Business
before-you-build
Product-risk review before implementation. Challenges demand, positioning, monetization, retention, trust, distribution, and feature-adoption risk before an agent starts building. …
Engineering
pydantic-ai-skills
Pydantic AI with agentskills.io. Type-safe schema validation for skill inputs/outputs.
Engineering
spring-boot
Use when creating, modifying, or working on Spring Boot projects. Triggers: creating a new Spring Boot application, adding REST endpoints, writing Spring services or repositories, …
AI / ML
darwin-skill
Darwin Skill 2.0 (达尔文.skill 2.0): autonomous skill optimizer, v2.0 integrates Microsoft Research SkillLens (arXiv 2605.23899) 9-dim rubric + SkillOpt (arXiv 2605.23904) validation-…
Testing
skills-lint
Validate Agent Skills against Anthropic open standard specifications, checking YAML frontmatter, file naming, description quality, version consistency, and content constraints. Use…
Testing
pulser
Diagnose and test Claude Code skills against Anthropic's 7 principles. Scans SKILL.md files, checks 8 rules (gotchas, description, allowed-tools, file-size, structure, frontmatter,…
Productivity
cerebro-doctor
Meta-audit of the skill system. Walks `{brain_root}/skills/` + `{brain_root}/AGENTS.md` and reports three classes of drift: (a) skills with no resolver row (unreachable), (b) AGENT…
Engineering
claude-codex-collaboration
Enable automated collaboration between Claude Code and Codex CLI using Byterover as shared memory. This skill should be used when architectural review or code validation from Codex…
Productivity
skills-check
Validates and reviews skills against the Agent Skills specification. Checks YAML syntax, naming conventions, description quality, file structure, and best practices. Provides impro…
Research
spectralbio-canonical-replay-and-portability-audit
Execute the frozen TP53 canonical replay, verify machine-checkable outputs, and inspect replay-ready portability surfaces across TP53, BRCA2, TSC2, and CREBBP, with BRCA1 and MSH2 …
Automation
commands-manager
Branch skill for building and improving commands. Use when creating new slash commands, adapting marketplace commands, validating command structure, working with $ARGUMENTS, or imp…
Data
spreadsheet-data-cleaning
Profiles, cleans, standardizes, transforms, fills, and deduplicates spreadsheet or delimited data into an authorized output with traceable rules, before/after stats, audit log, and…
Engineering
codex
Review code changes, implementation plans, or specific files using OpenAI Codex CLI. Triggers on "review", "check", "validate", "codex". Perfect for maker-checker workflows where y…
Testing
catalog-audit
Validate product data integration between Adobe Commerce and an AEM Edge Delivery Services storefront. Checks Catalog Service API connectivity, product data rendering accuracy, pri…
Business
geju
Delivers high-altitude strategic direction: a sharp thesis on target model, kill-list for delete/merge/split/reframe, Conservative-vs-Clean-vs-Staged options table, verification pa…
Testing
check-subagent
Audits custom subagent definitions against deterministic checks for location, frontmatter, naming, tools, prompt size, and structure, plus judgment dimensions covering scope, routi…
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 …
Research
food-deep-research
Produces fully written, source-validated literature reviews on any topic: scopes questions, discovers and screens sources by journal ranking, validates evidence, synthesizes findin…
Documentation
awl-frontmatter
YAML frontmatter standard for agents and commands: required fields (name, description), recommended (tools, model), optional metadata (version, category, color), with four-tier mod…
Data
analytical-self-review
Final analytical gate: runs after sensitivity and multiverse checks, before any summary or finding. Scans for Simpson's paradox, base-rate fallacy, leakage, p-hacking, ecological f…
Data
ontology
Typed knowledge graph for structuring agent memory and composable skills. Supports creating and querying entities such as Person, Project, Task, Event, or Document, linking related…
Productivity
story-analyze
Audits alignment between story.md, design.md, and implementation artifacts (testcases.md or tasks.md) before coding. Requires at least one of testcases.md or tasks.md; rejects if b…
Security
coverage-assessment
Validates provider credentials through NPI lookup, checks Medicare coverage rules via CMS, and evaluates clinical evidence against payer requirements with MET/NOT_MET/INSUFFICIENT …
Business
mittelstand-ma-tabellenreview
Reviews tables, formulas, and data points in corporate/M&A documents using a three-perspective internal matrix covering legal, tax, and economic factors. Validates formulas, checks…
Productivity
notion-prd-intake
Scans a Notion PRD database, validates the first ready-status page through the review pipeline, then either creates tickets and advances status or posts clarifying questions and bl…
Business
guimkt-offer-diagnosis
Evaluates offer strength across eight dimensions before ICP, ads, or landing pages are created. Scores clarity, specificity, proof, uniqueness, perceived risk, objections, real ver…
Engineering
muse-dev-patterns
Guides engineering discipline for triaging gate failures, probing live paths, validating tests, calibrating thresholds from measurement, and landing slices with proper writeback. A…
Business
offer-policy-checker
Validates proposed commissions, offers, or outbound actions against policy rules—checking tier caps, take-rate gates, product eligibility, and anti-spam parameters. Returns pass/wa…
Testing
pre-generation-check
Validates all pre-generation gates before sending tracks to Suno. Checks sources verified, lyrics reviewed, pronunciation resolved, explicit flag set, style prompt complete, and ar…
Engineering
unikit-fix
Fix bugs or issues in a project. Supports immediate fixes or plan-first mode. Executes .unikit/FIX_PLAN.md when no arguments provided. Validates compilation, recommends test covera…
Automation
flowing
DAG workflow runner encoding control flow in code. Enforces multi-step procedures with branching, retries, and validation via `when=`, `validate=`, and `retry_until=`. Owns executi…
Automation
converge-loop
Runs a bounded self-correcting loop that iterates until a measurable target state is reached or termination criteria (done-condition, max iterations, budget, no-progress) are met. …
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…
Testing
forge-clarify
Clarify and validate issues before planning. Reproduces bugs via browser, verifies UX expectations, and captures evidence screenshots. Moves issues from confirmed to clarified stat…
Engineering
pydantic-v2
Pydantic v2 patterns for production Python: validators, computed fields, strict types, discriminated unions, settings management, model serialization, Decimal handling for money, p…
Testing
ontology-validator
Validate material sample annotations against ontology constraints by checking class and property existence, verifying domain and range consistency for object properties, assessing …
Testing
aoa-eval
Routes evaluation work by surfacing session readiness packets, checking local and central eval surfaces, then selecting apply, local intake, design, or mining paths while respectin…
Productivity
skill-creator
Guides the agent through authoring and validating agent skills. Use when creating new skill directories, tightening skill metadata, extracting supporting references, or preparing s…
Automation
business-rules-reference
Integrates with Rossum for business-rules validation: native /v1/rules (TxScript trigger_condition + actions) and legacy Business Rules Validation Store (checks[] config, result ty…
Content
publish-storyline-book
Publishes chapter story outlines into a Storyline website and GitHub repository with metadata, README, full-book overview, route map, continuous narrative, and content validation. …
Research
animal-and-cell-validation-planner
Designs cell-based and animal-based validation plans that translate computational, omics, biomarker, genetic, or clinical findings into experimentally testable routes. Defines the …
Engineering
contract-acquisition
Retrieves a platform, library, or infrastructure contract directly from its toolchain oracles before writing against unfamiliar systems. Detects stack and version, then runs valida…
Testing
regle-advanced
Advanced Regle form validation: collection rules with $each, async/$pending handling, server/externalErrors, $reset options, global config via defineRegleConfig, discriminated unio…
Engineering
veomni-review
Mandatory pre-commit review gate. Triggers on multi-file edits, shared infrastructure changes, or uncertain fixes. Launches a subagent to validate implementation quality, cross-fil…
Testing
visa-inspector
Defines acceptance criteria, prospective parity tests, and validation metrics to confirm implementation matches discovered specifications. Produces `acceptance_specs.md` and Gherki…
Security
false-positive-reduction
Runs a false-positive reduction cycle on playbook sets: extracts overlapping patterns, classifies real risks, adds match.none discriminators, and validates via review and test comm…
Engineering
iru-code
Drives execution of implementation_plan.md tasks group-by-group: implements each group (parallel where allowed), validates, marks complete, then updates docs and archives the plan.…
Testing
dos-witness-claim
Route subagent claims through a witness step that extracts verifiable effects (git commits, files, DB rows) and confirms them via independent read-back before folding. Driven by do…
Business
idea-validator
Score income ideas against Layer 1 feasibility (market, simplicity, fit, legal, exit) and Layer 2 differentiation (saturation, moat, AI risk). Compare ideas via weighted matrix, ge…
Data
ontology-zh
Typed knowledge graph for structuring agent memory and composable skills. Supports entity creation and queries for Person, Project, Task, Event, or Document, linking objects, const…
Testing
aif-verify
Verify completed implementation against the plan. Checks that all tasks were fully implemented, nothing was forgotten, code compiles, tests pass, and quality standards are met. Use…
Testing
product-flow-validation
Validates end-to-end product meaning across user flows after UI or interaction changes. Checks that entry copy, choices, runtime state, persistence, recovery, history, and return s…
AI / ML
shadow-ds-govern
Runs a 5-voice data-science governance council on an ML artifact: Data Steward (drift), Model Validator (calibration), Fair-ML Auditor (EEOC 80% rule), Reproducibility Critic, and …
Automation
skillify
Captures the latest successful scrape sequence and saves it as a reusable browser skill on disk. Future calls execute the pre-built script in ~200ms instead of re-driving the page;…
Productivity
plan-grill
Determines when a request needs upfront planning before implementation, then validates the baseline, explores design options, and defines clear success criteria and observable outc…
Productivity
windags-looking-back
Applies Polya's four questions after WinDAGs execution. Q1 and Q2 run on every DAG; Q3 and Q4 trigger only on quality and cost thresholds, asynchronously, without delaying delivery…
Productivity
prototyping-pretotyping
Guides validation of ideas before full development using pretotyping techniques such as fake doors, concierge MVPs, and Wizard of Oz tests, plus prototyping at the right fidelity l…
Content
springer-food
Validates and formats manuscripts for Springer food journals including Food Engineering Reviews, Food and Bioprocess Technology, Food Security, and Food Production Processing and N…
Research
structured-element-extraction
Decomposes case facts or legal issues into a complete, mutually exclusive, and verifiable element checklist using MECE principles with triple validation. Each element is tagged by …
Showing the top 60 of 5,185. See the full list →