LightDevCoder/skills
Skill Claude CodeCodex
Turn a formal SPEC into tracer-bullet vertical slices with blocking edges, then publish them as single-file-per-ticket issues on the local markdown tracker. Use only when the user explicitly invokes $project-tickets; it verifies the SPEC handoff, drafts a quiz-able breakdown, and hands execution to the frontier via…
LightDevCoder/skills
Skill Claude CodeCodex
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
LightDevCoder/skills
Skill Claude CodeCodex
After an explicit $recap request, output one concise line of at most 400 characters summarizing what happened in the current session so far without clearing, replacing, compacting, or rewriting conversation history, then stop.
LightDevCoder/skills
Skill Claude CodeCodex
Run a first-party Agent Skills collection through a governance-gated release: prepare the candidate commit, create the annotated tag and GitHub release, fresh-install verify against the published tag with both the generic latest and pinned forms, then publish the verified evidence and flip the docs from…
LightDevCoder/skills
Skill Claude CodeCodex
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
LightDevCoder/skills
Skill Claude CodeCodex
Use when you need to resolve an in-progress git merge/rebase conflict.
LightDevCoder/skills
Skill Claude CodeCodex
Run a lightweight review→findings→repair→re-review loop by resolving a reviewer, collecting normalized findings, and re-running until clean or bounded limit. Use for bounded review convergence; use project-review for final acceptance.
LightDevCoder/skills
Skill Claude CodeCodex
Maintain a decision-owned clarification state and ask the current actionable frontier as a round of independent questions with choices and recommendations. Use as a model-invoked engine inside a clarification conversation; do not use it to research facts, perform experimental work, or write a formal specification.
LightDevCoder/skills
Skill Claude CodeCodex
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
LightDevCoder/skills
Skill Claude CodeCodex
Teach the user a new skill or concept, within this workspace.
LightDevCoder/skills
Skill Claude CodeCodex
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
LightDevCoder/skills
Skill Claude CodeCodex
Stop. That last message did not land — re-pitch it.
LightDevCoder/skills
Skill Claude CodeCodex
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
LightDevCoder/skills
Skill Claude CodeCodex
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.