Claude Skills by OneDro1d

Persistent, per-objective working memory for coding agents — one standalone git "notepad" repo per objective that survives context compaction, spans multiple code repos from a single session, keeps an append-only journal, and mirrors into an episodic memory index. Ships as a Claude Code plugin (hooks + skills + notepad template + a memory adapter). Evolves and supersedes handoff-auto. Use when setting up objective-scoped agent memory, running several long-lived concurrent agent sessions, surv...

Publish a deliberate, structured Handoff document for the current objective into the active notepad and force a git push so it syncs across machines. Use when wrapping a session, handing to a teammate or fresh agent, hitting a milestone, or asked to "create a handoff", "write a handoff", "checkpoint for next session", "hand this off". Writes to <notepad>/handoffs/<date>-<topic>.md (NOT a temp dir), redacts secrets, references artifacts by path/URL, suggests next skills. In agent-notepad this ...

Create or refresh an agent-notepad — a per-objective working-memory git repo (one notepad per objective, grouped by name prefix) that survives context compaction and drives several code repos from one session. Runs a short interview (objective, code-repo paths, done-criteria), optionally `gh repo create`s the notepad under the prefix→org map (consent required), writes SCOPE.md + repos.manifest.json, validates each code repo, offers per-repo df-context-store bootstrap (consent), warm-starts NO...

Archive a completed or abandoned agent-notepad while keeping its journal history intact. Marks the notepad retired (SCOPE.md status + a final journal milestone), stops it from auto-loading and syncing on future sessions, and preserves the append-only sessions/ history and handoffs for later recall — it never deletes the journal, the memory index entries, or the remote. Reversible: a later scope-init re-activates it. Use when an objective is done, a scope is being wound down, or a notepad shou...

Review architectural changes for coupling, blast radius, and long-term impact. Use when evaluating system design changes, cross-service dependencies, API changes, or infrastructure modifications. Triggers on "architecture review", "impact analysis", "blast radius", "coupling review", "dependency analysis", "breaking change", "migration review", "system design review".

Audit backend services for security, reliability, performance, and operability issues. Use when reviewing APIs, microservices, workers, or backend code changes. Triggers on "audit backend", "security review", "service audit", "API audit", "check vulnerabilities", "review microservice", "backend security", "audit API", "review service".

Read the sources you name — Teams/Slack channels, a code repo's commits and pull requests, a Confluence space, a tracker board or one person's tickets — and report only what is relevant to a project you name. You invoke it; it reads what is new since last time, checks each claim, and proposes what to do. Triggers on "check my channels", "what did I miss", "what happened in <repo>", "anything new in <space>", "what is on the board", "catch me up", "channel listener".

Comprehensive code review for quality, architecture, and performance. Use when reviewing PRs, auditing code quality, checking coding standards, evaluating design patterns, identifying performance bottlenecks, or analyzing technical debt. Triggers on "review", "audit", "analyze code", "check quality", "code smell".

Upload or download large files to/from a Coder CDE workspace using the coder CLI. Use when transferring files, directories, build artifacts, datasets, or binaries to a Coder workspace, when `rsync -e "coder ssh"` fails or desyncs, or when a copy over `coder ssh` hangs/corrupts. Triggers on "upload to coder", "copy files to workspace", "coder scp", "coder rsync", "transfer to CDE", "push files to my workspace", "coder config-ssh".

Analyzes any microservice codebase and generates a complete cold-start package — CLAUDE.md, custom skills, requirements template, development process docs, and onboarding guide. Works for any architecture. Use when setting up AI-assisted development for a new project. Triggers on "cold start", "set up AI development", "generate onboarding", "bootstrap project", "make this repo AI-ready".

Create high-quality Claude Code skills with proper structure, effective descriptions, and best practices. Use when creating a new skill, writing SKILL.md files, setting up skill directories, or asking how to make skills.

Proactively challenge implementation plans, architecture decisions, and design assumptions. Use when reviewing plans, designs, or technical decisions. Verifies claims via web search, cross-references documentation, identifies risks and gaps, and surfaces hidden assumptions. Activates automatically when evaluating technical proposals. Also the escalation gate — the moment your instinct is to ask the operator, run this skill on the most capable model available and decide whether the question is...

End-to-end Dark Factory build orchestrator: intent to shipped software via the df-* stages, test-first, adversarially verified, autonomous in dev/non-prod, documented as stage docs plus tickets. Triggers on "build this the dark factory way", "run a dark factory build", "take this spec to done end-to-end".

Analyze third-party dependencies for security, maintenance, and lock-in risk. Use when auditing dependencies, reviewing new packages, or assessing supply chain security. Triggers on "dependency audit", "package risk", "supply chain", "vulnerable dependencies", "license check", "outdated packages", "dependency review", "npm audit", "security scan".

Run the adversary gate: assess whether presented evidence proves a promise was kept, without redoing the work and never trusting a self-report. Use before trusting any "done/passing" claim, PR, or handoff. Triggers on "adversary review", "verify", "gate", "assess evidence", "is this really done".

Record a narrated, captioned product walkthrough video of a web app end-to-end with no human in the loop — synthesized voice-over, a real browser driven with a visible cursor, burned-in captions, assembled to mp4. Works against a public website or an authenticated app (Clerk session-ticket, or any Playwright storageState). Use when asked to record a demo, produce a walkthrough or product tour, make a screen recording of an app, narrate a UI, generate a demo video, or turn a demo script into a...

Dark Factory Stage 0.5 — scaffold a repo's in-repo agent inner-loop substrate (read-first context store + single-responsibility agents + checkable hand-off contracts + commit gate) from the proven template, populate it from the real codebase, and verify it. Use when bootstrapping a repo for DF work, running a DF build, or adding the agent substrate to an existing repo. Triggers on "context store", "agent substrate", "inner loop", "bootstrap agents", "df stage 0.5".

Navigate the codebase cheaply by reading the context store first, not re-scanning the repo. Use at the start of any investigation, feature, or review to locate the relevant service/file fast and with minimal tokens. Triggers on "where is", "how does X work", "understand the code", "find the service for".

Commit workflow — before committing, sync the knowledge layer (context store, per-service CLAUDE.md, and the agents/skills routing README) to the change, then draft a proper commit message and push. Use for "commit", "commit and push", "ship this", "save my work". Always stops for explicit approval before pushing.

Maintain and compress the context store so analysis is done once and reused, never repeated. Use to record a confirmed root cause, an architecture decision, or a service/contract change; or to compress sprawling notes back into the terse store. Triggers on "remember this", "update the context", "record decision", "we already analyzed this", "compress".

Validate an agent hand-off (Evidence Bundle, Root Cause, Design Spec, Implementation Report, Validation Report, Knowledge Entry) against its data contract before consuming it. Use at any pipeline seam to enforce LOCAL-reject ("escalate, don't guess") and the unforgeable-evidence rule (a PASS must carry test counts) instead of trusting prose. Triggers on "check the handoff", "is this evidence bundle complete", "verify the validation report", "contract check".

Trace a request/data flow end-to-end across services, queues, databases, object stores, and APIs to find every component a change or bug touches. Use when a problem spans boundaries or before changing a shared contract. Triggers on "trace the flow", "what depends on", "blast radius", "end to end path", "who consumes/produces".

Design a minimal-impact implementation for a new feature or fix before any code is written — files to touch, contracts, migrations, risks, and a test plan. Use for "implement X", "add feature", "how should we build this". Reuses the context store; records the decision as an ADR.

Turn a symptom into a confirmed root cause using evidence, not guesses — across any service, DB, queue, API, or infra. Use for "find the bug", "why is this failing", "0 records / stuck / DLQ / timeout / wrong data". Checks known findings first; escalates when evidence is missing instead of assuming.

Decide what to test and write the tests for a change — regression guards, edge cases, cross-service contracts — and scaffold the test project in the repo's conventions. Use after a fix or feature, or to assess coverage. Triggers on "write tests", "test coverage", "regression test", "validate change", "review test quality".

Model any system as data nodes (schema, origin, authority) and transforms tagged pure|effect, governed by validation rules and an authority that resolves conflicts. The shared frame the other df-* skills build on. Triggers on "data contract", "data flow", "validation rule", "transform", "pure or effect", "authority", "system of record".

Dispatch sub-agents under Promise Theory: state the promise plus the exact unforgeable evidence required, withhold holdout cases, verify the evidence not the self-report. USE EVERY TIME you spawn a sub-agent. Triggers on "dispatch sub-agent", "spawn agent", "parallel agents", "delegate", "fan out".

Dark Factory Infrastructure stage: produce the Deployment and Infrastructure Spec — DTAP placement, where data lives, trust boundaries mapped to enforcement mechanisms, secrets, and a verified observability surface. Triggers on "infrastructure", "deployment", "trust boundary", "where data lives", "deploy across environments".

Dark Factory Observability stage: make the consumable surface (dashboards and queryable traces keyed to scenarios, verified rendering live data) a named deliverable — a /metrics endpoint nobody can see is not observability. Triggers on "observability", "dashboards", "Grafana", "correlationId trace", "telemetry surface".

Dark Factory Product Owner stage: define Vision, Requirements as data contracts plus validation rules, and Test Scenarios — the semantics every later stage derives from. Triggers on "product owner", "requirements", "acceptance criteria", "test scenarios", "data contract", "what should we build".

Run the Dark Factory QA stage — execute the validation rules as tests, capture unforgeable evidence per scenario (by correlationId), run the holdout, and return a Works? verdict. QA is the OBSERVER: a self-report is not an assessment. Use when testing a deployed system, mapping PO scenarios to test cases, verifying with observability evidence, or judging a release. Triggers on "QA", "test plan", "verdict", "evidence", "holdout", "E2E test", "does it work", "verify the release".

Dark Factory Solution Architect stage: turn PO semantics into a Data Model, Data Flow (transform graph, pure|effect, idempotency, compensation) and Service Map, assigning each validation rule an enforcement locus. Triggers on "architecture", "data model", "data flow", "service map", "schema", "Avro contract", "solution architect".

Dark Factory Developer stage: build a service test-first (RED-GREEN-REFACTOR) where the test list is the PO validation rules and scenarios, not invented. Go and Python examples. Triggers on "TDD", "write tests", "test-first", "implement the service", "RED GREEN REFACTOR".

Drive and verify a Clerk-protected web UI end-to-end with a backend-minted session, no human login: mint the session, emit Playwright storageState, click through capturing per-scenario evidence and a verdict. Triggers on 'verify the UI', 'click through the app', 'test the front end', 'Clerk Playwright', 'authed UI test', 'UI evidence'.

Parse a video (mp4/mov/webm) into a transcript + timestamped frames so Claude can consume it, then extract context — specifically Dark Factory requirements — from it. Use when given a recording, demo, app walkthrough, screen recording, or "video" to summarize or turn into requirements/specs; when asked to "watch", "process", "consume", or "transcribe" a video; or to extract requirements/context from a demo for a dark factory build (PO vision, data contracts, validation rules, test scenarios).

Evaluate how easy it is for new engineers to work in a codebase. Use when assessing code quality, onboarding friction, or technical debt. Triggers on "code quality", "maintainability", "developer experience", "DX review", "onboarding", "cognitive load", "code smell", "refactoring", "tech debt".

Audit frontend code for security, UX regressions, performance, and accessibility issues. Use when reviewing React, Next.js, Vue, Svelte, or any frontend code changes. Triggers on "audit frontend", "review UI", "check accessibility", "a11y audit", "frontend security", "UX review", "performance audit", "review components", "audit React".

Publish a deliberate, structured Handoff document for the current objective into the active notepad and force a git push so it syncs across machines. Use when wrapping a session, handing to a teammate or fresh agent, hitting a milestone, or asked to "create a handoff", "write a handoff", "checkpoint for next session", "hand this off". Writes to <notepad>/handoffs/<date>-<topic>.md (NOT a temp dir), redacts secrets, references artifacts by path/URL, suggests next skills. In agent-notepad this ...

Design and architect microservices following Chris Richardson's Microservices Patterns. Use when designing services, APIs, data flows, or evaluating architecture decisions. Guides full workflow from feature intake to production-ready design with observability, async patterns, security, testing, and deployment strategies.

Verify whether a service, feature, or contract is safe to deploy to production. Use when preparing for deployment, reviewing release candidates, or validating production configs. Triggers on "production ready", "deploy review", "release check", "pre-deploy", "go-live checklist", "launch readiness", "deployment review", "ready for prod".

Generate comprehensive repository documentation following team standards. Use when creating README, CLAUDE.md, ARCHITECTURE.md, DESIGN_DECISIONS.md, or any project documentation. Includes Mermaid diagrams, status indicators, and AI context files.

Interactive requirements gathering that produces machine-executable specs for microservices. Guides conversation through structured rounds to produce a complete requirements doc where every section maps to a code artifact (SQL, Zod schemas, handlers, tests). Triggers on "new feature", "new service", "requirements", "I want to build", "let's spec out", "define requirements".

Security auditor for smart contracts - identifies vulnerabilities, logic flaws, reentrancy, access control issues, MEV/economic attacks, and oracle manipulation. Use when auditing Solidity, Vyper, or Rust/Anchor contracts, reviewing PRs for security issues, checking for exploits, or analyzing DeFi protocols. Triggers on "audit", "security review", "vulnerability", "exploit", "reentrancy", "access control", "MEV", "frontrunning".

Smart contract developer copilot for Solidity/EVM. Use when designing, implementing, refactoring, testing, or optimizing smart contracts; when adding features; when integrating with protocols; or when debugging failing tests.

Create or refresh an agent-notepad — a per-objective working-memory git repo (one notepad per objective, grouped by name prefix) that survives context compaction and drives several code repos from one session. Runs a short interview (objective, code-repo paths, done-criteria), optionally `gh repo create`s the notepad under the prefix→org map (consent required), writes SCOPE.md + repos.manifest.json, validates each code repo, offers per-repo df-context-store bootstrap (consent), warm-starts NO...

Archive a completed or abandoned agent-notepad while keeping its journal history intact. Marks the notepad retired (SCOPE.md status + a final journal milestone), stops it from auto-loading and syncing on future sessions, and preserves the append-only sessions/ history and handoffs for later recall — it never deletes the journal, the memory index entries, or the remote. Reversible: a later scope-init re-activates it. Use when an objective is done, a scope is being wound down, or a notepad shou...

Identify attackers, assets, trust boundaries, and realistic attack paths. Use when analyzing security posture, reviewing new features for threats, or creating threat models. Triggers on "threat model", "attack surface", "security analysis", "trust boundaries", "attacker goals", "threat assessment", "security review", "attack vectors".

Analyze a codebase to produce a complete service map — microservices, inter-service communication, database ownership, external integrations, and event flows. Generates AI-agent-friendly markdown. Use when onboarding to a new codebase, auditing architecture, updating CLAUDE.md, or before planning new features. Triggers on "map services", "service map", "map the architecture", "what services exist", "how do services communicate", "map this repo", "generate service map", "architecture map".

Assess whether tests actually protect the system from regressions. Use when reviewing test coverage, evaluating test quality, or identifying missing tests. Triggers on "test review", "test quality", "coverage gaps", "missing tests", "test assessment", "regression protection", "flaky tests", "test audit".

Run the autonomous, evidence-gated, Promise-Theory-verified control loop (the Vinculum governed loop + Dark Factory process) on any dev project. Use when the user wants to hand over a mission objective with full autonomy under a 2-trigger notify contract (done | blocked-on-all-fronts), evidence-gated decisions (Promise Theory, not self-reports), and an A/B/C decision policy. This is the single entry point that explains how the loop works and points to the dark-factory-build orchestrator. Trig...