Claude Skills by woditschka

Hold the agentic-coding-reference to a high bar after a change; three layers, one verdict. Layer 1 runs the deterministic battery (harness/verify-harness.py — its header carries the step list). Layer 2 runs the judgment-only consistency audit — six checks, agent depth delegated to /audit-agents. Layer 3 dispatches an adversarial multi-agent review of the working-tree diff. The default run scopes the judgment layers to the diff; "/audit-harness full" runs all six consistency checks across the ...

Pull generic improvements from a downstream project back into the /harness source tree. Detects the source project's stack (Go, Java Spring Boot, or the generic fallback), diffs its harness runtime (.claude/, schemas, scripts) against the materialized harness (core plus the stack slice), classifies each change as harvest, skip, or ask, generalizes domain patterns on the way back, and routes language-agnostic changes to core/ and stack-specific ones to stacks/<stack>/. Load when the user invok...

Scaffold the project-owned files a new harness consumer commits — its CLAUDE.md rules file, .claude/settings.json, scripts/layout.toml (with the channel declaration — copy by default), scripts/backlog.sh (the /next tracker connector, unbound until a team binds it), the docs/ brief roster, and the .gitignore block. Detects the target's stack (Go, Java Spring Boot, or the generic fallback) from its build marker. Does NOT install the runtime; that is materialize. Never overwrites a project file ...

Install or update the claude-dev tooling — the claude-dev command, the container Dockerfile, the default config, the egress allow-list, the IDE-oracle preflight, and the ~/.claude.json scrubber — from this repo's tools/claude-dev/ into ~/.local/bin and ~/.config/claude-dev. Thin front-end for tools/claude-dev/install.sh: run its check mode to show drift, apply only on the user's approval. Use when the user asks to install claude-dev, set up the development container, or update the launcher or...

Install or update the harness-stats tooling — harness-statusline.sh, cache-report.sh, and the cache-report skill — from this repo's tools/harness-stats/ into the user's ~/.claude/ directory. Thin front-end for tools/harness-stats/install.sh: run its check mode to show drift, apply only on the user's approval. Use when the user asks to install the cache tooling, set up the statusline, update the harness-stats scripts, or reconfigure cache reporting. Examples: "set up the statusline", "install ...

Install or upgrade a project's harness by completely replacing its harness-owned runtime with the current /harness. Auto-detects the stack (Go, Java Spring Boot, or the generic fallback) from the build marker, scaffolds project-owned files via /init when they are missing, replaces the runtime, removes stale orphans, preserves genuine project extensions (asking when unsure), respects the project's declared distribution channel, verifies the installed suites, and validates with the doctor. Load...

Cut a new harness version. Evaluates the semantic-version bump from the conventional commits since the last v* tag, proposes it with reasoning, and asks you to confirm or override (forward-only). On confirmation it runs harness/release-version.sh, which stamps harness/VERSION (+ release date), runs propagate-harness.sh (propagate + full battery), then creates the local chore(release) commit and the annotated v<VERSION> tag. It STOPS there and prints the push commands; it never pushes or publi...

Periodic multi-angle improvement review of the reference. Always fans out all five read-only research agents in parallel — maintainer tooling, documentation, runtime cost, source duplication, consumer surface — so cross-angle tension informs the synthesis. Every agent carries the challenge charter: question the design against the README's stated philosophy, recommend removals that pay for themselves. Judges findings by the resilience-first doctrine; a settled ADR decision is rebuttable with a...

Regenerate the reference's architecture figures when the harness changes, in one consistent house style. Owns the figures as native .drawio sources exported to embedded-XML PNGs; the sources are the style spec. The skill holds the intentions behind the style, each figure's composition, the draw.io export command, and the README embedding convention. Load when the pipeline, agents, loops, distribution channels, harvest flow, research-arc milestones, or claude-dev network topology change, when ...

Update the milestone timeline in docs/project-history.md with executive-level milestones since the last entry. Walks committed git history and uncommitted working-tree changes, filters out non-milestone work (deps bumps, prose tightening, mechanical refactors), proposes entries in imperative mood (one concise clause, ~8-20 words) for approval. Keeps a linear timeline: one dated milestone per line, oldest to newest, with no entry cap and no era rollups — every era stays as granular as its real...

Check upstream tool documentation for drift in the version-stamped surfaces: docs/cross-tool-strategy.md, docs/native-sandbox.md, docs/open-weight-models.md, and the workflow doc's stamped sections. Fetches source URLs, compares claims against current doc, and reports drift. Use when updating the cross-tool strategy guide or checking for tool changes.

Check pinned tool, plugin, and dependency versions across the Go and Java Spring Boot samples and the bookstore workspace members — including the init skeletons and root README that restate them — plus the SHA-pinned GitHub Actions in the root CI workflow and the dated pricing override in the harness-stats accounting, against upstream stable releases. Reports drift as a table, applies approved bumps to build files, version tables, and workflow pins, and verifies each change.

**Status:** Accepted

**Status:** Accepted

Architecture Decision Record format, naming conventions, and when to create ADRs. Load when making or documenting architectural decisions.

Audit the agentic configuration for consistency, coherence, and conciseness. Load when modifying agent definitions, skills, or pipeline structure, or to verify cross-tool parity.

Audit the project's docs/ briefs against the high bar — each document on its own (principle form, enforceability) and in combination (cross-document coherence, contradictions, brief-vs-data agreement). Runs the doctor (deterministic structural gate) first, then the advisory judgment review, and reports both. Load when you want to check the docs hold up — at onboarding, after a harness upgrade, or on request. The judgment half is advisory: it judges form, never philosophical direction.

Grade a passing change for how much human attention it deserves before merge. Load when running the change-grader after the reviewer roster approves. Holds the full grading protocol: the five facets, worst-facet aggregation, the facets-rationale-verdict order, persistence, and scope/non-goals.

Draft the project's docs/ briefs by surveying an existing codebase. Recovers requirements, design, vocabulary, and decisions from what the code demonstrably does, marking every statement with how it is known — derived, confirmed, or not recoverable. Load on a brownfield project whose briefs onboarding scaffolded but nobody has written, before the pipeline runs. Not for a greenfield project, where the owner writes them as the work proceeds. Observed behavior is not an intended requirement; thi...

Deterministic, blocking validation of the project's docs/ brief against the harness-project API: roster existence, required sections, data slots, naming conventions, channel invariants, and the reviewer roster. Load when onboarding a project, after a harness upgrade, or before starting pipeline work. Model-free, CI-runnable.

How to write and review project documents: the language-agnostic writing standards, the five-document architecture and ownership boundaries, the document-structure model, cross-reference and maintenance rules, and the review checklist the doc-reviewer enforces. Load when authoring or reviewing any PRD, system-design doc, ADR, brief, or CLAUDE.md.

The writer contract for the handoff log: how every pipeline agent appends records to .scratch/handoff.jsonl through scripts/handoff.py. Load when producing any handoff record — dispatch-start, a substantive record, or a consultation. The routing side lives in handoff-routing.

The reader board for the handoff log: render each slice of .scratch/handoff.jsonl — header, review-convergence matrix, timeline — to the terminal via scripts/handoff.py view. Load when the user asks where the pipeline stands, for a slice status, or for a review-progress summary. The writer side lives in handoff-append; routing lives in handoff-routing.

Pipeline routing rules and handoff conditions between specialist agents: gates, recovery, and the root-applied procedures. Load when coordinating feature delivery, checking pipeline state, or determining which agent to invoke next. The writer side of the log lives in handoff-append.

Run slice intake as a live discussion under the product expert's contract, then record the owner's request and decisions verbatim as an intake-decision record. Load when the user brings a feature request for discussion or invokes /intake.

Clear the scratch directory and start a fresh feature context. Load when starting a new feature or resetting pipeline state.

Reset feature context and recommend what to work on next based on PRD coverage. Load when the user asks "what's next" or invokes /next.

PRD format conventions, boundary rules, and template references. Load when writing or reviewing product requirements.

Review process overview, feedback tag definitions, and output format. Load when conducting or processing code reviews.

Run the quality gate, then commit staged and unstaged changes and push to the remote in one step. Load when the user asks to commit and push, or invokes /ship.

TDD cycle process and design-check decision tree for feature implementation. Load when implementing features using test-driven development.

Scaffold the project-owned files this harness plugin needs — CLAUDE.md, .claude/settings.json, scripts/layout.toml, scripts/backlog.sh, the seven docs/ briefs, and the .gitignore block — from the plugin's bundled skeletons. Marketplace channel by construction; no clone of the reference needed. Run once before marketplace-setup on a project that lacks these files; it never overwrites an existing one.

Set up or upgrade this harness plugin's project-side half. Installs the engine sliver (scripts, schemas, templates) into your project and gitignores it, and refreshes the managed CLAUDE.md chapters. Run after installing the plugin and again after every plugin update.

Build, test, format, and lint requirements that must pass before code review. Load when checking implementation completeness or running the quality gate.

Code-quality checklist — language-agnostic principles, design placement and workload fit against the project's recorded briefs, and the per-section slots a stack fills in. Load when conducting code quality reviews.

Architectural validation checklist for feature approval. Load when validating that features fit into the existing architecture.

Synchronize documentation with the current codebase. Fix drift between docs/prd.md, docs/system-design.md, and actual source code.

Security-review checklist, threat model, severity classification, and supply chain verification — language-agnostic, with per-section slots a stack fills in. Load when conducting security reviews.

Test quality checklist, security-testing requirements, and dynamic-analysis expectations — language-agnostic, with per-section slots a stack fills in. Load when conducting test reviews.

Build, test, format, and lint requirements that must pass before code review. Load when checking implementation completeness or running the quality gate.

Go code quality checklist based on Google Go Style Guide, plus design placement and workload fit against the project's recorded briefs. Load when conducting code quality reviews.

Architectural validation checklist for feature approval. Load when validating that features fit into the existing architecture.

Synchronize documentation with the current codebase. Fix drift between docs/prd.md, docs/system-design.md, and actual source code.

One-command health check for the GoLand MCP oracle: is it connected, is the right project bound, and is the project model loaded correctly (Go module synced)? Load when the user asks to check / diagnose / verify the GoLand (IDE / MCP / oracle) connection or status, or when an agent is about to rely on the IDE oracle's semantic results and needs to confirm they are trustworthy.

How to use GoLand's MCP tools as a read-only semantic oracle while coding Go. Use this skill WHENEVER the GoLand MCP server is connected and the task involves understanding or validating the codebase — finding where a symbol is used, understanding a type, or checking for problems. Consult it before reaching for grep on a Go-symbol question, and after any batch of edits. The agent is the sole writer; GoLand never mutates files and never runs code.

Security review checklists, threat model, severity classification, and supply chain verification for Go applications. Load when conducting security reviews.

Test quality checklist, security testing requirements, dynamic analysis, and test organization conventions for Go applications. Load when conducting test reviews.

Build, test, format, and lint requirements that must pass before code review. Load when checking implementation completeness or running the quality gate.

Java code quality checklist for Spring Boot applications, plus design placement and workload fit against the project's recorded briefs. Load when conducting code quality reviews.

Architectural validation checklist for feature approval. Load when validating that features fit into the existing architecture.