Skill collection

casioreview20-glitch/forge-os

278 agent skills across 13 categories, read straight from the repository tree. The repo holds 384 SKILL.md files — 106 are the same skills republished elsewhere in the tree, and we count things rather than copies.

casioreview20-glitch11★ across the radarProfile →

278

Skills published

Categories

Stars on the repo

Tracked on the radar · 11★Repository facts and velocity →

AI & Agents · 192

All in category →

projecting-artifact-deltasUse when an agent needs current artifact state and changes since a checkpoint without receiving full…resolving-skill-conflictsUse when candidate techniques, providers, policy profiles, ownership rules, or tool effects cannot safely…certifying-release-evidenceUse when a source archive, package, container, skill registry, or product release needs reproducible proof…selecting-minimum-provider-setUse when a route has several procedural, knowledge, MCP, or tool providers and must choose the smallest…selecting-skill-sectionsUse when a technique package contains overview, procedure, decisions, verification, failure modes, examples…composing-technique-workflowsUse when one outcome requires multiple specialized techniques with branch, join, parallel, retry, or rollback…consolidating-project-memoryUse when decisions, blockers, conventions, and stable summaries must survive across tasks without treating…enforcing-context-budgetsUse when planned context, tool schemas, model output reserve, or retrieved artifacts may exceed tenant…explaining-route-decisionsUse when a human or agent needs a concise, auditable explanation of why techniques and providers were…

designing-extension-manifest designing-extension-messaging minimizing-extension-permissions auditing-agent-actions benchmarking-skill-utility detecting-skill-regression learning-from-agent-failures managing-artifact-lineage recovering-interrupted-runs resolving-user-intent reducing-saas-churn testing-saas-entitlements decomposing-bounded-contexts defining-domain-model designing-event-contracts designing-extension-points applying-cross-domain-analogies backcasting-from-the-future breaking-hidden-assumptions clustering-semantic-ideas designing-invisible-interfaces exploring-edge-users controlling-code-complexity documenting-public-interfaces+ 159 more

Code Review & Quality · 20

All in category →

promoting-skill-providersUse when a quarantined or candidate provider requests validated, stable, or certified status and must prove…enforcing-review-separationUse when artifact, code, finding, provider, or release approval requires independent review across principal…designing-integration-testsUse when designing integration tests is required during quality work, especially when the result must be…designing-unit-testsUse when designing unit tests is required during quality work, especially when the result must be traceable…running-controlled-chaosUse when running controlled chaos is required during quality work, especially when the result must be…running-differential-testsUse when running differential tests is required during quality work, especially when the result must be…testing-accessibilityUse when testing accessibility is required during quality work, especially when the result must be traceable…testing-concurrent-behaviorUse when testing concurrent behavior is required during quality work, especially when the result must be…testing-end-to-end-flowsUse when testing end to end flows is required during quality work, especially when the result must be…

fuzzing-untrusted-inputs measuring-mutation-resistance testing-properties-and-invariants testing-performance-budgets testing-platform-compatibility testing-production-load testing-service-contracts testing-service-resilience testing-state-machines testing-state-models evaluating-ai-quality

Security · 20

All in category →

decomposing-multi-domain-workUse when one request spans independent product, engineering, design, security, data, legal, or operational…expiring-stale-skillsUse when provider sources, tool APIs, model behavior, security assumptions, evaluators, or compatibility…planning-incident-responseUse when planning incident response is required during security work, especially when the result must be…protecting-secretsUse when protecting secrets is required during security work, especially when the result must be traceable…reviewing-data-privacyUse when reviewing data privacy is required during security work, especially when the result must be…reviewing-secure-designUse when reviewing secure design is required during security work, especially when the result must be…sandboxing-untrusted-executionUse when sandboxing untrusted execution is required during security work, especially when the result must be…scanning-dependency-vulnerabilitiesUse when scanning dependency vulnerabilities is required during security work, especially when the result…securing-software-supply-chainUse when securing software supply chain is required during security work, especially when the result must be…

modeling-security-threats running-security-release-gate testing-agent-tool-abuse testing-cost-abuse testing-authentication-authorization testing-input-validation testing-prompt-injection testing-rate-limits testing-tenant-isolation designing-enterprise-audit forgeos-skill-security-review

Data & Analytics · 13

All in category →

designing-data-migrationsUse when designing data migrations is required during architecture work, especially when the result must be…designing-data-modelUse when designing data model is required during architecture work, especially when the result must be…rehearsing-data-migrationsUse when rehearsing data migrations is required during operations work, especially when the result must be…testing-data-integrityUse when testing data integrity is required during quality work, especially when the result must be…governing-ai-dataUse when governing ai data is required during ai-products product work, especially when the result must be…designing-data-lineageUse when designing data lineage is required during data-platforms product work, especially when the result…designing-data-partitionsUse when designing data partitions is required during data-platforms product work, especially when the result…designing-data-pipelinesUse when designing data pipelines is required during data-platforms product work, especially when the result…managing-schema-evolutionUse when managing schema evolution is required during data-platforms product work, especially when the result…

operating-data-incidents securing-data-access testing-data-backfills testing-data-quality

Backend & API · 9

All in category →

Testing & QA · 5

All in category →

planning-parallel-agent-workUse when several work units are independent enough to execute concurrently but still need deterministic…retrieving-semantic-code-symbolsUse when an agent must orient in a large codebase or fetch one implementation body by stable symbol identity…detecting-semantic-duplicationUse when several skills or providers may express the same trigger, mechanism, outputs, evaluation surface, or…distilling-tool-outputUse when test, compiler, browser, database, or terminal output is too large for model context but must remain…issuing-trusted-execution-receiptsUse when a command, test, scanner, brokered tool, or sandbox run must produce evidence whose pass status and…

Documentation · 4

All in category →

writing-agent-skills-with-tddUse when creating or changing an agent skill whose behavior, routing, discipline, or technique must improve…writing-executable-plansUse when writing executable plans is required during planning work, especially when the result must be…writing-minimal-sufficient-codeUse when writing minimal sufficient code is required during implementation work, especially when the result…writing-agent-skillsUse when writing agent skills is required during meta work, especially when the result must be traceable…

Design & Presentation · 4

All in category →

validating-visual-asset-deliveryUse when validating visual asset delivery is required during visual-design product work, especially when the…designing-production-visual-systemsUse when designing production visual systems is required during visual-design product work, especially when…maintaining-prior-art-mapUse when maintaining prior art map is required during research work, especially when the result must be…designing-saas-onboardingUse when designing saas onboarding is required during saas product work, especially when the result must be…

Content & Marketing · 3

All in category →

calibrating-token-estimatesUse when estimated token counts differ systematically from provider-reported usage across models, content…designing-content-scriptsUse when designing content scripts is required during browser-extensions product work, especially when the…designing-game-content-pipelineUse when designing game content pipeline is required during games product work, especially when the result…

Workflow & Productivity · 2

All in category →

compiling-global-contextUse when an agent request must combine system policy, task state, skill sections, code, artifacts, memory…sequencing-task-dependenciesUse when sequencing task dependencies is required during planning work, especially when the result must be…

DevOps & Cloud · 1

All in category →

designing-ci-cdUse when designing ci cd is required during operations work, especially when the result must be traceable…

Business & Finance · 1

All in category →

designing-product-pricingUse when designing product pricing is required during product work, especially when the result must be…

Other · 4

binding-approvals-to-actionsUse when an irreversible, high-risk, scope-changing, or trust-changing operation requires a human decision…routing-capability-graphUse when the system must translate confirmed intent, failed gates, missing artifacts, risks, and tools into…invalidating-dependent-proofUse when a semantic change, artifact supersession, provider substitution, policy change, or source revision…validating-evidence-freshnessUse when a gate, artifact verification, finding closure, or release decision depends on evidence that may…

About this collection

How many skills does casioreview20-glitch/forge-os publish?

278 that pass our gate — each has a real description and a SKILL.md we could read. The repository actually contains 384 SKILL.md files, but 106 of them are the same skills republished in other folders, so we count things rather than copies.

How do I install one?

Every skill page carries its own command — `npx skills add casioreview20-glitch/forge-os --skill <name> --agent claude-code`. Swap the agent for codex, cursor or copilot.

Keep going

All skills →

The full catalog, by category and by tool.

Open Source Radar →

The repositories these collections come from.