lemur47
UserPMO as a Service - Atomic logic for decision-making. Turning abstract ideas into executable functions.
Categories
Indexed Skills (6)
session-rituals
Open or close a programme working session — reconcile shared memory against repo and tracker ground truth, sweep for staleness, and hand over. Use for the boot ritual (start of session — read memory, verify against the working tree and the work tracker, check inbound PRs, report and prepare sprint work) and for the close ritual (end of session — write findings back, check doc staleness, open a doc PR, log the handover). Triggers on /boot-ritual, /close-ritual, "boot the session", "close the session", "session handover".
ship
Drive a change from working tree to a merge-ready pull request — reproduce the gates exactly as CI runs them, triage reds correctly, and sequence the merge. Use when committing, pushing, opening a PR, or when a pre-commit hook or CI check has gone red and you need to decide whether to fix, defer, or stop. Terminates at green-awaiting-approval; it never merges.
cleanup
Staleness sweep across durable-claim surfaces — README, agent instruction files, docs, and shared memory — before a retro, before sprint planning, or after a run of merges. Finds claims that reality has moved past, then corrects them, marks them unverified, or retires them.
anonymisation
Binding rule for any content drawing on real client or engagement experience — blog posts, talks, marketing, public case studies. Triggers the moment material moves toward a public surface and references a client, vendor, project, team composition, sector, scale, or timeline.
content-cadence
Pipeline for turning one R&D artefact (PR, PoC, analysis) into one public post — briefing or deep dive — plus a LinkedIn derivative. Triggers when an R&D output is ready to become content, or when drafting any blog post for the site. Enforces the anonymisation gate and repo editorial conventions.
si-quick-check
Detect manipulation and disinformation patterns in spiritual, metaphysical, New Age, guru, channelled, prosperity-gospel, conspirituality, or self-help text, scoring seven dimensions plus a CVP consciousness-topology layer. Use whenever the user asks to quick-check, screen, vet, or analyse a passage for manipulation markers, coercion, red flags, or undue influence — e.g. "quick-check this", "analyse this text for manipulation", "is this spiritual content manipulative?", "run a threat check on this channelled message", "スピリチュアルのテキストを分析して", "この文章を診断", "操作のパターンをチェック". Auto-detects English or Japanese (日本語) input. Produces an approximate 0–100 threat score, a per-dimension table, quoted signals, matched tradition categories, and a CVP structural assessment. Heuristic pattern analysis for human judgement, not a verdict on truth or harm.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.