked before tagging.
    0
    installs
  100. Reproducible Training Runs · yeaight7
    Use 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.
    0
    installs