Claude Skills by EfiPerez

github.com/EfiPerez

5 skillsA× 50 installs2 views

DoneAEnd-of-session wrap-up skill. Run at the end of every working session to: summarize what changed, update any affected CLAUDE.md sections, run the project's test suite (if one exists), commit and push to git, and print a final status report. Trigger this skill whenever the user types /done, says "wrap up the session", "end of session", "let's close out", "finish up", "session summary", or any variation of wanting a structured close-out after completing work. Also trigger if the user says "we'...ai-agentsgoshellVotes: 0GitHub stars: 4
HandoffACompresses the current session's context, progress, and next steps into a Markdown file in the project's handoffs/ folder, so a future Claude Code session can resume exactly where this one stopped. Trigger this skill whenever the user types /handoff, or says "write a handoff", "hand off to the next session", "save the session context", "save where we left off", "I'm running out of context", "context is running low", "I'll continue this tomorrow", "dump the state so I can resume", "session ha...ai-agentsgoshellVotes: 0GitHub stars: 4
Resume HandoffALoads the most recent session handoff document from the project's handoffs/ folder, reads the files it points at, checks whether anything has changed since it was written, and reports where the last session stopped so work can continue seamlessly. Trigger this skill whenever the user types /resume-handoff, or says "resume the handoff", "load the last handoff", "read the handoff", "pick up where we left off", "continue from yesterday", "continue where the last session stopped", "what were we ...ai-agentsgoshellVotes: 0GitHub stars: 4
Codec BuildAHands a frozen spec to a second model to IMPLEMENT, then runs a bounded review-and-fix loop between Claude and OpenAI Codex over the resulting diff. Claude picks the topology (Codex builds by default; a Sonnet subagent builds when the main context needs protecting), enforces a clean-tree or snapshot gate before any write, and caps fix rounds at 2 before Opus takes over directly. Runs silently: the user is asked only whether to commit, and the output is one report file with a table of topics a...ai-agentsgoshellVotes: 0GitHub stars: 4
Codec ReviewARuns a bounded adversarial review loop between Claude (builder and arbiter) and OpenAI Codex (newest GPT Sol model, read-only critic) over a document or codebase. Codex attacks the work and returns a structured verdict; Claude judges each finding, rewrites the target, and re-submits to the SAME Codex thread until Codex approves or the round cap is hit (5 by default). Runs silently: the only question the user is asked is whether to spend more rounds at the cap. Output: one report file. Use whe...ai-agentsgoshellVotes: 0GitHub stars: 4