Agent Skills·Tag ·validation
Tag · 6,339 skills

Agent skills tagged validation

6,339 SKILL.md skills tagged validation — the most complete ones are below, all usable across Hermes, Cursor, Codex, Gemini CLI, OpenCode, Claude Code and 30+ more agents.

Browse all 6,339 validation skills →

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. …
claude-codecodexhermesopenclawawesome-hermes-skillsproductionproduct-risk
Engineering
pydantic-ai-skills
Pydantic AI with agentskills.io. Type-safe schema validation for skill inputs/outputs.
hermesawesome-hermes-skillsproductionpydantic
Engineering
proof-of-work
Enforces validation and evidence before claiming work complete. Use before declaring implementation done, creating a PR, or submitting deliverables for review
openclawvalidationevidencepr
DevOps
git-workspace-review
Verifies workspace state and staged changes as a read-only preflight. Use before commits or PRs to confirm staged set is clean and correct
openclawgitworkspacepreflight
Productivity
shared-patterns
Provide reusable patterns for validation, error handling, scaffolding. Use for skill consistency
openclawpatternsvalidationerror-handling
DevOps
pr-prep
Prepares pull requests by running quality gates, drafting descriptions, and validating tests
openclawprquality-gatesvalidation
Testing
test-updates
Updates, generates, and validates tests using git-workspace context and TDD/BDD methodology
openclawtddbddtests
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, …
claude-codecodexcursorgemini-clispring-bootjavajpa
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-…
claude-codecodexcursorgemini-cliskill-optimizationrubricvalidation
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-…
claude-codecodexcursorgemini-cliskill-optimizationrubricvalidation
Productivity
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-…
claude-codecodexcursorgemini-cliskilllensrubricvalidation
Testing
skills-lint
Validate Agent Skills against Anthropic open standard specifications, checking YAML frontmatter, file naming, description quality, version consistency, and content constraints. Use…
claude-codecodexcursorgemini-clilintvalidationyaml
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,…
claude-codeclaude-codeskillsvalidation
Data
profile-imaging
Profiles a medical-imaging dataset before modeling: acquisition grid, voxel spacing, orientation, intensity range, present label values, target volume fraction, and size in millili…
claude-codecodexcursorgemini-climedical-imagingprofilingvalidation
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…
claude-codecodexcursorgemini-clitype:auditmeta-auditdrift-detection
Automation
loop-up
Multi-agent loop that auto-corrects multi-stage work: an orchestrator plans and validates upgrades, an implementer executes changes, a read-only observer logs actions, and an inspe…
claude-codecodexcursorgemini-cliai:agentmulti-agentorchestration
General
Quetzalcoatl
Validates meaning and value first, applies pressure-testing, runs agent teams, compares 3–5 alternatives, cross-checks across models, and turns the full workflow into a repeatable …
claude-codecodexcursorgemini-cliai:claudevalidationagent-teams
AI / ML
model-validation
Audits clinical-validation study design for medical-imaging models (segmentation, classification, detection) before reporting or manuscript. Enforces patient-level split integrity,…
claude-codecodexcursorgemini-clitype:auditclinical-validationmedical-imaging
AI / ML
uncertainty-imaging
Audits uncertainty quantification, OOD detection, and selective prediction layers in medical-imaging models, validating MC-dropout, ensembles, conformal intervals, and abstention r…
claude-codecodexcursorgemini-clitype:audituncertaintymedical-imaging
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…
claude-codecodexcursorgemini-cliclaudecodexcollaboration
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…
claude-codeskillvalidationyaml
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 …
claude-codecodexcursorgemini-clibioinformaticstp53replay
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…
claude-codecommandsclislash-commands
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…
claude-codecodexcursorgemini-clitype:auditspreadsheetcleaning
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…
claude-codecodexcursorgemini-cliopenaicodexcli
DevOps
manifeste
Manages WAMA manifest layers (apps, libraries, models, functions, pipelines, projects, datasets) — extract, compose via requires, validate, and ingest. Activates for any request to…
claude-codecodexcursorgemini-climanifestwamalayers
Documentation
okhp3-mermaid-governance
Manages Mermaid governance profiles for visual and behavioral standards across diagram projects. Validates diagrams against declared profiles, audits for cross-project coherence, a…
claude-codecodexcursorgemini-clitype:auditmermaidgovernance
Data
product-search
Performs ingredient-level verification of supplement and product recommendations by cross-checking against user constraints in MEMORY.md and medical-history.md, fetching actual pro…
claude-codecodexcursorgemini-clisupplementsverificationingredients
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…
claude-codecodexcursorgemini-clitype:audittype:integrationadobe-commerce
Engineering
generate-ppmplugin-manifest
Validates and stages a `manifest.json` for `.ppmplugin` bundles, reconciling entrypoints to target platforms after running compatibility checks (name regex, prefixes, method shapes…
claude-codecodexcursorgemini-clitype:generatormanifestppmplugin
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…
claude-codecodexcursorgemini-clistrategyreframingthesis
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…
claude-codecodexcursorgemini-clitype:audittype:reviewsubagent
Research
reference-validation
Validate references in an academic PDF. Phase 1 extracts text + parses refs. Phase 2 verifies EVERY ref individually via WebSearch (existence + topic relevance), confirms cited arX…
claude-codeacademicreferencesvalidation
Data
dq-validator
Data quality validation across any database: completeness, syntactic/semantic correctness, internal/external consistency, and uniqueness checks on operational tables, lookup tables…
claude-codecodexcursorgemini-clitype:auditvalidationcompleteness
DevOps
id-validate
Performs static validation of infrastructure changes before testing or merging: resolves the active stack profile, executes read-only `tofu validate` and `tofu fmt`, and evaluates …
claude-codecodexcursorgemini-clitofuconftestopa
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 …
claude-codecodexcursorgemini-cligovernancevalidationquality
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 …
claude-codecodexcursorgemini-cligovernancevalidationquality
Business
sales-miskmap
Sales idea validator that scores a concept 0-100 across market urgency, defensibility, monetization, and distribution, then returns a BUILD / PIVOT / DON'T BUILD verdict, competito…
claude-codecodexcursorgemini-cliai:claudesalesvalidation
DevOps
tss-batch-prefetch
Maintains the batched TSS-prefetch list of peripheral updaters. Use when onboarding new device models, debugging TSS POST rejections, or extending prefetch coverage to additional c…
claude-codecodexcursorgemini-clitssprefetchdevices
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…
claude-codecodexcursorgemini-clitype:reviewliterature-reviewfood-science
Content
h3-reality-physics-guard
Pre-generative physics and reality gate for 5–15s clips. Classifies subject reality mode, runs an eight-category fact check against a fixed priority ladder, and outputs a Reality S…
claude-codecodexcursorgemini-climinimax-h3physicsreality-check
Research
numerical-check
Numerically stress-test a self-authored mathematical claim over its parameter space to seek counterexamples or characterize violations. Use when checking monotonicity, thresholds, …
claude-codecodexcursorgemini-climathematicsnumerical-analysiscounterexamples
Documentation
skill-description-audit
Cross-validates an Agent Skill's SKILL.md frontmatter and description against its implementation body, checking compliance, claim accuracy, non-emptiness, trigger words, rename res…
claude-codecodexcursorgemini-cliai:agenttype:auditaudit
Engineering
deep-assessment
Performs comprehensive whole-project audits on demand, orchestrating layered validation instruments plus specialized checks for gate efficacy, citation sampling, adoptability, and …
claude-codecodexcursorgemini-clitype:auditauditvalidation
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…
claude-codecodexcursorgemini-cliearsacceptance-criteriareview
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…
claude-codecodexcursorgemini-cliyamlfrontmattermarkdown
Testing
grounding-conformance
Audits frozen acceptance-contract.yaml files against the current system-state snapshot, classifying each as GROUNDED, UNGROUNDED, or STALE using structural and consistency validato…
claude-codecodexcursorgemini-clivalidationconformanceaudit
AI / ML
tool-schema-design
Design and validate model-facing tool schemas with precise names, action-oriented descriptions, bounded JSON parameters, explicit side effects, safe defaults, idempotency, and test…
claude-codecodexcursorgemini-clifunction-callingjson-schemaagents
Engineering
check-xaml-layout
Detects and fixes visual layout defects in CvWpfclient XAML - clipped text, insufficient margins, bottom/right cut-off, missing ScrollViewer, hardcoded sizes, and design inconsiste…
claude-codecodexcursorgemini-clixamlwpflayout
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…
claude-codecodexcursorgemini-clitype:reviewreviewbias
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…
claude-codecodexcursorgemini-cliontologyknowledge-graphentities
Engineering
review-contrib
Audits contributor commits or PRs from forks before merge: validates conflicts, runs tests/lint/build, performs code review, fact-checks external rules against primary sources, gen…
claude-codecodexcursorgemini-clitype:audittype:reviewpr-review
Research
target-validation-ladder
Ranks drug-target genetic validation on a causality ladder from rare-variant/Mendelian evidence through coding GWAS, Mendelian randomization, and non-coding signals; outputs a 0-13…
claude-codecodexcursorgemini-clidrug-discoverygeneticsvalidation
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…
claude-codecodexcursorgemini-clitype:audituser-storiesvalidation
Business
create-business
Guides teams from raw idea through validation, positioning, pricing, and beachhead selection by sequencing ten complementary frameworks—jobs-to-be-done, Mom Test, design sprints, l…
claude-codecodexcursorgemini-clibusinessvalidationstrategy
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 …
claude-codecodexcursorgemini-clinpimedicarevalidation
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…
claude-codecodexcursorgemini-clitype:reviewtablesformulas
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…
claude-codecodexcursorgemini-clitool:notiontype:reviewnotion
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…
claude-codecodexcursorgemini-clitype:debugoffermarketing
Engineering
implement-tickets
Coordinates a batch of normalized tickets by building a dependency graph, grouping same-file work, dispatching groups to agents with fresh context, validating each against acceptan…
claude-codecodexcursorgemini-cliticketsdependency-graphbatch-processing

Showing the top 60 of 6,339. See the full list →