Engineering
dorodango
Polishes working code through successive quality passes in fresh subagents. Use after tests pass when code needs multi-dimension refinement before release
Testing
quality-gate
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates
Productivity
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits
Engineering
pr-review
Reviews pull requests with scope validation, requirements compliance, and line comments
Engineering
code-refinement
Improves code quality across duplication, efficiency, and architectural fit
Productivity
skills-eval
Evaluate Claude skill quality through auditing
Testing
quality-playbook
Explore any codebase from scratch and generate six quality artifacts: a quality constitution (QUALITY.md), spec-traced functional tests, a code review protocol with regression test…
Security
salesforce-apex-quality
Apex code quality guardrails for Salesforce development. Enforces bulk-safety rules (no SOQL/DML in loops), sharing model requirements, CRUD/FLS security, SOQL injection prevention…
Engineering
brutal-agent
Orchestrate subsystem-by-subsystem project hardening by combining brutal-project-review and task-worker in a strict loop: review one subsystem, create CRITICAL/MAJOR tasks, run all…
Engineering
config-drift-detect
Audit project gates including coverage thresholds, tsconfig strictness, eslint rules, husky/lint-staged, sonar quality gate, and branch protection. Flags values mathematically inco…
Engineering
loopx-change-quality
Qualify the exact final diff for a LoopX-managed goal. Use when policy requires change_quality_qualification before non-trivial delivery or merge, or when producing or repairing an…
General
yes-ja
Triggers on file, config, database, or deployment changes; repeated debug failures; unsupported guesses; deferring to users; unverified completions; root-cause conclusions; unused …
General
yes-zh
Triggers on file, config, database, or deployment changes; repeated debug failures; unsupported guesses; deferring to users; unverified completions; root-cause conclusions; unused …
Data
list-quality-scorecard
Pre-send quality scorecard for any lead list. Grades duplicate rate, title diversity, bad-title patterns, catch-all domain density, ICP fit, email verification coverage. Outputs a …
Testing
yamlet-criteria-challenger
Adversarial reviewer invoked inside the yamlet-author flow to surface gaps in a proposed requirement and its EARS acceptance-criteria before commit. Flags multi-capability bundling…
General
conscientiousness
Apply thoroughness and diligence in execution through systematic checking, completeness verification, follow-through on commitments, and disciplined task completion. Use before mar…
Productivity
ultraloop
Completion discipline that treats a task as done only when the result is verified and demonstrably works. Inspects the repo first, sets explicit assumptions and a Definition of Don…
Productivity
skill-streamlining-audit
Audit a single skill directory (SKILL.md, references, templates) to detect redundant, contradictory, or outdated content and generate a severity-classified report recommending remo…
Testing
testing-philosophy
Defines test quality by prioritizing observable behavior over implementation details, establishing a Testing Trophy with minimum end-to-end coverage for user-facing features. Appli…
DevOps
ai-sdlc-quality-lenses
Applies structured quality lenses—pre-mortem, adversarial, edge-case, stakeholder, reversibility, abuse-case, operational-failure—to challenge requirements, designs, plans, tests, …
DevOps
workflow-green-repo
Drives any repository to a fully green baseline—typecheck, lint, tests, and build all passing from a clean checkout—when pre-existing debt is explicitly authorized. Enumerates ever…
Testing
police
Triple Gate quality enforcement system. Triggers on non-trivial builds. Runs three self-drafts plus six specialized validators across four phases with task isolation, compaction sa…
Documentation
audit-noise
Scans markdown for five noise patterns—stale citations, ghost references, existence preambles, hard-linked consumer lists, and loading meta-commentary—assigning each to Tier 1 (rem…
Engineering
uberdev-cmd-ubersimplify
Performs whole-repo simplification across Reuse, Quality, and Efficiency lenses by partitioning code into balanced areas, auditing each with a multi-lens analyzer, and committing p…
Engineering
pr-verify
Validates pull request test plans with evidence-rated verdicts: extracts each item, classifies verification strategy, gathers cited evidence, and issues PASS/FAIL/PARTIAL ratings a…
Business
bigdata-earnings-quality-screen
Screens public-company earnings for quality issues and accounting red flags via Bigdata.com filings. Evaluates cash conversion, accruals, working-capital trends, revenue recognitio…
Engineering
ai-sdlc-requirements-readiness-review
Runs a final quality review on PRFAQ and BRD artifacts to surface gaps, contradictions, and readiness gaps before design begins. Supports quick assumption-driven or full question-d…
Documentation
wenbi-review
Reviews drafts or completed chapters across seven quality dimensions and hard gates. Returns the single highest-impact fix for iterative drafting, or writes a full YAML review with…
Automation
team-assembler
Activates when a workflow requires collective judgment: identifying takt imbalances needing line-level correction, distinguishing defects from acceptable variation before halting w…
Testing
quality-strategy
Audits or designs a project's verification strategy across types, static analysis, tests, contracts, fuzzing, monitoring, formal methods, reviews, and supply-chain controls. Conver…
Engineering
hv-review
Staff-engineer review of a feature branch before merge or PR — reads commits, diff, referenced item IDs, and matching knowledge topics; checks intent match, convention compliance, …
Testing
quality-eval-orchestrator
Routes quality, testing, and evaluation tasks to the right specialist among 12 focused skills covering eval-driven development, agent benchmarking, TDD, verification gates, E2E tes…
Research
analytical-method-validation
Plans and documents validation, verification, and transfer of analytical methods under ICH Q2(R2), Q14, USP <1220>/<1225>/<1226>, ICH M10, CLSI EP, and ISO/IEC 17025 for HPLC, LC-M…
Testing
aktenauszug-strukturpruefung
Validates completeness of a case extract covering case identification, introduction, summary, factual chronology, procedural history, party submissions table, evidence table, and l…
Documentation
product-doc-audit
Performs three-layer audit of product documentation sets: completeness vs required/optional docs, type-specific checkpoints, and cross-validation alignment. Outputs readiness score…
Data
lead-quality-pattern-analysis
Red flag detection frameworks for lead quality analysis across GA4 behavioral data. Identifies bot traffic, no-shows, and conversion patterns using five structured analysis framewo…
Testing
skill-quality-gate
Evaluates skill trigger conditions, execution flow, output contracts, validation methods, and regression quality for any SKILL.md-based agent. Supports pre-release checks, before-a…
Engineering
app-quality-patterns
Guides spec and implementation of app features using battle-tested behavioral quality patterns (QP-xx) for stateful URLs, deletion cascades, empty/loading states, and mutation guar…
Engineering
plan-exit-review
Pre-implementation engineering review that stress-tests scope, architecture, quality, and test strategy of a concrete plan before any code is written. Delivers opinionated, recomme…
Testing
validate-skillmd
Validates SKILL.md files through four tiers: basic location, IS 100-point rubric grading, static production checks (tools, auth, safety), and optional JRig 7-layer behavioral evalu…
Security
reviewing-changes
Apply layered quality gates to code changes: quality, security, and architecture. Produces severity-ranked findings with concrete fixes tied to file:line. Supports OWASP Top 10, SO…
Documentation
kb-create
Guided pattern and bug creation with interactive prompts and automatic quality validation. Helps users build high-quality KB entries with proper structure, scoring, and categorizat…
Content
course-quality-editor
Reviews entire courses or individual chapters for cognitive delivery, module sequencing, logic flow, information density, narration pacing, factual accuracy, and AI writing artifac…
Productivity
jira-write-ticket
Creates or updates Jira tickets with enforced quality standards: structured sections, Gherkin acceptance criteria, epic links, explicit relationships, remote references, labels, co…
Engineering
bashsmithing-report
Delivers structured Bash code quality audits via the SIFT Protocol V1.0, generating 8-section reports covering architecture, compliance, and error handling. Accepts pasted code, fi…
Productivity
linear-write-issue
Manages Linear work items (Epics, Stories, Sub-tasks) with enforced quality standards: audience-focused descriptions, Gherkin criteria, parent-child hierarchy, explicit relationshi…
Engineering
work-review-request
Coordinates a reviewer subagent to inspect changes, enforces severity rules on findings, and manages the fix-and-re-review cycle until no Critical or Important issues remain. Use b…
General
course-quality-review
Performs evidence-based course quality audits aligned with Quality Matters and Community of Inquiry frameworks. Evaluates structural quality, teaching/social/cognitive presence, an…
Content
wenqu-review
Reviews Chinese content for factual accuracy, logical flow, terminology standards, translation artifacts, AI patterns, and structure. Works with articles, reports, tutorials, and p…
Testing
skill-validator
Audits and scores skills across nine production criteria—structure, content, interaction, documentation, standards, robustness, maintainability, zero-shot use, and reusability—deli…
Documentation
api-docs-quality-report
Crawls any API docs site to audit endpoint coverage across five quality checks—descriptions, spec presence, parameter docs, status codes, and schema completeness—then generates an …
Engineering
repo-quality-system-lifecycle
Define or audit structural quality contracts for agent-run repositories: charters, docs ownership, validation gates, evidence paths, and repair loops. Supports audits, maturity che…
Engineering
adhesive-bonding-machine-operator
Deploys adhesive bonding machine operator expertise to distinguish open-time violations from pot-life checks, control bond line thickness with calibrated spacers, verify surface pr…
Engineering
river-review-discipline
Enforces consistent review quality by classifying targets, separating requirements/design/diff/validation/report, and issuing evidence-based decisions (approved/needs_revision/bloc…
Testing
generated-video-quality
Detects generation-specific defects in AI video: identity drift, artifacts, physics violations, temporal breaks at splices, lip-sync drift, and prompt mismatch. Pair with general v…
Business
control-plan-builder
Builds complete Control Plan rows from PFMEA failure modes and process steps, specifying control methods, sampling plans, and reaction plans per AIAG and IATF 16949 §8.5.1. Use for…
Design
design-polish
Final quality pass fixing alignment, spacing, consistency, interaction states, and micro-details before shipping. Executes changes directly. Triggers on polish requests, finishing …
Testing
paper-autoraters
Execute the four paper-quality autoraters: Citation F1, Literature Review Quality (6-axis), SxS Overall Paper Quality, and SxS Literature Review Quality. Triggers on requests to sc…
DevOps
build-pre-commit-config
Generates a pinned, reproducible `.pre-commit-config.yaml` at the repository root that runs formatters, linters, and validators on staged files via the pre-commit framework. Option…
Research
dod-mq-bok
Knowledge base covering DoD Manufacturing and Quality Engineering Body of Knowledge v3.0 for acquisition lifecycle phases, M&Q threads, Manufacturing Readiness Levels, standards (A…
Showing the top 60 of 1,141. See the full list →