527 skills · sorted by relevance
Create a standard folder layout for a DDD bounded context, a module organized around one business area. Generate TypeScript export files, keep infrastructure outside the public exports, and record the context in a domain model graph.
[BETA] AEM Cloud Service expert skill — handle an explicitly-unbounded query (`p.limit=-1` predicate or JCR `setLimit(-1)`): bound it when capping is provably safe, otherwise flag it for human pagination. Use for "bound my query", "unbounded query", "query causing OOM", or a scan that flags `p.limit=-1`. Top CSO OOM cause: an unbounded result set traversed in a loop fills the heap and saturates the instance. The analyzer locates the explicit markers; the recipe triages each by how the result is consumed — single-result → 1, already-bounded list → N, iterate-all on the request path → escalate. Never silently cap a result the caller reads in full. This skill is in beta. Verify all outputs before applying them to production projects.
The English summary is being prepared. Showing the original description.
Automatically repair source code against a failing test while preserving the test itself. Set a spending limit and attempt count, then receive verification results and usage costs based on rerunning the test command.
Delegate a bounded task to the local OpenClaw main agent without opening an interactive interface. Run it in an authorized directory, read its structured response, and check for reported errors or timeouts.
Use for bounded reasoning, partial planning, commitment policy, deliberation cost, and reconsideration-threshold design instead of assuming free deliberation. NOT for exhaustive planning, static optimization, or domains where reconsideration cost is irrelevant.
The English summary is being prepared. Showing the original description.
Use for bounded reasoning, partial planning, commitment policy, deliberation cost, and reconsideration-threshold design instead of assuming free deliberation. NOT for exhaustive planning, static optimization, or domains where reconsideration cost is irrelevant.
The English summary is being prepared. Showing the original description.
Coordinate bounded test runs for one Terminal-Bench task through Paperclip. Record evidence, diagnose failures, and manage approval for product fixes while keeping reruns in the same isolated working copy.
Use PathML for local pathology image research, from loading whole-slide images and splitting them into tiles to preprocessing and quality checks. Plan multiplex measurements, analyze spatial relationships between cells, and run model inference in bounded batches.
Use PyTDC to discover therapeutic machine-learning datasets, create task-appropriate training and test splits, and evaluate predictions against curated benchmarks. Also score selected molecules with supported scoring functions, with explicit download plans and bounded outputs.
Look up biomedical relationships in ARAX using explicit entity types and tightly bounded paths. Inspect direct links or paths through one intermediate entity, along with returned publications and source records, to identify candidates for further research.
Inspect supported local scientific files before modeling, summarize structure and missing values, and flag possible data leakage or outlier effects. Produces bounded aggregate reports with identifiers obscured and provides a structured analysis report template.
Delegate a bounded local task to Hermes Agent in a single run and receive its text result. The workflow accounts for automatic tool approval, isolates read-only work, and inspects file changes after authorized edits.
Carry out an engineering plan through stepwise code changes, dependency impact checks, tests, and focused commits. It also handles small, bounded tasks directly, checking the code relationship index before relying on its results.
Split a large goal into clearly bounded tasks that can run in parallel. Coordinate existing agent and worktree tools, then combine and verify the results. The skill starts only when explicitly requested.
Evaluate a Claude Managed Agent against a written rubric, a set of checkable criteria, and guide improvements within a fixed attempt limit. After a version passes, prepare separate evaluation cases to check performance beyond the examples used for revision.
Find repeated engineering tasks and turn them into agent workflows with clear checks, stopping rules, and approval boundaries. Compare published workflows, adapt suitable examples, or review existing ones for weak verification and uncontrolled repetition.
Inspect database connections and table structures configured in DBX, run read-only queries with row and time limits, and generate schema documentation or DBML, a text format for describing database structures.
Design loops that improve an agent’s own prompts, workflows, or execution code from failure records. Define bounded edits, preserve candidate histories, and accept changes through independent tests that check improvements and regressions.
Turn supplied text, files, or approved URLs into linked Obsidian notes with source records and evidence tracking. Review proposed changes before applying them, preserve original materials, and record contradictions or gaps in support.
Design and run bounded procedures in environments where current conditions are uncertain. The skill separates agent judgment from precise tool actions, verifies each effect, and records checkpoints so interrupted work can resume from observed evidence.
Design and implement a NestJS backend organized into business modules within one deployable application. The skill defines module boundaries, separates data ownership, builds layered code and event communication, and validates isolation through checks and tests.
Design a modular monolith, a single application with clear business boundaries. Plan module structure, external service integration, failure handling, and future separation, then produce an HTML architecture document with SVG diagrams.
Produce a token-bounded, citation-ready context slice from an existing Obsidian vault for a downstream agent or task. Use for "/wiki-context-pack", "use my vault as context", "context slice for X", "pack the wiki for my agent", or "bounded context for Y".
The English summary is being prepared. Showing the original description.
Execute one bounded CCB work item and report evidence without changing workflow authority.
The English summary is being prepared. Showing the original description.