Claude Skills by hamr0

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

Review a branch before merge

Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them

Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.

Refactor and optimize [code]

Verify, write the CHANGELOG, cut a version — then hand the release sequence back

Consolidate stashes + friction into project memory

Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time

Security audit — recurring six, injection, auth, trust boundaries

Mechanical pre-deploy gate — tests, build, tree state

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Stash session context [name]

Generate and run tests [file]

Review a branch before merge

Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.

Refactor and optimize [code]

Verify, write the CHANGELOG, cut a version — then hand the release sequence back

Consolidate stashes + friction into project memory

Stash session context [name]

A test skill for fixture purposes.

Verify what you delivered since the last self-review with real runs, and review its structure

Verify what you delivered since the last self-review with real runs, and review its structure