Cooper Email

mh-mansouri/Project-Planning-Journaling

Scope a new project (or resume one) and set up a living, resumable documentation journal for it, including a routine weekly health check, not just updates triggered by commits. Use at the start of any project, before writing code, to ask about project type, Git repo status, short/long-term goals, and whether it should stay public/open-source or become a private product later. Also use when someone wants to document what has been done, wants a changelog or decision log, needs to resume work from a prior session without re-reading chat history, wants docs kept current after every commit, or want

ghorbanies/workflow-design

Models, proves, measures, and safely changes multi-step workflows — approval chains, review pipelines, intake/triage/fulfillment flows, ticketing, order processing, state machines with human gates. Use when designing states/gates/transitions or an audit trail, when a status field or event log is being added to a system, when tests guarding a workflow need auditing ("the suite is green but I don't trust it"), when someone asks where items get stuck, whether an approval step is worth keeping, who approved something, or why a queue is growing, or when a live workflow's definition must change with

jack-reson8/skill-skill

Write, upgrade or audit a Claude skill so it actually changes what gets generated, not a pile of notes. Use whenever the user wants to create a skill, turn a conversation, workflow or methodology into a skill, rename it, add research or lessons, asks why a skill isn't taking effect, or wants to publish a skill and get it listed in awesome lists and plugin marketplaces. Covers distilling from real work (corrections, rejections, accepted outputs), forcing functions (required artifacts, gates, checklists, scripts), descriptions that trigger, naming, a static audit with a health score, a with/with

luchasarie/feedback-loop

Turn post-task feedback—even blunt or angry feedback—into an evidence-based, approval-gated improvement plan for the agent/user workflow. Use after agent work goes wrong, misses expectations, creates friction, or should improve in future. Never mutate during the feedback turn.

DataOrigin/trade-show-prep-skill

Prepare, work and follow up a B2B trade show for an exhibitor or a visiting sales team. Builds a dated plan from 8 weeks before the fair, drafts meeting requests for the user's own accounts (email and LinkedIn), writes a booth qualification guide with a note template, and drafts a post-show follow-up sequence with cost per lead and ROI. Use when the user says "prepare our trade show", "we are exhibiting at", "we are visiting a fair", "meeting requests for the show", "booth qualification", "trade show follow-up", "post-show emails" or asks for help before, during or after a B2B fair or conferen

ggrigo/align

Epistemic feedback loop. Generate an interactive HTML form where the user rates LLM-produced claims as correct, wrong, almost, needs-nuance, can't-verify, or skipped — plus add notes and flag missing items. Submit downloads an align.md that Claude reads back to apply corrections to TASKS.md, smart-memory (guarded), and the per-session archive. Source-agnostic by design: any producer (rhythm, digest, briefing, todo, code review, financial recon, anything) that emits claims matching the claim shape can be aligned. Trigger words: "/align", "align", "give feedback", "correct the rhythm", "that's n