Total Skills
10
Author Profile: henry-md
Skills published by henry-md with real stars/downloads and source-aware metadata.
Total Stars
0
Total Downloads
0
Skills Performance
Comparison chart based on real stars and downloads signals from source data.
add
0
Stars
0
Downloads
0
characterize
0
Stars
0
Downloads
0
check
0
Stars
0
Downloads
0
checks
0
Stars
0
Downloads
0
fix-ts
0
Stars
0
Downloads
0
railway
0
Stars
0
Downloads
0
see
0
Stars
0
Downloads
0
steal
0
Stars
0
Downloads
0
Published Skills
add
Stage only the current chat's relevant changes while leaving unrelated work in the tree untouched. Use when the user explicitly invokes the add skill to rebuild the staged set from this conversation only, including earlier messages in the same chat. By default it suggests a commit message without committing or pushing, and `/add push` additionally commits and pushes the staged result.
Repository SourceNeeds Review
characterize
Reviews all staged, unstaged, and untracked changes in the working tree and groups them into logical buckets that likely belong in separate commits or parallel tasks. Use when the user wants to understand a dirty tree before staging or committing, split local changes into coherent chunks, or explicitly asks for an `auto` mode that stages, commits, and pushes each bucket in sequence.
Repository SourceNeeds Review
check
Capture and inspect a page from Henry Deutsch's logged-in browser perspective by refreshing or reusing Playwright auth state, then taking a real screenshot. Use when Codex needs to verify a protected route, inspect Henry-specific data, or see what a page looks like for the signed-in user `henrymdeutsch@gmail.com`.
Repository SourceNeeds Review
checks
Iteratively implement and visually verify a requested UI or product change by repeatedly visiting the target page, comparing real screenshots against the user's request, editing code, and looping until the result matches spec or a real blocker remains. Use when the user invokes `/checks`, wants you to keep checking a page until it looks right, or expects an autonomous edit, screenshot, compare, and fix loop rather than a single verification pass.
Repository SourceNeeds Review
fix-ts
Perform a thorough TypeScript cleanup pass when the user explicitly invokes the fix-ts skill to address compiler failures, high-value lint issues, or build-breaking type regressions. Use it for TypeScript-heavy cleanup work where errors should be grouped by root cause and fixed cleanly at the source rather than patched with broad casts or one-off assertions.
Repository SourceNeeds Review
railway
Investigate a failed Railway deployment when the user explicitly invokes the railway skill or asks to debug a Railway deployment failure. Anchor the work to a specific failed deployment ID, read the full deployment-specific logs, reproduce the failing Railway command locally, make the smallest relevant fix, verify locally, and stage only the Railway-related changes without committing or pushing.
Repository SourceNeeds Review
see
Show the raw contents of another skill's SKILL.md file when the user explicitly invokes the see skill, such as `/see test` or `$see test`. If the user invokes see without a second argument, treat it as a request to inspect the most recently created skill in the current conversation history. Do not use for general code or file browsing.
Repository SourceNeeds Review
steal
Keep Claude and Codex skills in feature parity by comparing `~/.claude/skills` and `~/.codex/skills`, finding missing skills on either side, and reconciling functionality gaps inside matching `SKILL.md` files. Treat matching Codex built-ins such as `skill-creator` as satisfying the Codex side so duplicate custom Codex files are not created. Use when the user wants to sync custom commands across Claude and Codex, mirror one or more named skills between them, or close behavior gaps without copying the entire built-in Codex catalog into Claude.
Repository SourceNeeds Review
test
Return exactly "hi :)" and nothing else when the user explicitly invokes the test skill to verify custom skill discovery or slash-menu wiring. Do not use for general testing tasks.
Repository SourceNeeds Review
verify-page
Open a route in a real browser with Playwright, capture a screenshot, and visually inspect the result before claiming the page works. Use when the user asks you to see a page, verify that a route loads, or check UI changes directly.
Repository SourceNeeds Review