Loading...
Loading...
Found 3,053 Skills
Audits all OrchestKit skills for quality, completeness, and compliance with authoring standards. Use when checking skill health, before releases, or after bulk skill edits to surface SKILL.md files that are too long, have missing frontmatter, lack rules/references, or are unregistered in manifests.
Generate interactive prototypes from PRD documents. **This skill must be used when users need to generate interactive UI prototypes, multi-page jump demos, or quickly validate product designs based on PRD**. Trigger scenarios: Users say "generate prototype", "make a demo", "generate navigable prototype", "turn PRD into clickable pages".
Annotates codebases with dimensional analysis comments documenting units, dimensions, and decimal scaling. Use when someone asks to annotate units in a codebase, perform a dimensional analysis, or find vulnerabilities in a DeFi protocol, offchain code, or other blockchain-related codebase with arithmetic. Prevents dimensional mismatches and catches formula bugs early.
Agent skill for challenges - invoke with $agent-challenges
Verify whether a GitHub issue is fixed in the local codebase. User provides a GitHub issue URL, the skill fetches it, extracts reproduction steps, builds the product from source, runs the reproduction steps, and reports whether the issue still exists or not.
Side role: find and correct bad signals, earn leaderboard points per Publisher-approved correction (max 3/day)
Build and use the verification infrastructure coding agents need to prove their work. Use when: a repo has no bootable dev environment, no real-surface tests, or no interaction layer an agent can use; auditing or grading a repo's agent-readiness; verifying changes work end to end on real surfaces; or when harness gaps block reliable agent output.
Patient safety evaluation harness for healthcare application deployments. Automated test suites for CDSS accuracy, PHI exposure, clinical workflow integrity, and integration compliance. Blocks deployments on safety failures.
Walk through a Jira task plan and interactively confirm assumptions, resolve open questions, and validate decisions — using progressive disclosure. Only asks questions relevant to the CURRENT phase or task being executed. Use when the user says "review the plan", "ask me questions", "clarify assumptions", "let's go through the questions", "grill me on the plan", "validate plan for PROJECT-1234", or anything about reviewing, questioning, or validating a task plan. Also triggered by the orchestrating-jira-workflow skill as Phase 3 of the pipeline, and re-invoked during Phase 5 before each task execution. Requires a task plan at docs/<TICKET_KEY>-tasks.md.
Solve competition math problems (IMO, Putnam, USAMO, AIME) with adversarial verification that catches the errors self-verification misses. Activates when asked to 'solve this IMO problem', 'prove this olympiad inequality', 'verify this competition proof', 'find a counterexample', 'is this proof correct', or for any problem with 'IMO', 'Putnam', 'USAMO', 'olympiad', or 'competition math' in it. Uses pure reasoning (no tools) — then a fresh-context adversarial verifier attacks the proof using specific failure patterns, not generic 'check logic'. Outputs calibrated confidence — will say 'no confident solution' rather than bluff. If LaTeX is available, produces a clean PDF after verification passes.
Execute deep research on every item in a research outline, producing structured JSON per item and a final markdown report. Use after running /research to generate an outline. Reads outline.yaml and fields.yaml, launches parallel research agents in batches, validates output, generates a consolidated report, and supports resume on interruption. Trigger when the user says "start deep research", "research these items", "run the deep phase", "fill in the fields for each item", or "generate the research report".
ZeroBounce integration. Manage data, records, and automate workflows. Use when the user wants to interact with ZeroBounce data.