2.6K skills · sorted by relevance
Turn agent activity and transcript token counts into a cost report organized around completed outcomes. Separate estimates from measured spending, examine waste and rework, and export readable HTML with supporting JSON, CSV, and evidence.
Reviews completed changes through hands-on checks and one reviewer agent. It compares the implementation and recorded evidence with the original goal, constraints, code quality, and security requirements, then reports approval, specific blockers, or an inconclusive result.
Analyze price swings to detect Elliott Wave structures: five waves following a trend and three waves correcting it. Check wave rules and Fibonacci ratios, then generate signals for completed advances or pullbacks using a pandas implementation.
Perform live Windows or macOS desktop tasks that dedicated tools cannot complete. The skill guides app and window selection, clicks, text entry, and keyboard actions, checking fresh screen information and verifying the requested result.
Manage a running task list in a gbrain page using stable IDs and four priority levels. Add, complete, defer, remove, or review tasks while recording completion dates and deferral reasons, and clarifying ambiguous task references before changes.
Turn call notes, meeting transcripts, or email exchanges into completed CRM activities linked to the relevant account, deal, and contacts. Review the entry with its sources, save it on request, and check past activity.
Review logs and source files from a completed manual example run. Check that results are current and complete, verify intended behavior beyond successful exit codes, and distinguish product defects from environment or credential problems.
Review completed code changes against the original requirements, choosing review depth by behavioral risk. Coordinate independent reviewers, resolve actionable findings, and verify that the delivered changes match the content actually reviewed.
Review completed AI work by scoring task difficulty and execution quality separately. A fixed scoring matrix, arguments for higher and lower ratings, and saved score history help examine weaknesses and detect repetitive scoring patterns across sessions.
Archive several OpenSpec changes together after reviewing their documents, task completion, and specification conflicts. The agent checks actual code to decide which specification updates to apply, asks for confirmation, and reports successes, skipped changes, and failures.
Learn the complete OpenSpec workflow through a small task in an actual codebase. The agent explains each stage while creating a proposal, specifications, design, and tasks, then implements the change and archives its records.
Review a completed development task against its acceptance criteria, check differences from design and architecture documents, and prompt code review. After approval, update the task's status and identify the next story to work on.
Build a short, playable game sequence before full production to check whether the complete gameplay loop works at the intended quality. Use playtest observations and daily progress records to assess feasibility and decide the next direction.
Evaluate whether completed experiments support a research claim using a separate Codex reviewer. Identify unsupported conclusions and missing evidence, then determine whether to revise the claim, run additional experiments, or move toward paper writing.
Develop mathematical proofs for machine learning and AI theory by checking assumptions, intermediate results, and edge cases. Produce a complete proof, a corrected claim with its proof, or a report explaining the unresolved gap.
Prepare a conference talk from a completed paper, including an outline, Beamer slides, editable PPTX, speaker notes, and a full script. Polish the visuals, check exported files, and optionally audit claims, citations, and anonymity.
Uses a completed ZKsync Era investigation with no reportable findings as a defense study. It explains 25 tested attack vectors, the safeguards that blocked them, and criteria for deciding whether to continue reviewing a large bridge protocol.
Work through design or implementation choices one at a time, with concise context and clear alternatives. You can also review completed code change by change, recording decisions, approvals, and requested revisions in a final table.
Track shared work across AI agents using a SQLite database. The skill claims tasks, records progress and evidence for each step, skips completed work, and checks required procedures before marking a task complete.
Prepare a structured JSON handoff for bug fixes or pull request reviews. Capture outcomes, test evidence, change impact, publication status, and remaining work so the next person or workflow can understand what is complete and what remains.
Audit validation coverage for a completed development phase and fill missing checks. The skill updates VALIDATION.md, reconstructs missing validation records from existing project artifacts, and generates test files to address gaps.
Review open GitHub issues and pull requests against project templates and contribution guidelines. Get a report on missing information and compliance, with options to apply recommended labels or close incomplete submissions with an explanatory comment.
Extract decisions, lessons, recurring patterns, and unexpected findings from the artifacts of a completed development phase. It organizes these learnings into a LEARNINGS.md file using planning, summary, verification, acceptance testing, and state documents.
Add tests to a completed development phase using its records and implementation. Review the proposed coverage, then generate unit tests for individual components and browser tests for full workflows, verify them, and commit the test files.