CorvinOS

In the author's own words, from each skill's SKILL.md.

• forge

  Forge schema-bound, sandboxed tools at runtime. Paired with the cowork `forge` persona for chat-driven use in the voice-skill bridge. Use when you would otherwise write the same Bash snippet ≥3× with different parameters, when you need precise numerical results over a dataset, or when the user wants reproducible/deterministic output written to a file.

  corvin_operator/forge/SKILL.md on GitHub (opens in a new tab)

• academic-paper-generation

  No description in the SKILL.md.

  corvin_operator/skills/academic-paper-generation/SKILL.md on GitHub (opens in a new tab)

• paper-generator-orchestrator

  No description in the SKILL.md.

  corvin_operator/skills/paper-generator-orchestrator/SKILL.md on GitHub (opens in a new tab)

• os.delegation_router

  Route tasks to native OS, ACS, or TDE

  core/skills/bundled/os_delegation_router_v1.0/SKILL.md on GitHub (opens in a new tab)

• quality-layer-control

  Toggle quality disciplines (ADR Gate, docs-as-definition-of-done, etc.) on or off globally

  corvin_operator/bundle/skills/quality-layer-control/SKILL.md on GitHub (opens in a new tab)

• cowork

  Multi-persona layer for Claude Code. Per chat (or per CLI call) a different agent role: coder (default), browser, inbox, research, ... Each persona has its own tools, MCP servers, system prompt and workspace. Optional, on top of voice or standalone. Trigger when the user mentions cowork, persona, agent role, multi-agent, bind chat, /cowork-*.

  corvin_operator/cowork/skills/cowork/SKILL.md on GitHub (opens in a new tab)

• voice

  Voice mode for Claude Code — automatically reads assistant replies aloud via TTS, with German/English auto-detection and optional summarization for long responses. Trigger when the user mentions voice, vorlesen, sprachausgabe, TTS, "speak", "say it out loud", or asks about /voice-* commands.

  corvin_operator/voice/skills/voice/SKILL.md on GitHub (opens in a new tab)

• adr_gate

  ADR Gate — evaluates after non-trivial tasks whether an ADR is warranted; writes to Corvin-ADR repo when yes, names the skip reason when no, requires three-level analysis (conceptual/structural/implementation), emits ADR-0264 decision-graph frontmatter (depends_on/related/paths/docs — the three-layer Code/Docs/ADR graph) so scripts/adr_graph.py can traverse it, and generates E2E tests for every n…

  corvin_operator/bundle/skills/ldd/adr_gate/SKILL.md on GitHub (opens in a new tab)

• concept_gate

  Concept Gate — evaluates after non-trivial tasks whether a reusable WORKING METHOD (not a decision, not a bug fix) is worth archiving; writes to Corvin-ADR/concepts/ when yes (or amends an existing entry), names the skip reason when no, requires evidence citations (real commits/tasks), and mints a bootstrap-graded companion SkillForge learned-experience skill so durable methods are auto-injected…

  corvin_operator/bundle/skills/ldd/concept_gate/SKILL.md on GitHub (opens in a new tab)

• dialectical-reasoning

  Use when making any non-trivial recommendation, analysis, plan, design decision, code-review note, or architectural trade-off — before presenting to the user or acting. Forces a thesis / antithesis / synthesis pass so first-pass conclusions cannot ship without surviving their strongest counter-case.

  corvin_operator/bundle/skills/ldd/dialectical-reasoning/SKILL.md on GitHub (opens in a new tab)

• docs-as-definition-of-done

  Use when finishing any code change that modifies behavior, public API, CLI flags, config shape, defaults, error messages, or anything a reader-of-the-docs would model — before committing, pushing, or declaring "done." Forbids deferring doc updates to a follow-up commit, ticket, or "cleanup later."

  corvin_operator/bundle/skills/ldd/docs-as-definition-of-done/SKILL.md on GitHub (opens in a new tab)

• drift-detection

  Use periodically (weekly, at release candidates, before major version bumps) to scan a codebase for cumulative drift that no per-commit gate catches. Complements docs-as-definition-of-done, which prevents drift from being introduced per commit; this skill surfaces drift that already happened despite per-commit gates.

  corvin_operator/bundle/skills/ldd/drift-detection/SKILL.md on GitHub (opens in a new tab)

• e2e-driven-iteration

  Use at the start of every inner-loop iteration where the goal is to fix a bug / close a failing test / reach a green E2E. Forbids editing code without first running the E2E to capture a fresh loss signal, and forbids declaring "done" without the E2E passing. Makes the cycle "E2E → loss → 5-why-by-layer → fix → E2E" the only admissible rhythm.

  corvin_operator/bundle/skills/ldd/e2e-driven-iteration/SKILL.md on GitHub (opens in a new tab)

• e2e-wiring-proof

  Use immediately before declaring "done" on any code generation that adds a new entry point — function, endpoint, route, CLI command, UI component, plugin, hook, or bridge handler. Forbids closing the task without (1) proving the new code is reachable from a real trigger, outside test files, and (2) a generated or extended E2E test that exercises it through that real entry point, executed with cap…

  corvin_operator/bundle/skills/ldd/e2e-wiring-proof/SKILL.md on GitHub (opens in a new tab)

• iterative-refinement

  Use when a deliverable (document, diff, design, report, code module) is complete but "good enough, not great" and you want to improve it with a targeted re-iteration instead of starting over. Forbids re-running the task from scratch when refinement is more efficient. Operates on the y-axis (output) not the θ-axis (code or method).

  corvin_operator/bundle/skills/ldd/iterative-refinement/SKILL.md on GitHub (opens in a new tab)

• loop-driven-engineering

  Use at the start of any non-trivial engineering task (feature, bugfix touching more than one file, refactor with observable behavior change, incident response). Orchestrates the three LDD loops — inner (code), refinement (deliverable), outer (method) — with hard iteration budgets, dispatches the specialist skills at the right moments, and forbids declaring "done" without a synced doc-level mental…

  corvin_operator/bundle/skills/ldd/loop-driven-engineering/SKILL.md on GitHub (opens in a new tab)

• loss-backprop-lens

  Use when deciding whether to edit code at all, how large the edit should be, or whether a "working" fix actually generalizes. Applies when iterating on a failing test/run, chasing a flake, committing a sequence of small patches, or tempted to ship on one data point. Frames code changes as gradient steps and forbids overfitting to a single sample or a single test.

  corvin_operator/bundle/skills/ldd/loss-backprop-lens/SKILL.md on GitHub (opens in a new tab)

• method-evolution

  Use when the same rubric violation, the same kind of symptom-patch, or the same escalation happens across 3+ distinct tasks — meaning the problem is in the method (skill, prompt, rubric), not in the tasks. Forces a disciplined outer-loop step: name the pattern, propose a skill/rubric change, measure Δloss before and after, roll back on regression.

  corvin_operator/bundle/skills/ldd/method-evolution/SKILL.md on GitHub (opens in a new tab)

• reproducibility-first

  Use when you have observed a failing test, a flaky run, a surprising log line, or any single-sample signal you are about to treat as a gradient. Forbids code edits based on one observation unless the log itself is unambiguous signal. Applies before invoking root-cause-by-layer or proposing any fix.

  corvin_operator/bundle/skills/ldd/reproducibility-first/SKILL.md on GitHub (opens in a new tab)

• root-cause-by-layer

  Use when encountering a bug, failing test, or unexpected behavior — especially under time pressure where try/except, retry loops, xfail, type-tolerance shims, "I'll clean up later," or compat-for-both-shapes feel like the fastest path. Forbids symptom patches until structural and conceptual origins are named.

  corvin_operator/bundle/skills/ldd/root-cause-by-layer/SKILL.md on GitHub (opens in a new tab)

• using-ldd

  Use at the start of any conversation, and whenever the user mentions LDD, loss-driven development, loss, gradient, SGD on code, drift, refinement loop, outer loop, inner loop, method evolution, or says "LDD:" / "apply LDD". Establishes how to dispatch the ten LDD skills and when each fires. Must be the first skill considered in any coding task where LDD is available.

  corvin_operator/bundle/skills/ldd/using-ldd/SKILL.md on GitHub (opens in a new tab)

• market_analyst

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/dag_complex/src/skills/market_analyst/SKILL.md on GitHub (opens in a new tab)

• news_analyst

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/dag_simple/src/skills/news_analyst/SKILL.md on GitHub (opens in a new tab)

• code_reviewer

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/delegation/src/skills/code_reviewer/SKILL.md on GitHub (opens in a new tab)

• data_analysis

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/full_pipeline/src/skills/data_analysis/SKILL.md on GitHub (opens in a new tab)

• quality_assessment

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/full_pipeline/src/skills/quality_assessment/SKILL.md on GitHub (opens in a new tab)

• report_writing

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/full_pipeline/src/skills/report_writing/SKILL.md on GitHub (opens in a new tab)

• quant_trading

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/mixed/src/skills/quant_trading/SKILL.md on GitHub (opens in a new tab)

• risk_management

  No description in the SKILL.md.

  core/awpkg/tests/fixtures/mixed/src/skills/risk_management/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• rufloby ruvnet 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems.… 79.3k stars · 30 skills
• claude-code-tipsby ykdojo 45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running it… 10.3k stars · 9 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 107k stars · 30 skills
• OpenMontageby calesthio World's first open-source, agentic video production system. 12 production pipelines, 100+ tools, 700+ agent skill and production-knowledge… 71.9k stars · 30 skills
• claude-code-best-practiceby shanraisshan from vibe coding to agentic engineering - practice makes claude perfect 68.1k stars · 9 skills
• agentsby wshobson Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi 41.7k stars · 30 skills