Inspect pod logs, analyze resource quotas, trace network policies, check deployment rollout status, run cluster health checks for Kubernetes. Use this skill when diagnosing Kubernetes cluster issues, debugging failing pods, investigating network connectivity problems, analyzing resource usage, troubleshooting deployments, performing cluster health checks.

Creates test stacks, analyzes CloudFormation events, compares actual vs documented update behavior, then confirms whether a resource property change triggers replacement rather than an in-place update. Use when: testing if a CFN property change causes resource replacement; investigating stack update behavior, "Update requires" documentation accuracy; validating whether a workaround (e.g. hash-based logical IDs) is actually necessary; questioning UpdateRequiresReplacement behavior for immutable properties; needing empirical evidence before an architectural decision involving CDK/CloudFormation stack updates.

Extract structured data from scientific literature PDFs using AI-powered OCR and LLM analysis. Supports enzyme kinetics, experimental results, and literature review templates. Use when researchers need to parse tables, charts, or text from paper PDFs into Markdown or CSV. Triggers: extract data from PDF, scientific data extraction, parse paper tables, enzyme kinetics extraction, batch PDF extraction, literature data, research data from paper, OCR scientific paper, convert PDF to structured data.

Search and analyze biomedical literature from PubMed using the free E-utilities API. Use when researching medical topics, discovering clinical papers, fetching article metadata by PMID, performing deep paper analysis, or downloading open-access PDFs from PubMed Central. Triggers: pubmed search, search biomedical literature, find medical papers, PMID lookup, pubmed metadata, clinical literature search, biomedical research, life sciences papers, PMC download, ncbi search.

Advanced TypeScript type-system mechanics — union and intersection types, conditional types with `infer`, mapped types, template literal types, generics and their constraints, index signatures, type assertions, and extracting types from other types (return types, array elements, promise results). Use when designing a complex generic, modeling a type that transforms based on another type, extracting a type from a function or structure with `infer`, or deciding between a type assertion and a real narrowing check.

Type-first TypeScript coding practices — designing types before implementation, making illegal states unrepresentable with discriminated unions, runtime validation with Zod at system boundaries, and module organization (single-function modules, barrel files, encapsulation). Use when starting a new feature by asking what the types should look like first, spotting an interface with too many optional fields that let impossible combinations compile, or deciding how to validate data coming from outside the type system (an API response, form input, environment variables).

Generate an original British surrealist comedy sketch, script, or comic bit in the Monty Python tradition, built on absurd literalism, escalating internally-consistent illogic, bureaucratic pedantry, semantic argument, deadpan seriousness amid impossible premises, sudden non sequiturs, abrupt anticlimactic endings. Use this when a user asks for a new sketch, script, dialogue bit, or scene built on a mundane premise pushed to logical extremes. Do NOT use this to reproduce, quote, paraphrase, reword any actual Monty Python sketch, character, catchphrase (e.g. Dead Parrot, Spanish Inquisition, Ministry of Silly Walks, Argument Clinic); this is a generative skill for fresh original material, not a lookup, quotation, transcription tool. Not for slapstick, observational stand-up, roast comedy, American-style sitcom writing, where the humour depends on delivery, timing, rather than an escalating internally-consistent premise.

Generate original cringe comedy and provocateur stand-up material in two modes — (1) character-based cringe scenes/sketches with an oblivious, self-important figure (boss, host, celebrity) surrounded by uncomfortable onlookers, mockumentary-style; (2) direct-address stand-up bits, monologues, roast lines that state a taboo truth bluntly, without hedging, then escalate. Trigger for requests for an original sketch, scene, monologue, roast bit, cringe scene, blunt stand-up line, built on oblivious self-delusion, awkward silence, escalating humiliation, mock self-congratulation, flippant treatment of solemn subjects. Do NOT use this skill for gentle observational humor, warm sitcom banter, wordplay/puns with no discomfort element, requests to reproduce/paraphrase a real comedian's actual routine, script, special — this skill generates new material; it does not mimic an existing performance.

Generate original British political satire sketches in the pompous-establishment two-hander tradition, a formal interview, briefing, consultation scene built on faux-serious rhetoric, class pretension, institutional hypocrisy, euphemism, slow-burn escalation, self-serving reasoning concealed beneath polished language. Use this skill for an original satirical sketch script, an interview-format dialogue exchange, a briefing-scene transcript, featuring a pompous official, minister, executive, regulator, spokesperson, peer, who sincerely believes their evasive reasoning is sound. Not intended for reproducing real sketches, quoting real public figures' actual recorded words, near-verbatim programme dialogue, slapstick, absurdist non-political comedy, or monologue writing without an interview/dialogue frame.

Review a connected Paperclip team's agents, tasks, blockers and pending approvals when the user asks for a team summary or what needs attention.

Review a connected Paperclip team's agents, tasks, blockers and pending approvals when the user asks for a team summary or what needs attention.

Review a connected Paperclip team's agents, tasks, blockers and pending approvals when the user asks for a team summary or what needs attention.

Use agentic-flow's ReasoningBank to learn from past work - search similar episodes before a task, record reward, success and critique after it, and read trends. Use when the user wants agents to remember what worked, or asks about ReasoningBank, pattern store/search, or self-learning.

Connect this coding agent to Deacon's MCP server, so it can read what the founder's visitors asked and reported, and help fix it. Use when asked to connect to Deacon.

Find, live-validate, map the blast radius of, and revoke leaked secrets with Kingfisher (MongoDB) — across a local repo, Git history, a GitHub/GitLab/Bitbucket org, S3/GCS, Docker images, Slack, Jira, Confluence, Teams, or Postman. Covers local CLI scanning, direct validate/revoke without a scan, baseline management (track only new secrets), kingfisher.yaml policy, CI diff-scan gates, and pre-commit/Husky hooks. Use when asked to "scan for secrets", "is this key still live", "what can this credential reach", "revoke this token", "did we leak a secret", or "block new secrets in CI". Pattern-only secret scan bundled with a CVE pass → /platform-skills:trivy. Secrets-context safety in workflow YAML → /platform-skills:zizmor. Storing/rotating secrets inside the cluster → /platform-skills:secrets.

Scaffold, lint, review, security-audit, test, and upgrade-verify Helm charts. Runs an interactive interview to build production-ready charts from scratch. Covers chart structure, values design, schema validation, kubeconform, helm diff, and multi-environment scaffolding. Use when asked to "create a helm chart", "lint my chart", "review my helm chart", "check helm security", "generate values schema", "run helm diff", or "add helm tests".

Scaffold, lint, review, security-audit, test, and upgrade-verify Helm charts. Runs an interactive interview to build production-ready charts from scratch. Covers chart structure, values design, schema validation, kubeconform, helm diff, and multi-environment scaffolding. Use when asked to "create a helm chart", "lint my chart", "review my helm chart", "check helm security", "generate values schema", "run helm diff", or "add helm tests".

Triage open herdr GitHub issues into a concise decision-first Markdown table. Use when the user says "triage", asks to triage open issues, asks which issues need attention, or wants issue priority/recommendation lights for herdr.

Generate 4-6 complete candidate design systems for a web project, let the user pick one visually in the browser, and freeze the winner into a Google-spec design.md at the project root. Use ONLY when the user explicitly invokes /design-md or explicitly asks to run the design-system picker. If a conversation merely suggests it would help, suggest it — never start it unasked (it launches a server, opens a browser, and writes many files).

Extract text from images using pytesseract OCR. Handles PNG, JPG, JPEG, GIF, BMP, TIFF formats. Use when processing image files that may contain text, diagrams with labels, screenshots, or scanned documents. Returns extracted text content. Routed from file-identifier.