Explore skills

Check a documentation file for drift against the actual codebase — CLI commands, file paths, config keys, function signatures, version numbers, environment variables — and propose corrections. Use when the user wants to audit README.md, docs/*.md, or similar for claims that no longer match reality. Drift usually comes from refactors that forgot to update the docs.

Audit a plan's design decisions — library, framework, pattern, and architecture choices in IMPL.md / ROADMAP.md — for missing `# research(YYYY-MM):` provenance, then web-search to ground them. Use when you want architectural choices verified against current best practice before they harden into code, rather than resting on training-cutoff recall. Catches committed decisions stated as fact but neve

Rewrite docstrings and comments by reading the actual implementation, call sites, and tests — produce grounded, factual prose instead of deleting slop. Sibling of /techne:deslop. Use when the user wants to replace overhyped or hallucinated documentation with accurate one- or two-line descriptions derived from what the code actually does.

Cross-repo drift audit across linked repos listed in `~/.claude/techne.toml` (configurable per-user). Read-only inspection of CI action pins, toolchain pins in pyproject.toml, skill-context structural parity, GitHub merge settings, open PRs, and branch hygiene. Triggers on phrases like "audit the sisters", "are the sisters in sync", "check cross-repo drift", or when multiple sister repos are menti

Run an observed live dev session — Claude drives an interactive REPL in a named tmux session, the human spectates read-only via `tmux attach -r`. Use when the user wants to play through, debug, or explore a service's REPL together. Trigger phrases include "let's do a live smoke", "run a theoros session", "I want to spectate while you drive the CLI", "start an observed dev run". Reads per-repo fact

Review the current project state and continuously guide the project toward better Harness and Compound Engineering practices. Identify: - behaviors that align with best practices - anti-patterns or weak workflows - missing operational discipline, evals, harnesses, or feedback loops Then recommend the next highest-leverage step, including: - what to do next - why it matters now - what commands, too

Turn the current conversation context into a GSD-compatible PRD with WHAT/HOW constraints, optionally writing to .harness/phases/01-discuss/CONTEXT.md. Use when user wants to create a PRD from the current context.

Briefs the current session by reading session state, handoff doc, and memory to determine the active phase, task, and context budget. Outputs a structured briefing and detects whether the phase should be skipped or reverted based on observable artifacts. Use at the start of every long-running agent session, or when user says "start session", "what are we working on", "resume", "pick up where we le

Use when designing REST or GraphQL APIs, creating OpenAPI specifications, or planning API architecture. Invoke for resource modeling, versioning strategies, pagination patterns, error handling standards.

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.

Parses error messages, traces execution flow through stack traces, correlates log entries to identify failure points, and applies systematic hypothesis-driven methodology to isolate and resolve bugs. Use when investigating errors, analyzing stack traces, finding root causes of unexpected behavior, troubleshooting crashes, or performing log analysis, error investigation, or root cause analysis.

This skill should be used when the user needs deep, multi-step research using native web tools (WebSearch/WebFetch) without external API keys.