platypeeps

platypeeps

@platypeeps Organization

GitHub
81 Skills
0 Total Stars
October 2026 Joined

Public Skills

sd-research-repo

by platypeeps

Use when writing, rendering, reviewing, or publishing a document in a research repo that follows the shared research-repo standard — the numbered layout, provenance blocks, Status sections, and the outward mirrors.

Templates 0 8d ago

sd-watchlist

by platypeeps

Use when the user wants a read-only review of configured channels, feeds, authors, searches, playlists, podcasts, or collections that reports only material new items since an explicit checkpoint.

Code Review 0 10d ago

sd-ship

by platypeeps

Take committed work from a verified branch to a merged pull request, committing only enumerated paths.

Code Review 0 10d ago

sd-review

by platypeeps

Review the exact current diff with local providers and dispose of the findings locally, never posting them.

Code Review 0 10d ago

sd-topic-radar

by platypeeps

Use when the user wants ten ranked technical writing opportunities grounded in authorized personal activity, current developments, prior coverage, evidence readiness, novelty, and effort.

Academic 0 11d ago

sd-tips

by platypeeps

Use when the user wants short standalone tips surfaced, scored, and filed into the vault tip inbox of a writing content repository.

File Ops 0 11d ago

sd-status

by platypeeps

Read-only derived status for the repository you are standing in — is anything wrong, what is pending, what is next — with branch-protection enforcement gaps named.

Code Review 0 11d ago

sd-effort-calibrate

by platypeeps

Recommends a Claude effort level (low, medium, high, xhigh, max) for a task, subagent, skill, or recurring claude -p job. Resolves the level in effect today, proposes a starting level from task shape, and names where to set it. Optionally runs a small A/B eval of one frozen prompt at two or three adjacent levels, scores quality against a rubric fixed before the runs, and picks the lowest level that ties the best. Records one result line locally. Use when choosing or changing effort, after a model change, when a scheduled job runs slow or costly, or before adding effort: frontmatter or --effort to a job.

Prompts 0 11d ago

sd-check

by platypeeps

Run this repository's own check, test and lint entrypoints and report one typed result each.

Automation 0 11d ago

sd-plan

by platypeeps

Interview the user into a work item under docs/work, review the plan, and open its branch.

Templates 0 13d ago

sd-draft

by platypeeps

Use when the user wants to write, continue, or revise the draft of a registered piece in a writing content repository, and move it through the drafting, review, and ready stages.

File Ops 0 13d ago

sd-research

by platypeeps

Use when the user asks for deep, multi-source research on a question, topic, or writing piece and wants a verified, source-graded written brief or research notes rather than a quick answer.

Templates 0 13d ago

sd-draft-review

by platypeeps

Use when the user wants a draft from a writing content repository pushed to a private Google Doc for human review, or wants the reviewers' comments and edits pulled back as a working list.

Comments 0 13d ago

sd-publish-drive

by platypeeps

Use when the user says a ready piece in a writing content repository should ship, to run its final gates, attach a tip, and push it to the Drive publishing folder; or when the live URL comes back.

File Ops 0 13d ago

sd-grill

by platypeeps

Use when the user wants their own proposal, plan, claim, or half-formed idea interrogated one question at a time until it survives an outsider, producing a hardened statement of intent, or an honest account of where it stopped, rather than an implementation.

Code Review 0 13d ago

sd-author

by platypeeps

Use when the user wants to develop an original evidence-backed technical article through a one-question interview, approved editorial brief, staged drafting, review, and publication handoff.

Writing 0 15d ago

sd-humanizer

by platypeeps

Remove signs of AI-written prose while preserving facts, structure, and the author's voice.

Comments 0 15d ago

sd-bookmark-triage

by platypeeps

Use when the user wants to deduplicate and triage a bounded collection of saved links, videos, pages, or notes into a small evidence-labeled attention queue without mutating the source collection.

Finance 0 16d ago

sd-study-guide

by platypeeps

Use when the user wants a bounded source set transformed into a durable study guide with traceable concepts, definitions, examples, retrieval prompts, practice, solutions, traps, and review order.

Code Review 0 16d ago

sd-fact-check

by platypeeps

Use when the user supplies claims or a draft and wants a claim-by-claim evidence audit with supported, partially supported, unverified, contradicted, or outdated verdicts.

Research 0 16d ago

sd-rebase-hygiene

by platypeeps

Use when the user explicitly asks to rebase a long-lived branch or worktree — user-invoked only, never triggered automatically. Fetch before trusting local state, dry-run the merge before touching the working tree, pre-plan every conflict resolution, and verify the remote ref after a user-approved force-with-lease push.

Git & VCS 0 16d ago

sd-profile

by platypeeps

Use when the user wants to create, inspect, correct, review, import, export, or forget a consent-driven personal operating profile with traceable assertions.

Code Review 0 16d ago

sd-docs-bustest

by platypeeps

Use when documentation must survive a cold read — checking that a newcomer with no prior context can execute a README, runbook, setup guide, or handoff doc exactly as written, when docs are created or changed, or when asked to bus-test docs.

Code Review 0 16d ago

sd-meeting-follow-through

by platypeeps

Use when the user wants a source-traceable post-meeting package that reconciles intended and actual outcomes, decisions, commitments, unresolved items, and consent-gated follow-through.

Automation 0 16d ago