ctx-dispatch
Coordinate nontrivial work in the ctx repository when a task has independent investigation, implementation, or test lanes;…
Select proportional validation for changes or reviews in the ctx repository. Use before handing off material code, workflow, migration, documentation, security, packaging, or release changes; before a PR; or when asked whether a change is adequately tested. Do not use for pure
Claude Code
$ npx -y skills add stevesolun/ctx --skill ctx-verify --agent claude-code
Codex
$ npx skills add stevesolun/ctx --skill ctx-verify -a codex -y
Cursor
$ npx skills add stevesolun/ctx --skill ctx-verify -a cursor -y
Gemini CLI
$ npx skills add stevesolun/ctx --skill ctx-verify -a gemini-cli -y
GitHub Copilot
$ npx skills add stevesolun/ctx --skill ctx-verify -a github-copilot -y
OpenCode
$ npx skills add stevesolun/ctx --skill ctx-verify -a opencode -y
Windsurf
$ npx skills add stevesolun/ctx --skill ctx-verify -a windsurf -y
name: ctx-verify description: Select proportional validation for changes or reviews in the ctx repository. Use before handing off material code, workflow, migration, documentation, security, packaging, or release changes; before a PR; or when asked whether a change is adequately tested. Do not use for pure questions with no changed artifact.
1. Inspect the requested behavior and changed surface. Read only the relevant section of `CONTRIBUTING.md` before selecting checks. 2. Run the smallest focused tests or deterministic checks that exercise the changed behavior first. 3. Escalate evidence in proportion to risk:
change: run the fast gate, then `python scripts/ci_preflight.py --profile pr`.
contract in `CONTRIBUTING.md`; do not require tracker changes for ordinary prose-only edits.
`CONTRIBUTING.md`; local checks do not replace required Windows evidence. 4. Treat the fast gate as committed-history evidence. When the working tree is dirty, pair it with focused checks against the actual uncommitted changes. 5. If a gate cannot find its trusted pytest, Ruff, and mypy environment, report the environment failure. Do not silently install dependencies or weaken the trust check. 6. Use an independent validator only when semantic risk remains after deterministic checks, especially for material security, migration, or release work. 7. Report each check, its result, and any omitted or unavailable evidence.
Mark each applicable criterion `pass`, `fail`, or `not verified`:
failure or regression paths.
and platform requirements remain satisfied where relevant.
stale or inapplicable.
Do not claim completion while an applicable criterion fails. Treat missing required evidence as `not verified`, not as a pass.
Find the cheapest AI coding setup that actually works on your repo. CTX Fit analyzes your repository, tests promising AI coding configurations against real tasks in it, and produces the winning configuration as a reviewable change — in your working tree with
Coordinate nontrivial work in the ctx repository when a task has independent investigation, implementation, or test lanes;…
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style,…
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate…
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional…
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all…
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger:…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.