Destynova2
UserProduction-ready Claude Code skills — audit code quality, forge design docs, generate documentation, automate infrastructure. CLI = Command Line Interface + Clement Liard Initials.
Categories
Indexed Skills (28)
cli-audit-code
Audit code quality with weighted scoring across 12 dimensions (naming, complexity, module design, DRY, errors, security, tests, architecture). Detects named anti-patterns (Fowler/Mantyla taxonomy). Use when reviewing code quality, auditing clean code compliance, checking for code smells, or saying 'audit code', 'code quality', 'code review', 'tech debt'. Invoke with an optional file or directory path.
cli-audit-doc
Audit documentation quality with weighted scoring across 12 dimensions (Diataxis coverage, completeness, freshness, readability, examples, accessibility, CI testing). Detects doc anti-patterns (Wall of Text, The Lie, Jargon Soup). Use when reviewing doc quality, auditing documentation, checking for stale docs, or saying 'audit docs', 'doc quality', 'documentation review'. Invoke with an optional file or directory path.
cli-audit-drift
Detect silent semantic drift between intended behavior (CONTRACTS.md) and actual implementation. Scans code against functional contracts, invariants, and known drift history to catch behavioral changes that compile and run but violate the original intention. Use when reviewing code changes, before commits, auditing behavioral conformity, or saying 'check drift', 'contract check', 'intention vs implementation', 'semantic drift', 'is this still correct', 'does this match the spec', 'behavioral regression', 'silent bug', 'autophagy scan'. Also triggers on 'CONTRACTS.md', 'invariant check', 'intention audit', 'contract violation'.
cli-audit-shell
Audit shell scripts against Google Shell Style Guide + ops best practices. Scores 12 dimensions: strict mode coherence, error surfaces, logging, stderr hygiene, variable discipline, quoting, control flow, naming, CLI ergonomics, idempotency, namespace, and security. Goes beyond shellcheck — detects semantic anti-patterns invisible to linters (dead fallbacks under set -e, custom loggers vs logger(1), redundant package checks, env var injection in heredocs, missing getopts). Use when reviewing shell scripts, auditing bash code, checking deployment scripts, or saying 'audit shell', 'bash review', 'script quality', 'shell style', 'shellcheck not enough', 'review my script'. Also triggers on 'set -euo pipefail', 'getopts', 'shell injection', 'logger', 'bash best practices', 'google shell style'.
cli-audit-sync
Verify documentation-code coherence: detect stale references, broken links, terminology drift, outdated diagrams, and non-working examples. Use when the user wants to check if docs match reality, detect doc drift, verify README accuracy, find stale documentation, or says 'is my doc up to date', 'check coherence', 'sync docs', 'doc drift', 'stale docs', 'verify documentation'. Also triggers on 'broken links', 'outdated references', 'docs match code'.
cli-audit-tangle
Detect spaghetti code and dependency cycles using graph theory, spectral analysis, and biomimetic patterns. Finds god functions, circular dependencies, dead code, suboptimal module boundaries, CI/CD pipeline deadlocks, and inefficient call patterns. Uses call graph topology (not just line-level metrics) to identify structural problems invisible to linters. Provides concrete fix patterns per domain. Use when the user says 'spaghetti', 'tangle', 'untangle', 'god function', 'god object', 'circular dependency', 'cycle detection', 'call graph', 'module coupling', 'dead code', 'code topology', 'complexity analysis', 'who calls who', 'démêler', 'couplage', 'dépendances circulaires', 'fonction dieu', 'code mort', 'import cycle', 'ImportError', 'pipeline deadlock', 'CI stuck', 'needs deadlock', 'everything depends on everything'. Also triggers on 'refactor structure', 'split module', 'too coupled', 'architecture debt', 'dependency diagnostic', 'workflow cycle'.
cli-audit-test
Audit test plan quality and maturity. Scores coverage, techniques, pyramid balance, negative testing, NFR, automation, CI integration. Use when reviewing a test plan, test strategy, test suite structure, or saying 'audit tests', 'test quality', 'test plan review', 'test maturity', 'are my tests good enough', 'test scoring', 'test pyramid'. Also triggers on 'test coverage', 'test gaps', 'missing tests'.
cli-audit-wizard
Audit configuration wizard UX and lifecycle quality (setup, doctor, edit, migrate). Scores the 4 Laws (ask once, defaults, recap, config-as-code), credential discovery, multi-surface consistency (CLI/MCP/web), and scriptability. Detects wizard anti-patterns. Use on 'wizard', 'setup flow', 'config UX', 'init command', 'doctor mode', 'wizard audit', 'onboarding UX', 'first-run experience', 'config lifecycle', 'wizard broken', 'interactive setup', 'MCP config', 'config reload'.
cli-cycle
Continuous improvement cycle — orchestrates all cli-* skills on the current project, synthesizes results, and proposes prioritized improvements. Use when the user wants a full project review, a health check, a weekly cycle, or says 'audit everything', 'review the project', 'health check', 'what should I improve', 'run all audits', 'cycle', 'improvement cycle'. Designed for recurring use with '/loop 7d /cli-cycle'.
cli-forge-arch
Router for architecture design. Detects whether the user needs an HLD or LLD and delegates to the appropriate skill. Use when the user says 'design doc', 'architecture', or is ambiguous about HLD vs LLD. For explicit HLD requests, use cli-forge-hld directly. For explicit LLD requests, use cli-forge-lld directly.
cli-forge-chef
Generate a multi-agent orchestrator for any project using the Brigade de Cuisine pattern: Chef (plans, decides), Sous-Chef (validates, merges), Commis (execute). Clients order via a Menu (PERT), the kitchen delivers Plats (merged features). Creates tmuxinator config, prompts, shared-state memory, quality gates, and permissions. Uses Claude Code Agent Teams (TeamCreate + SendMessage) with visible tmux panes. Use when the user wants to parallelize work across multiple Claude Code agents, orchestrate a multi-agent sprint, or says 'boss', 'multi-agent', 'orchestrate', 'parallelize agents', 'team of claudes', 'sprint multi-agent', 'brigade', 'chef'. Also triggers on 'swarm', 'agent team', 'parallel workers', 'PERT multi-agent'.
cli-forge-demo
Generate a reproducible live-demo kit for any project: a staged demo script (DEMO.md), deterministic seed and idempotent reset wired into the project's own task runner (make / just / task / npm / ansible / flux / chainsaw — never an imposed .sh), a pre-flight checklist, and a backup recording. Picks the best delivery support for the project (live, terminal GIF via VHS, asciinema cast/SVG, subtitled video, or a self-guided 'next-next' interactive walkthrough) and lets you force one. Tunes dramaturgy to the audience: technique, fonctionnel, commercial, or pédagogique. Use when the user says 'demo', 'démo', 'live demo', 'demo script', 'demo gif', 'record a demo', 'show this off', 'walkthrough', 'interactive tutorial', 'present OpenBao', 'sprint review demo', 'sales demo', 'pitch demo', 'reproducible demo', 'reset demo data', 'seed demo', 'demo magic', 'asciinema', 'vhs tape', 'demo that does not break'. Do NOT use for slide decks (use cli-forge-prez) or for a README (use cli-forge-readme).
cli-forge-doc
Generate and audit comprehensive project documentation from a Git repository. Produces standard documentation (CONTRIBUTING.md, architecture, troubleshooting) in Diataxis structure with zero AI markers by default. Use this skill whenever someone asks to document a project, generate docs, create a README, write API docs, or improve existing documentation. Also trigger when someone mentions "doc", "documentation", "readme", "explain this codebase", "onboard developers", or "make this project understandable".
cli-forge-github
Audit and fix GitHub repository health: rulesets vs CI alignment, branch hygiene, PR lifecycle, release automation flow, permission issues, and transient CI failures. Detects misconfigurations that cause PRs to hang, CI to fail silently, branches to accumulate, and releases to stall. Use when the user says 'PR stuck', 'CI pending forever', 'branch cleanup', 'ruleset', 'release blocked', 'merge conflicts on sync-main', 'stale PRs', 'orphan branches', 'GitHub health', 'repo hygiene', 'required checks', 'path pruning', 'release-plz stuck', 'auto-merge not working', 'workflow scope', 'token permission'. Also triggers on 'gh api', 'rulesets', 'branch protection', 'status checks'.
cli-forge-hld
Generate a High-Level Design (HLD) document for a software system. Use when the user mentions 'HLD', 'system design', 'architecture document', 'design doc', 'ADR', 'C4 diagram', 'back-of-envelope', 'capacity planning', 'ATAM', 'arc42', 'design proposal', 'Gate review', or says 'design X', 'architect Y'. Produces C4 L1-L2 diagrams, capacity estimations, ADRs, tradeoff analysis, and deployment architecture. Do NOT use for low-level/detailed design (class diagrams, DB schemas, API specs) — use cli-forge-lld instead.
cli-forge-infra
Ops integration assistant — reads service docs, finds the simplest config path (CLI/Helm/Operator/Terraform), builds dependency trees, proposes upgrade paths, and tracks decisions in ADRs. Use when debugging infra, integrating services, bootstrapping platforms, upgrading versions, simplifying config, or reviewing infrastructure code. Triggers on ops tool names (OpenBao, Vault, Consul, Traefik, Gitea, ArgoCD, Prometheus, Grafana, cert-manager, Istio, Linkerd, Terraform, OpenTofu, Podman, Docker, K8s, etc.) or keywords like "bootstrap", "integrate", "simplify config", "upgrade infra", "ops stack", "service mesh", "dependency tree".
cli-forge-lld
Generate a Low-Level Design (LLD) document for a software component or service. Use when the user mentions 'LLD', 'low-level design', 'detailed design', 'class diagram', 'sequence diagram', 'API spec', 'database schema', 'component design', 'module design', 'STRIDE', 'threat model', or asks for detailed technical design of a specific service/component. Produces C4 L3-L4 diagrams, class/sequence/state diagrams, API contracts, DB schemas, error handling, and testability design. Do NOT use for system-level architecture — use cli-forge-hld instead.
cli-forge-oci-rootless
Agentic migration architect for transforming Ansible, bare-metal, VM, shell-scripted, or systemd-root deployed middleware into an operable OCI rootless product using any OCI-compliant runtime (Podman, Docker rootless, nerdctl, or equivalent), systemd --user, declarative units (Quadlet, compose), explicit host bootstrap, a single operator CLI, executable gates, monitoring, and proven recovery. Uses a stratigraphic/metallurgical reasoning model: extract the bedrock contract, separate ore from gangue, map fault lines, forge target alloys, stress-test fracture surfaces, and remediate legacy tailings.
cli-forge-perf
Catalogue + méthode pour optimiser la performance de n'importe quoi : code, requêtes, algorithmes, pages web, systèmes. Couvre complexité algorithmique, structures de données, requêtes DB (index, N+1), cache et RAM-vs-disque, astuces math/physique (distance² vs sqrt, éviter cos/sin, SIMD), async/concurrence, frontend/web (Lighthouse), bas niveau et hardware. Utilise ce skill DÈS QUE l'utilisateur veut accélérer quelque chose, réduire latence ou mémoire, "rendre plus rapide", "ça rame", "ça consomme trop", optimiser une boucle/requête/page — même sans dire "performance". Couvre aussi comment mesurer et benchmarker rigoureusement (harnais A/B, distribution vs moyenne, pièges de mesure), générer des idées hors catalogue et expérimenter : déclenche pour "benchmark ça", "ce gain est-il réel ?", "pourquoi X est plus lent que Y", "perf budget", "p95/p99", "hot path", "profiling", "flamegraph".
cli-forge-pipeline
Expert CI/CD pipeline optimizer using biomimetic patterns from nature: leafcutter ants (task partitioning), slime mold (adaptive path optimization), army ants (self-organizing parallelism), honeybees (dynamic resource allocation), and mycelium (fault-tolerant routing). Works with any CI system — examples cover both GitLab CI and GitHub Actions. Use this skill whenever the user asks to optimize, design, review, speed up, parallelize, or fix a CI/CD pipeline. Also triggers on: "slow pipeline", "flaky tests", "runners", "artifacts", "CI cache", "parallel build", "GitLab CI", "GitHub Actions", "pipeline design", "reduce build time", DAG pipelines, job dependencies, or any request mixing infrastructure + automation + deployment. Use it even when the user just pastes a YAML pipeline without asking explicitly.
cli-forge-prez
Generate technical presentation decks in Marp Markdown from code, architecture, or documentation. Produces speaker-ready slides with notes, dark theme, and CI templates for PDF/HTML export. Use when the user mentions 'prez', 'presentation', 'slides', 'deck', 'talk', 'lightning talk', 'pitch', 'conference talk', 'demo day', 'speaker notes', 'technical presentation', 'Marp', 'slide deck', or wants to present a project, architecture, or design to an audience. Also triggers on 'keynote', 'meetup talk', 'sprint review prez', 'make slides', 'present this'.
cli-forge-readme
Use this skill whenever the user wants to create, improve, audit, or rewrite a README.md file for any project. Triggers include: 'readme', 'README', 'documentation for my project', 'write a readme', 'improve my readme', 'project landing page', or any request to document a codebase, library, CLI tool, infrastructure project, or research repo. Also triggers when the user asks to 'make my project more accessible', 'add a getting started guide', or wants badges, installation instructions, or contributing guidelines. Use this skill even when the user just says 'document this' or 'make this repo presentable'. Do NOT use for API reference docs generation, full documentation sites (mdbook, docusaurus), or man pages.
cli-forge-resilience
Generate a production-parity resilience blueprint: test battery, troubleshooting runbook, failure-injection plan, and incident blackbox templates. Uses biological and physical reasoning — genome/contracts, membranes/boundary conditions, homeostasis/health checks, immune system/negative tests, stress-strain/failure budgets, phase transitions/resource cliffs, hysteresis/reruns, and memory cells/post-incident capitalisation. Use whenever the user asks to prevent prod bugs, make dev/staging closer to prod, design pre-prod checks, write a runbook, create a smoke test ladder, harden deployments, or turn incidents into durable anti-regressions.
cli-forge-schema
Use this skill to generate, convert, or refine diagrams and visual representations in GitHub-compatible Mermaid. Triggers include: 'diagram', 'schema', 'flowchart', 'sequence diagram', 'architecture diagram', 'ER diagram', 'state machine', 'gantt', 'mindmap', 'timeline', 'mermaid', 'visualize', 'draw', 'convert table to diagram', 'kanban', 'PERT', 'roadmap', 'changelog', 'sankey', 'quadrant', 'git graph', or any request to create, fix, or improve a visual representation of data, processes, or architecture. Also triggers when the user pastes broken Mermaid, asks to simplify a complex diagram, wants to convert markdown tables/bullet lists/SQL schemas/JSON structures/API lists/RACI matrices into visual formats, or says 'make this visual'. Do NOT use for actual image generation (PNG, SVG rendering) — output is always Mermaid markdown.
cli-forge-tree
Use this skill whenever the user wants to visualize, generate, audit, or scaffold a project directory structure. Triggers include: 'project structure', 'folder structure', 'directory layout', 'tree', 'arborescence', 'scaffold', 'init project', 'organize my files', 'naming conventions', or any request to understand or create how files and folders should be organized in a codebase. Also triggers when someone says 'create a new project', 'bootstrap', 'init', or asks 'where should I put this file'. Use for any language or framework. Do NOT use for file system operations unrelated to project organization (like disk cleanup or backup scripts).
cli-git-conventional
Enforce Conventional Commits v1.0.0, SemVer 2.0.0, branch naming, and human ghostwriter style on all git/jj operations. Zero AI markers. Use on 'commit', 'branch', 'tag', 'release', 'changelog', 'semver', 'bump version', 'next version', 'CHANGELOG.md'. Also trigger proactively when the user shares code changes without mentioning commit.
cli-watermark
Steganographic code watermarking for IP defense. Generates multi-layered fingerprints that survive AI rewrites, language changes, renaming, and clean-code passes. Produces timestamped cryptographic commitments for legal proof of authorship. Use when the user wants to watermark a codebase, protect IP, prove code ownership, detect code copying, add steganographic markers, generate proof-of-authorship, or says 'watermark', 'fingerprint', 'steganography', 'IP protection', 'code ownership proof', 'anti-copy', 'prove authorship', 'detect copy', 'canary'. Also triggers on 'paper town', 'CFG watermark', 'code provenance'.
cli-forge-quorum
Generate a Byzantine-fault-tolerant multi-agent orchestration using the REC-Quorum pattern (Reflect/Execute/Control with adaptive quorums, tickets pré-signés, leaderless execute, view-change timeouts). Use when a brigade-style orchestrator has stalled on a single-leader bottleneck, when deterministic decision quality is required (SLA/compliance/incident-response), when the team has > 5 agents with parallelism, or when operators mention 'BFT agents', 'REC-Quorum', 'deterministic consensus', 'threshold signatures', 'quorum adaptatif', 'view-change', 'leaderless execute', 'Byzantine orchestration'. Upgrade path from cli-forge-chef when Brigade stalls or requires formal audit trail.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.