最近新增
刚加入收藏的新技能，抢先试用。
mplusautomation-guide
lzhs1995
Use when running or reproducing Mplus models from R with MplusAutomation, including APIM, mediation, moderation, conditional mediation, [[init]] templates, ClaudeR/RStudio execution, multiple imputation, batch recovery, diagnostics, and manuscript tables.
comparegroups-guide
lzhs1995
Use when creating publication-ready descriptive statistics or Table 1 outputs with the R compareGroups package, especially from labelled Stata data, panel/repeated-cross-section data, attrition samples, or ClaudeR-managed RStudio workflows.
cmaverse-paired-mval
lzhs1995
Use when running CMAverse 4-way decomposition with paired mval (M=0 and M=1 in one bootstrap), saving full cmest objects, and fanning the per-mediator workers out across one RStudio session. Pairs with clauder-rstudio-workbench for the parallel async fan-out machinery.
clauder
lzhs1995
Connect to RStudio through ClaudeR or route R script execution, async progress and connection recovery to the maintained clauder-rstudio-workbench skill.
budget-coach
PersonalClaw
Weekly spend review
personal-cfo-setup
PersonalClaw
Finish setting up the Personal CFO pack — bind the finance folder and the digest day.
health-os-setup
PersonalClaw
Finish setting up the Health OS pack — bind the journal folder and the reminder time.
web-verify
PersonalClaw
Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence. Use before claiming a frontend change works.
visual-output
PersonalClaw
Emit rich visual output in chat via <widget> tags — styled HTML cards, charts, tables, interactive tools, and drawn SVG/canvas diagrams, illustrations, and animations — theme-aware, centered, and responsive instead of clashing or cramped.
task-and-project
PersonalClaw
Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.
research-campaign
PersonalClaw
Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated. Use for open questions that need real investigation rather than one lookup.
pclaw-features
PersonalClaw
Channel-neutral reference for PersonalClaw's capabilities — sessions, agents, models, dashboard, scheduling, goal loops, tasks, subagents, file/media handling, and config — so you can explain what PersonalClaw can do and route the user to the right surface.
pclaw-api
PersonalClaw
The operator's manual for DRIVING PersonalClaw's API and tools — how to find an exact tool/route signature, the mandatory verify-after-mutate loop, and what NOT to hand-roll. Load this before creating triggers, wiring models, driving app routes, or authoring skills through the API.
memory-discipline
PersonalClaw
When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool error) as lessons; recall before re-asking.
clauder-rstudio-workbench
lzhs1995
Use when an agent needs to connect to a live RStudio session through ClaudeR, configure or verify the r-studio MCP bridge, run R code safely, poll long async jobs with progress, or avoid multi-session and multi-agent conflicts.
ledger-anatomy
abhione
Explain a business, finance or strategy concept (SaaS flywheel, unit economics, LTV:CAC, cash conversion cycle, marketplace liquidity, network effects, burn and runway, cohort retention, pricing, operating leverage, funnels) as a live isometric "how things work" machine in one self-contained HTML page. A small business model drives every moving part, sliders change its inputs, and hover/click shows what each part means. Use this whenever someone wants to explain, teach, visualise or animate how a business works, an interactive explainer for a metric or business model, or a figure for a deck, memo, course or landing page, even if they never say "isometric" or "machine".
loop-worker
PersonalClaw
Per-cycle protocol for an autonomous goal loop worker — the unified autonomous goal engine that runs one self-directed cycle per turn until its goal is met, then self-retires. Drives one cycle against a loop's file interface (status.json gate, brief.md goal, guidance.txt nudges, findings/cycle_NNN.json, FINDINGS.md, the type-appropriate deliverable, STOP sentinel). The worker produces work and reports evidence; a deterministic check or a separate judge — never the worker — decides done-ness.
yt-transcript
PersonalClaw
Fetch the transcript of a YouTube video and summarise it with timestamps. Use when the user shares a youtube.com or youtu.be link and asks what it says.
incident-writeup
PersonalClaw
Turn my incident notes, Slack excerpts and graphs into a blameless postmortem in Cartwheel's format. Use after an on-call incident once the mitigation is in.
feedsmith-release
PersonalClaw
Cut a feedsmith release - bump the version, move the Unreleased changelog section, tag, and draft the GitHub release notes. Use when I say "release feedsmith" or "cut 0.x".
evaluate-enrichment
monarch-initiative
Use when evaluating a GO enrichment method or a GOA evidence variant (all vs IBA vs IBA+IEA vs no-contributes_to) against the curated benchmark in this repo — the IBA/evidence-ablation eval. Covers building queries.gmt, prepare_go_eval, running genesets-rs, and scoring with the confirmatory/mechanistic split and the recovery_status diagnostics, plus the don't-refit-the-gold guardrail.
curate-geneset
monarch-initiative
Use when curating or reviewing a GO-term interpretation of a non-GO gene set (MSigDB C8/C2/H, literature disease-activity, or GWAS/CRISPR genetics) for the curation/ gold standard in this repo. Covers grounding in the real membership, OLS term verification, the category / recovery_status / insight axes, evidence, series, the 4-gate validator, and folding the set into the eval.
scheduled-verification-with-session-fallback
jinwon-int
Schedule a verification/check to run at a future time, choosing a scheduler that survives what can happen before it fires — a persistent systemd timer/crontab when the wait can cross a reboot (any multi-hour or overnight wait), a systemd-run transient timer only for short waits — and treating session-bounded CronCreate as a last resort. Use when a check must fire at a known future time, when a scheduled check silently never ran, or before claiming a node "cannot schedule durably".
nclex-multi-pr-pre-flight-gate-validation
jinwon-int
Pre-flight validate one or many jinwon-int/nclex content PRs against the CURRENT main gate before A2A dispatch or rebase — pin each head in a detached worktree, replay the gate job's validation steps, reproduce the stale-base trap that makes an old green CI turn red on push, classify failures per tool (validate_refs, ko_terminology, ko_coverage, content_process/coverage, a2a_quorum, similarity), and emit READY / NEEDS_FIX / NEEDS_REBASE verdicts with preserved evidence. Use when triaging a batch of open nclex PRs, when a PR's merge base is weeks behind main, when a PR shows green checks but you suspect the rules moved, or before dispatching to nclex-a2a-content-pipeline.