jackfranklin/dotfiles

design-discussion

Collaboratively discuss designs, evaluate trade-offs, and explore alternative implementation approaches. Starts from the simplest viable option and explores justified alternatives without fixed personas.

implementing

Implements an approved code-change plan safely. Use when beginning a feature, bug fix, or refactor that requires source changes, tests, a dedicated branch, small logical commits, and a GitHub pull request when applicable.

write-plan

Write a right-sized, no-placeholder implementation plan as a series of focused tasks, with exact file paths, implementation details, proportionate test steps, and commit instructions. Performs a pre-planning preflight investigation and Ponytail decision…

later

Log items to come back to later — bugs found mid-task, feature ideas, project feedback — as GitHub Issues. Use when the user asks to log, list, view, or work through items saved for later.

plan-walkthrough

Walk the developer through an implementation plan step-by-step in the chat interface. Explains the rationale, non-trivial alternatives considered, and risks for each step before pausing for feedback or approval.

agent-runner-github-code-review

Review the pull request snapshot prepared by agent-runner. Use only inside the agent-runner Docker image; it gathers GitHub context and applies the canonical code-review standard to the runner's pinned, isolated checkout.

grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

educational-reviewer

Explain the core concepts, library design patterns, system architecture, or host environment internals involved in a plan or git diff.

review-focus-areas

Identify and flag key areas of concern, plan deviations, risky changes, and uncertainties for the user to review.

summarize-for-bug-report

Use when the user requests to turn the current conversation, exploration, or technical findings into a succinct bug report.

wtf

Re-pitch the preceding response in clear, shared language.

ast-grep

Use when searching for multiline code patterns, AST node structures, API usages, or function signatures where plain regex/grep fails due to whitespace, linebreaks, or comment noise.

github-code-review

Perform a thorough, read-only review of one GitHub pull request. Use when given a GitHub PR number and you need to understand its linked issue(s), all existing discussion and review feedback, and independently apply the code-review skill to the exact PR code.

code-walkthrough

Walk the developer through the implemented code changes (diff) step-by-step in the chat interface, explaining each part and pausing for questions.

resolve-merge-conflict

Use when you need to resolve an in-progress git merge/rebase conflict.

glossary

Glossary: capture stable, repository-wide terms and concepts in `.jai/glossary.md` when they emerge. Use when a term or concept should become canonical repository context.

adr

Capture an Architecture Decision Record (ADR) for a significant decision made in the current project. Store in the project's adrs/ folder. Use when the user asks to record a decision, log an ADR, or capture why something was built a certain way. PROACTIVELY…

code-review

Aggressive maintainability review focused on structural simplification, deleting complexity, type safety compiler soundness, resource leaks, accessibility, localization, and concurrency. Activate this skill ANY TIME the user asks for a code review or when you…

diagnose-and-propose

Systematically diagnose a failing command (compilation error, test failure, runtime crash, etc.) before proposing any fix. Traces the root cause through source files and error chains rather than guessing. Only proposes options once the cause is confirmed; if…

jack-references

Manage Jack's personal technical reference library at ~/git/references. Use for searching/reading existing references, or adding new ones. Invoke with /jack-references and optional keywords to search, or when the user wants to save a new reference guide.…

new-deno-app

Scaffold a new Deno 2 + Hono + Deno KV + Eta + HTMX app with password auth and PWA support. Use when the user wants to create a new personal web app following this stack.

new-lit-pwa

Scaffold a new Vite + LitElement + IDB PWA app hosted on Netlify with a private GitHub repo. Use when the user wants to create a new personal web app following this stack.

update-neovim

Use when the user requests to update, upgrade, or install the latest release of Neovim.

review-plan

Present a plan to the user for inline annotation via the ai-review UI. Use when you have a plan ready for human review before executing it. The user will annotate it in the browser; you then revise based on their comments.

adversarial-reviewer

Use when planning code changes, writing an implementation plan, or reviewing code to identify potential edge cases, security vulnerabilities, input sanitization issues, race conditions, or boundary values.

handoff

Manage and search session handoffs, plans, and conversation summaries. Supports saving progress, listing previous handoffs, or generating a scannable chat summary.

onboard-branch

Onboard onto the current Git branch. Explores recent commits, diffs, uncommitted changes, and handoffs, then summarizes the state and asks clarifying questions to get up to speed.

onboard-plan

Gives a fresh agent a plan, audits it for comprehension gaps, and verifies technical assumptions against the codebase before implementation begins. Spawns a single sub-agent to perform both checks and presents the findings.

doc-clarity-opportunity

Looks for opportunities to improve documentation and code clarity — JSDoc, inline comments, and README updates. Use when the user wants to find documentation gaps or improve code clarity.

one-by-one

Walk through a list of items (e.g. code review findings, design questions, open decisions) one at a time, giving full context and discussion for each before moving to the next. Use when the user wants to work through a structured list interactively rather…

cloudflare

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), feature flags (Flagship), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use…

code-quality-reviewer

Reviews code changes for hacky patterns, redundant state, parameter sprawl, and leaky abstractions. Use when the user asks to "review code quality", "check for hacky patterns", "quality review", or wants a quality-focused code review.

code-reuse-reviewer

Reviews code changes to identify opportunities for reusing existing utilities and helpers. Use when the user asks to "review for reuse", "check for duplicate code", "find existing utilities", or wants a reuse-focused code review.

convert-audio-mono

Use when the user wants to convert a video or audio file's stereo audio to mono, or fix audio that only plays in one ear.

efficiency-reviewer

Reviews code changes for efficiency issues, unnecessary work, missed concurrency, and memory leaks. Use when the user asks to "review for efficiency", "check for performance issues", "find memory leaks", or wants an efficiency-focused code review.

fresh-eyes-amend

Amends the previous commit with current changes, then spawns two subagents to independently review the full git diff and propose fresh commit messages. Synthesizes the best parts into a final, accurate commit message without recency bias.

review-diff

Present a git diff to the user for inline annotation via the ai-review UI. Use when you want to review code changes before committing or requesting review.

skill-workshop

Iteratively improve a skill using subagent consensus and simulation testing. Use when a skill is producing bad outputs, has unclear instructions, or you want to stress-test it before shipping. Runs proposal evaluation and scenario simulation rounds with…

suggest-manual-tests

Use when the user wants to generate manual test cases, QA steps, or test plans based on a git diff of latest commits, branch comparison, or unstaged changes.

verify-mechanical-change

Spawns two independent subagents to verify if the staged or specified git diff is purely mechanical (no behavior or UI changes), then synthesizes their findings to ensure high accuracy.