Analyze competitor repositories with evidence-based approach. Use when tracking competitors, creating competitor profiles, or generating competitive analysis.
Compile any supported file type. Detects format (.typ, .qmd, .py) and runs appropriate build command.
Deep interview a human and compile them into an installable AI agent plugin. Conducts comprehensive behavioral interviews, analyzes work artifacts via MCP tools, and generates a…
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when compiling lecture slides.
Create and compile beautiful Beamer presentations following the Rhetoric of Decks philosophy. Use when making slides, creating decks, or compiling .tex presentation files.
Archive current cycle artifacts and prepare for the next cycle. Updates CYCLES.md, moves artifacts to .design/archive/cycle-N/.
Use when asked to work on, implement, or complete a GitHub issue — before writing any code, checks issue state, existing PRs, git history, and codebase to determine what work…
\"Holistic completion workflow after a feature's tasks are marked COMPLETE: code review, feature verification, integration check, documentation drift audit/update, and context…
Use this skill when archiving a completed milestone, preparing for the next version, marking a milestone complete, shipping a version, or wrapping up milestone work.
Run full import compliance analysis — classify, duty, PGA, entry type, and declaration readiness in one shot using AskRosetta. Use for end-to-end import analysis.
Audit Android Jetpack Compose repositories for performance, state management, side effects, and composable API quality.
This skill should be used when capturing solved problems as categorized documentation with YAML frontmatter for fast lookup.
Compress images for web/SEO performance using cwebp. Use when optimizing images for faster page loads, reducing file sizes, or converting JPG/PNG to WebP format.
This skill should be used when the user asks to "compress this video", "reduce file size", "make this video smaller", "optimize for web", "shrink this video", "compress to under X…
Use when analyzing TPU pretraining compute efficiency from xplane.pb — produces source-line-aggregated HLO duration tables, layer-scoped breakdowns, non-compute…
Propiedad horizontal — revisa estatutos, actas de junta y derramas de comunidades de propietarios. Comprueba quórums (art. 17 LPH), impugnación de acuerdos (art.
Read project config from .agents.yml and .agents.local.yml with local overrides. Supports dot notation for nested fields. Invoke with args " ".
Claude plugins marketplace setup: .claude/settings.json, GitHub Actions, plugin pinning. Use when onboarding to claude-plugins, setting up claude.yml, pinning plugins, or…
Use this skill when configure kata workflow toggles and model profile. Triggers include "settings".
Analyse les conflits git et propose à l'utilisateur une résolution pas à pas avec validation de chaque étape.
Convert a markdown string/file to Confluence-compatible XHTML and publish it as a page to Confluence Cloud. Supports create, upsert, and update modes.
Concise communication mode. Short sentences, one thought per line, no filler. Keeps grammar and technical accuracy.
Run N blind agents on the same job in parallel, then merge findings into consensus/unique/conflicts. Agents report only — no edits for concurrent safety.
Управление consent в learning.tracking_consent — opt-in / opt-out / status / revoke. Обязательное условие для работы stage_evaluator worker (WP-253 Блок 2). GDPR-совместимо.
Enforce policies, guardrails, and permission boundaries; refuse unsafe actions and apply least privilege.
Open an interactive Claude Code expert consultation grounded in the current project. Use when the user has questions about Claude Code setup, CLAUDE.md, subagents, MCP, models, or…
Responde consultas rápidas de derecho laboral con referencia a artículos del ET y convenio colectivo
AUTO-TRIGGER: Apply this skill when the user is preparing to present findings, recommendations, or results to a consulting client.
Guide for using /compact (Claude Code built-in) with the pre-compact save pipeline. Shows what gets saved before compression and what gets reinjected after.
Reduce Claude AI token consumption by 5x-27x using prompt-native workflows and structural code manifests.
Credit Maximizer v8.4.0 — 5D router (model×effort×version×context×dispatch) + auto-dispatch to specialized agents/skills + cross-provider session bridge.
**WORKFLOW SKILL** — Structured context analysis before acting. USE FOR: questioning assumptions, mapping dependencies, identifying blind spots, validating scope of any task or…
Begin a work session on a Contextia task. Loads full context including project identity, relevant specs, norms, and previous session logs.
Alias for /gdd:resume — restore session context from the most recent checkpoint.
Retoma um batch SDD em andamento. Use quando houver delta operacional novo, mudanças humanas em sdd ou batches, ou quando for preciso continuar a mesma rodada sem reiniciar a…
Download CI Doctor artifacts from a completed prow job and set up a local workdir for continued analysis
Ragas 기반 품질·안전 평가를 매 배포 직후와 매 1시간 cron으로 실행하여 faithfulness, answer relevance, context precision, toxicity, PII leakage 지표를 측정한다.
Guía para las primeras contrataciones de una startup: tipos de contrato, convenio colectivo aplicable, coste real, alternativas (autónomos, becarios) y riesgos (falso autónomo).
Contrata (recruta) um novo agente especialista para compor o squad. Agentes de nível 5+ (Especialista) podem sugerir contratações.
Read-only nomination brief for a named GitHub contributor on . Aggregates GitHub activity across all contribution tracks plus maintainer-supplied off-GitHub signal, and…
Audit and improve project conventions files (AGENTS.md, CLAUDE.md, GEMINI.md). Scans for all conventions files, evaluates quality against a scoring rubric, outputs a quality…
Convert markdown paper (with LaTeX math, tables, figures) to publication-quality PDF via Mermaid + MathJax + Puppeteer pipeline.
This skill should be used when the user asks to "convert this video", "change format to mp4", "trim from X to Y", "cut the first X seconds", "speed up this video", "slow motion",…
Check for a published coordinator update and advise a preserve-by-default migration path — never a blind overwrite.
Review Copilot comments on a GitHub PR, validate each suggestion, apply valid fixes, commit, reply with commit links, and resolve threads.
Audit Core Web Vitals (LCP, INP, CLS) for a URL list or sitemap via PageSpeed Insights and CrUX — producing a per-URL scorecard, worst-offender summary, and root-cause remediation…
Deep Corefall BP-LEVEL closure review (BP0..BP12) with T-CAPTURE evidence, grading.json LLM-graded verdicts, Self-Play Validation Matrix, AI-Agent Self-Test Report, Universal…
Run the corpus benchmark — booster locally, optional Gemini/Sonnet/Opus baselines — and persist a verifiable measured-vs-claimed table
Apply a simple code transform via agent-booster's WASM engine — sub-millisecond, deterministic, $0 (no LLM call). Companion to cost-booster-route.
Route tasks through hooks_route, partition by Agent Booster availability, and report Tier 1 bypass utilization with $0 cost
Read accumulated cost-tracking spend + budget config, compute utilization, emit 50/75/90/100% alert ladder
Wrap getTokenOptimizer().getCompactContext() to retrieve compacted ReasoningBank context for cost-analysis queries; report bridge-reported tokensSaved
Estimate the cost of a task before starting it. Analyzes task complexity, predicts token usage, and compares cost across all Claude models.
Export cost-tracking telemetry in Prometheus textfile or webhook JSON formats — for external observability (Grafana, Datadog, custom dashboards)
AWS Pricing과 Cost Explorer를 MCP로 조회하여 agent별 비용 귀속을 집계하고 예산 alert을 발행하며, 사용 패턴이 정당하면 Opus → Sonnet → Haiku 모델 다운그레이드를 권고한다.
Per-session cost and token budget tracking for AI coding agents. Monitors cumulative spend, warns at thresholds, and enforces limits with three modes: reject (stop work), alert…
Advanced cost intelligence: efficiency scoring, waste detection, ROI metrics, model savings calculator, anomaly detection, and GitHub badge generation.
Map fixed vs variable costs by line, contribution-margin waterfall, and scale curve (how costs change at 2× / 5× / 10× volume).
Single-shot programmatic dump of all cost data — total spend, per-tier, top session, budget status, federation aggregate. JSON or markdown.
Explain how and when to use Chain of Verification (CoVe) in prompt design. Use when designing prompts that require factual accuracy, self checking, or reduction of hallucinations.