tekhne

Generates, validates, and optimizes Fluent Bit configurations for production use. Use when creating new Fluent Bit configs, implementing log collection pipelines (INPUT, FILTER, OUTPUT sections), configuring Kubernetes log collection with metadata enrichment, forwarding logs to destinations (Elasticsearch, Loki, S3, Kafka, CloudWatch, OpenTelemetry), building multi-line log parsing, or converting existing logging configurations to Fluent Bit.

Validates syntax, checks pipeline tag connections, detects security misconfigurations, audits best practices, and performs dry-run testing for Fluent Bit configurations. Use this skill when working with Fluent Bit config files, validating syntax, checking for best practices, identifying security issues, performing dry-run testing, or troubleshooting configuration-related errors.

Read-only status check across the follow-up backlog: lists every ACTIVE follow-up entry, assesses whether it's still genuinely open, and recommends the single best next item to work on -- pulling in open RISK_REGISTER and TECH_DEBT rows and the value-rubric's ranked PLAN/FINDING/KNOWN_ISSUE candidates when the follow-up list itself is empty, since that's where promoted follow-up work actually ends up living. Triggers: '/follow-up', 'check follow-ups', 'what's open', 'what should I work on next', 'follow-up status check', 'next best item', 'what's still open'. Does NOT promote, close, or otherwise edit anything -- it reports and recommends, then applies follow-up-triage's own flow directly or hands off to the risk-register / tech-debt / plan-create skills for the actual write.

Master higher-order functions, map/filter/reduce patterns for expressive data transformations

Apply immutability principles across languages for safer, more predictable code

Write pure functions and avoid side effects for predictable, testable code

Sense-making before action. Classify problem using Cynefin triangulation (3 tests + decomposition) to route to the right skill chain. Use when: frame, what approach, how should I start, which skill, where to begin, unsure what to do. NOT for known tasks — just do them.

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.

Generates production-ready GitHub Actions workflows, custom actions, and CI/CD configurations following security and performance standards. Creates CI/CD pipelines, test workflows, deployment configurations, matrix builds, caching strategies, composite actions, Docker actions, JavaScript actions, and reusable workflows. Use when creating or scaffolding GHA resources, writing .github/workflows YAML files, setting up build automation, implementing deployment pipelines, adding security scanning, or building reusable actions — including triggers like 'create a workflow', 'build a pipeline', 'add CI', 'set up GHA', or 'generate a YAML workflow'.

Comprehensive toolkit for validating, linting, and testing GitHub Actions workflow files, custom local actions, and public actions. Use this skill when working with GitHub Actions YAML files (.github/workflows/*.yml), validating workflow syntax, testing workflow execution with act, or debugging workflow issues.

Query and display available GitHub Copilot AI models with their capabilities, context limits, and features. Use when: "what models are available", "show copilot models", "list github models", "check model capabilities", "switch models". Examples: - user: "What models can I use with GitHub Copilot?" → fetch and display available models - user: "Show me models with vision support" → filter models by capability - user: "Which model has the largest context window?" → compare model specifications - user: "List all GPT-5 models" → filter by model family

Fetches and analyzes GitLab merge request (MR) comments, metadata, and review feedback using authenticated API calls. Capabilities include fetching comment threads, retrieving reviewer feedback, filtering unresolved discussions, and generating MR activity reports. Use when the user asks about GitLab MR comments, code review discussions, review feedback, approval status, troubleshooting review delays, or needs to fetch merge request metadata via the GitLab API.

Creates .gitlab-ci.yml files, configures pipeline stages, defines CI jobs and runners, sets up deployment workflows, and generates reusable GitLab CI/CD templates following current best practices and security standards. Use when users ask to create or build a GitLab CI/CD pipeline, CI config, build pipeline, deploy pipeline, GitLab YAML, CI jobs, or any .gitlab-ci.yml configuration from scratch or for a new project.

Validates .gitlab-ci.yml syntax, detects security misconfigurations in job definitions, checks for deprecated keywords, ensures proper stage ordering, and audits pipeline configurations for best practices. Use when working with .gitlab-ci.yml files, validating GitLab CI/CD pipeline syntax, debugging configuration errors, checking for hardcoded secrets or credentials in pipeline jobs, optimizing pipeline performance with DAG or cache, or performing security audits on GitLab CI/CD configurations.

Record a session goal as a dated file with items plus evidence, keep its status current, then answer "what's left" in under 100 words: achieved, parked, still open. Use when the user states a session goal, asks what's left, what's outstanding, what's still open, whether the goal is met, are we done, where the session got to. Also use to park an item, to promote an overgrown goal into a plan, to close a goal out.

Search Google Scholar for academic papers and author profiles. Use when discovering papers to triage — by keyword, author, or year range. Returns titles, authors, abstracts, and links. Triggers: search papers, find papers, google scholar, search scholar, find author, author profile, literature search, paper discovery, search academic literature.

Conduct a structured, one-question-at-a-time interview to explore a specific topic or decision — each question offers 3-4 concrete, mutually exclusive options plus a free-text path, and later questions adapt to prior answers rather than following a fixed script. Ends with a recap the user confirms before finalizing, and only then produces a synthesized answer or (when the interview clearly feeds downstream work) a written brief. NOT for open-ended ambiguity-surfacing (use socratic-method) or single-fact lookups.

Write a session handover document in .context/handovers/ so another agent or session can resume the work without re-deriving context. Use when a session is ending (or pausing) with work still in progress, when the user asks to 'write a handover', 'document what's outstanding for the next session', 'hand this off', or 'summarise where we got to', or when a long-running task is about to be interrupted (context limit, user stepping away, switching worktrees). Covers the frontmatter contract, required sections (Session Summary, Completed, Outstanding, Current State, Next Steps, References), the JSON Schema and shell validator that check a handover's shape, and how a follow-up session should pick one up and close it out.

Comprehensive toolkit for generating best practice Helm charts and resources following current standards and conventions. Use this skill when creating new Helm charts, implementing Helm templates, scaffolding Chart.yaml and values.yaml, defining deployment templates, service definitions, ingress configurations, .tpl helpers, or building Helm projects from scratch. Trigger phrases include "create", "generate", "build", "scaffold" alongside terms like "kubernetes helm", "k8s charts", "helm package", "chart dependencies", "values.yaml", or "helm install".

Comprehensive toolkit for validating, linting, testing, and analyzing Helm charts and their rendered Kubernetes resources. Use this skill when working with Helm charts, validating templates, debugging chart issues, working with Custom Resource Definitions (CRDs) that require documentation lookup, or checking Helm best practices.