Engineering
pydantic-ai-skills
Pydantic AI with agentskills.io. Type-safe schema validation for skill inputs/outputs.
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…
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…
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
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…
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…
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…
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…
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…
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 …
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 …
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…
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…
Testing
verify-agent-output
Validates deliverables and builds evidence during agent handoffs, including pre-execution expectations, structured proof collection, post-execution validation against external anch…
Business
problem-framing
Discovery skill that restates the client problem, target user, current workaround, success signal, and generates a falsifiable hypothesis. Validates against falsifiability, specifi…
Automation
kb-orchestrator-workflow
Orchestrator-first workflow for building and shipping changes via KB Orchestrator. Sets up target repo or workdir, runs validation jobs with artifacts and safety checks, performs s…
Research
arxiv-preflight
Run a submission-readiness preflight on a manuscript before arXiv upload. Detect hallucinated references, LLM meta-comments, placeholder data, AI-use disclosure issues, and scholar…
Content
microcopy
Writes and reviews functional UI text including button labels, empty states, tooltips, dialogs, placeholders, loading messages, toasts, and validation copy. Applies patterns such a…
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…
Data
diff-nested-json-api-responses-and-config-snapshots-before-appro
Uses DeepDiff to compare structured objects deeply and return precise additions, removals, value changes, and deltas instead of noisy line-based diffs. Best when validating API pay…
Testing
graph-audit
Verify every SKILL.md conforms to schema, manifest entries match frontmatter, and relation targets point to real sibling skills. Covers schema conformance, manifest sync, relation …
Testing
mcp-server-evaluations
Test MCP servers for quality and reliability. Verify tool functionality, test error handling, generate tests, and assess response quality using only curl. Apply when validating imp…
Productivity
repo-assessing-criticality-confidence
Universal classification system for checker and fixer agents using orthogonal criticality (CRITICAL/HIGH/MEDIUM/LOW) and confidence (HIGH/MEDIUM/FALSE_POSITIVE) dimensions. Include…
DevOps
hm-deploy
Validate deployment by distribution model before first production release, after local environment issues, infra changes, or to confirm anyone can deploy from scratch. Covers Conta…
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…
Research
research-from-prd
Designs and runs structured user research across six blocks (Purpose, Plan, Criteria, Analysis, Conclusions, Next Steps) using JTBD, Mom Test, and Field Study. Positioned after PRD…
Testing
boolti-mixpanel-validator
Validate and suggest Mixpanel event implementations for Boolti AppTracker following official conventions. Triggered by requests to add, modify, or review tracking code for AppTrack…
Research
hypothesis
Write testable product hypotheses with clear success metrics, baselines, targets, and timeframes. Produces a structured statement, supporting evidence, validation plan with method …
Documentation
plan-challenger
Adversarial review of implementation plans — finds failure modes, hidden dependencies, scope risks, missing edge cases, and architecture concerns BEFORE coding begins. Use when a p…
Research
two-sample-mr-research-planner
Generate complete two-sample Mendelian randomization research designs from a user-provided research direction. Output four workload tiers (Lite/Standard/Advanced/Publication+) with…
Data
monte-carlo-prevent
Surfaces Monte Carlo table health, alerts, lineage, and blast radius on any referenced dbt model, SQL file, or table. Shapes code recommendations from those findings, generates mon…
Research
experiment-plan
Turn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap with ablation matrix, evaluation protocol, run order, compute budget, and paper-rea…
Content
ncp-author
Schema reference, canonical vocabulary, validation rules, and 10-stage workflow for NCP (ncp-schema.json v1.3.0). Coordinates with dramatica-theory and dramatica-vocabulary skills …
Automation
social-media-image-sizes
Validate image dimensions against specs for Instagram, Facebook, X, LinkedIn, TikTok, YouTube, Pinterest, Snapchat, and Threads. Run check.js to receive ranked matches and exact re…
Engineering
he-deepen-spec
Deepen an existing system or UI spec so boundaries, lifecycle rules, failure handling, and validation are strong enough for planning. Use when the user wants Harness Engineering sp…
Documentation
apsa-style
Validates APSA style in Quarto (.qmd) files. Checks numbers, capitalization, abbreviations, citations, titles, neutral language, and terminology per the APSA Style Manual, producin…
Business
problem-interview
Validates that a problem is real, painful, and worth solving before building. Applies Cindy Alvarez's structured approach to problem discovery interviews for customer discovery, pi…
Research
githubpill
Check whether a project idea already exists on GitHub before building. Returns a 🟢/🟡/🔴 verdict in ~90 seconds using gh api metadata. Deep-search option clones candidates and evalua…
Design
design-study
Reviews study design and validity for radiology and medical AI research. Checks analysis unit, cohort logic, leakage risks, comparator design, validation approach, and reporting gu…
Research
bio-pose-validation
Validate docked or generated protein-ligand poses with PoseBusters physical-validity tests, strain energy, geometric checks, and pose-energy assessment. Filter AI-docking outputs a…
Content
amcs-validator
Scores song artifacts against a blueprint rubric covering hook density, singability, rhyme tightness, section completeness, and profanity compliance. Returns scores plus an issues …
Data
fix-contribution
Fixes common issues in geographic data contributions to the CSC database. Use for data contribution or PR corrections, validation errors, removing auto-managed fields, fixing count…
Content
migrate-posts-to-v2-frontmatter
Migrates every post in content/posts/**/*.md to the v2 frontmatter schema: adds required summary field, normalizes tags to controlled vocabulary, converts dates to ISO 8601 with ti…
AI / ML
dataset-evaluation
Validates dataset formatting and quality for model fine-tuning (SFT, DPO, or RLVR). Detects file format, checks schema compliance against the selected model and technique, and repo…
DevOps
env-manager
Manages environment variables across .env files, .env.example, and documentation. Generates validation scripts, integrates with secret stores, prevents accidental commits via Git h…
Design
figma-check-design-parity
Compare a Figma node's specs against code implementation to produce a 0–100 parity score, discrepancy list, and fix suggestions. Detects design-to-code drift across visual, typogra…
Automation
goal-mode-tag-discipline
Provides exact regex and format rules for goal-mode tag emission, including parse-tags semantics, code-fence stripping, attribute quoting, and edge-case handling. Consult before em…
Research
Independent Research
Research-driven investigation skill for validating solutions and exploring documentation. Use web fetch, search, and testing to validate ideas before presenting them. Deliver concr…
Business
soldatenversorgungsgesetz-beschaedigtenversorgung
Validates eligibility, documentation, risks, and exceptions under the Soldatenversorgungsgesetz for disability benefits. References Soldatengesetz, Wehrbeschwerdeordnung, Wehrdiszi…
Automation
agentprivacy-dragon-flight
Threshold activation mechanics for the dragon metaphor. Covers dragon anatomy completion including boundary, hide, brain, forge, and ceremony, plus external validation triggers and…
Automation
bmad-create-story
Creates and enriches implementation-ready stories with real-data validation, external research, structured NFRs, security gates, observability requirements, deployment audits, impa…
Business
kanzlei-allgemein-ustva-simulation
Provides fallbacks when VAT filing or ELSTER fails. Walks through ELSTER simulation, manual entry, XML upload validation, software export, advisor package, error diagnosis and tran…
Research
zirkelschluss-pruefen
Detects circular references and self-referential chains in legislative drafts. Validates against direct, indirect, and tautological loops, checks EU dynamic references, and produce…
Security
global-validation
Implement comprehensive server-side validation with allowlists, type checking, input sanitization, and consistent error messages. Use when validating user input, form data, API req…
Security
kyverno-policy-review
Review Kyverno policies across ValidatingPolicy, MutatingPolicy, GeneratingPolicy, DeletingPolicy, and ImageValidatingPolicy. Assess safety, exceptions, enforcement mode, CEL migra…
Productivity
repo-applying-maker-checker-fixer
Three-stage content quality workflow (Maker creates, Checker validates, Fixer remediates) with detailed execution steps. Use for content quality workflows, validation, audit report…
Showing the top 60 of 2,222. See the full list →