Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

awrshift

@awrshift source repo

11 published skills

  1. ▌
    Brainstorm · awrshift bundle
    Multi-round brainstorm between Claude and Gemini that turns a single idea into one converged, actionable decision. Use this skill whenever the user wants to brainstorm, ideate, explore strategic options, compare approaches, or think through a decision with multiple viable paths. Also trigger when user says 'brainstorm', 'let's think through options', 'ideation session', 'explore this idea with Gemini', 'brainstorm with Gemini', 'diverge and converge', or wants more than a simple second opinion — a real multi-round dialogue between two top models. This is the upgrade from a single Gemini second-opinion call to a structured 3-round adversarial dialogue.
    0
    installs
  2. ▌
    Claude Friends · awrshift bundle
    Ask AIs from other families to review something before you commit to it. User-triggered, never automatic. Fires when the user signals uncertainty or asks for another perspective: 'ask a friend', 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test this', 'critique this', 'devil's advocate', 'poke holes in this' (one reviewer); 'this is important', 'high-stakes', 'run a full review', 'ask everyone', 'check before I send', 'before publishing', 'boardroom debate', 'don't let me ship something dumb' (the whole table in parallel); 'help me choose', 'brainstorm options', 'I have several paths', 'compare these approaches', 'diverge and converge' (multi-round round-table); 'ask Gemini', 'ask Opus', 'ask GPT' (a named reviewer). Reviewers come from different model families (Gemini, an isolated Claude with no parent context, optionally GPT) so they do not share blind spots; their findings are input, never a vote. Not for factual lookups — use WebSearch.
    0
    installs
  3. ▌
    Telegram · awrshift bundle
    The only Telegram skill your AI agent needs. Read messages, parse channels, download and transcribe voice notes — all via Telethon user API. One session file, zero bots. Use when user says 'read telegram', 'check saved messages', 'fetch from telegram', 'parse channel', 'transcribe voice', 'telegram search', 'check my telegram', or when any agent needs Telegram data. Also trigger on 'what did I save in telegram', 'read my saved messages', 'get messages from channel X', 'download voice notes'. Covers: ad-hoc reading, channel parsing with sanitization, voice/audio download. Requires TG_API_ID, TG_API_HASH env vars and a session file.
    0
    installs
  4. ▌
    Close Session · awrshift
    End-of-session ritual — audit today's patterns against accumulated memory, propose promotions, refresh MEMORY.md, and write the session handoff. Use when the user says "/memory-kit:close-session", "закрой сессию", "закрываем", "we're done for today", "wrap up".
    1
    install
  5. ▌
    Second Opinion · awrshift
    Cross-check the agent's own answer with independent reviewers before bringing it to the user. Use when the user says 'second opinion', 'sanity check', 'cross-check', 'am I missing something', 'stress-test', 'devil's advocate', 'run a full review', 'this is important', 'high-stakes', 'help me choose between', 'critique this', or similar. Three review styles: Devil's Advocate (single critique), Boardroom Debate (parallel multi-reviewer validation), Round-Table (multi-round brainstorm for choosing between paths). Not for factual lookups — use WebSearch for those.
    1
    install
  6. ▌
    Session Review · awrshift
    End-of-session adversarial review loop. Assemble the session's work into a role-assigned, self-contained brief, then run independent reviewers in parallel — an isolated code-reader (the idea-validator agent) that reads the ACTUAL files and web-checks technology currency, plus an external-family model if you have one — synthesize where they agree vs diverge, apply the cheap-safe fixes immediately, record a measurable plan for the rest, and CHALLENGE reviewer claims you disagree with (never blind-accept). Use at the close of a substantive coding or design session, when the user says "session review", "review my session", "stress-test this session", or types /session-review. Skip for trivial one-off edits.
    1
    install
  7. ▌
    Setup · awrshift
    Adopt the Memory Kit in THIS repository — scaffold the memory layers, decide how the kit coexists with Claude Code's native auto memory, and install safe permission rails. Use when the user says "/memory-kit:setup", "set up the memory kit", "adopt the kit here", "настрой кит", or when a session starts in a repo where the kit plugin is installed but no .claude/memory/MEMORY.md exists.
    1
    install
  8. ▌
    QA Sweep · awrshift
    Run a multi-lens agent QA sweep of the RUNNING product: spawn `qa` agents (one per lens — user-flow · edge-state · honesty · contract · ux-critique), collect their structured findings, integrator-verify the load-bearing ones, and land verified findings as backlog tickets + a run record in the project's qa/ folder. Use whenever the user asks to QA, test, or probe the product from the user's side — "qa sweep", "test the UI", "walk the flows", "find inconsistencies", "check how this looks to a client" — and proactively after integrating any large UI slice, before a milestone, or when a manual walk found one bug and siblings are likely. Trigger even when the user names only one angle (e.g. "check the API errors") — pick the matching lens subset. NOT for unit testing (your test suite does that) and NOT a replacement for the integrator's own acceptance walk.
    1
    install
  9. ▌
    Memory Audit · awrshift
    Audit MEMORY.md against the memory discipline — oversized sections, settled multi-session patterns that belong in knowledge/concepts/, stacked chronicle blocks, stale entries. Produces a move plan as a table for approval, then executes the approved moves atomically. Use when the SessionStart hook reports a tripped cap, when PreCompact blocks on an oversized cache, or when the user says "/memory-kit:memory-audit", "audit memory", "проверь память", "почисти память". Refuses only when no cap is tripped AND no settled-pattern candidate exists.
    1
    install
  10. ▌
    System Audit · awrshift bundle
    Periodic evidence-based self-audit of the whole agent system — the orchestrator, its docs/SSOTs, rules, memory, subagents, tools, infra and the work it claims to have delivered — followed by immediate cheap-safe fixes and a ranked backlog. Use when the user says 'аудит системы', 'проверь себя', 'самопроверка', 'system audit', 'audit yourself', 'health check', 'что у нас накопилось', 'система раздулась', 'проверь что работает а что на бумаге', 'gap-анализ', 'что удалить', or on cadence triggers (every ~10 sessions, before a milestone, after a big refactor, when memory hits its caps, when onboarding this repo to a new agent). Seven lenses: delivery reality · knowledge drift · operational layer · layer telemetry (did it ever fire) · tools & infra · domain gaps · anti-bloat subtraction. Not for reviewing a single diff (use a diff-review pass) and not for probing a running product (use /memory-kit:qa-sweep).
    1
    install
  11. ▌
    Tour · awrshift
    Interactive walkthrough of the Memory Kit system using the user's actual project files. Use when the user says "/memory-kit:tour", "give me a tour", "покажи как это работает", or right after /memory-kit:setup.
    0
    installs