Pull account data from Telegram (pushed from another Mac). Triggered by "pull accounts", "pull", "sync accounts".
Score 80/100
Fast-tracks small tasks into a ready-to-use prompt pack in one command. Skips discover, generates an ephemeral spec in memory, and outputs a prompt pack with embedded patterns.
Score 80/100
Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list…
Score 80/100
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
Score 80/100
Score and order items by user-specified criteria. Reads items from prior primitive output in context. Keywords: sort, score, prioritize, order, compare, evaluate, weight.
Score 80/100
Read raw content of a GitHub gist from a URL or gist ID. Use when user shares a gist.github.com link, asks to read a gist, or references a gist ID.
Score 80/100
Read full text of an X/Twitter post from a URL. Use when user shares an x.com or twitter.com link, asks to read a tweet, or needs tweet content extracted.
Score 80/100
Analyze text readability with Flesch-Kincaid, Gunning Fog, SMOG, and other metrics. Returns objective scores with interpretation and recommendations.
Score 80/100
Audit a README against its actual project state. Decomposes README into atomic claims, then verifies each against repo files, configs, code, git history, and live URLs.
Score 80/100
Reapply user modifications to reference/ files after a plugin update. Detects customizations via git diff against pristine baseline.
Score 80/100
Validates git rebase correctness using a five-layer pipeline (range-diff, sem, weave, jscpd, tests). This skill should be used after completing a git rebase (especially stacked…
Score 80/100
Reclaim a stuck loop from a dead or unresponsive owner. Check reclaim candidacy, prompt confirmation, atomically take ownership and increment generation.
Score 80/100
Reconcile accounts by comparing GL balances to subledgers, bank statements, or third-party data. Use when performing bank reconciliations, GL-to-subledger recs, intercompany…
Score 80/100
Start terminal recording with asciinema. TRIGGERS - record session, capture terminal, start recording.
Score 80/100
Polish screen recordings with Recordly (open-source Screen Studio alternative) — auto-zooms, cursor animations, webcam overlays, styled backgrounds, timeline editing.
Score 80/100
Add a repo to the .reference/ folder for study — either shallow-clone a GitHub repo or symlink a local path.
Score 80/100
Recommend the best providers for a specific development use case, including plain asks like cheap hosting, best value auth, free-tier database, or good email service for a SaaS.
Score 80/100
Use when the user has an existing draft, text, code, or artifact and wants it iteratively improved through multi-model critique and weaving across multiple passes.
Score 80/100
Stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations.
Score 80/100
Control the silence-reminder nudge. Fires once when no send happens within N seconds; resets on next send.
Score 80/100
Feature remover: traces full dependency graph via /tracing, builds a surgical removal plan (DELETE/EDIT/ADAPT classification), executes removal along critical path only, adapts…
Score 80/100
Reorganize code file structure: rearrange modules, extract reuse, remove redundancy, add section comments. Preserves all functionality and logic.
Score 80/100
Full re-pair of a stale airc mesh — `teardown --flush` + reconnect using the saved invite string. Use when your sends silently fail or `resume` reports stale auth.
Score 80/100
Audit and harden repository profile, community health, discoverability metadata, and contribution surfaces across repos using bounded, evidence-based checks.
Score 80/100
Classify a repository by app type and route it to the correct standards branch, policy profile, and verification gates.
Score 80/100
Enforce file organization, naming conventions, and app-type-specific project layouts. Use when creating, restructuring, or onboarding a repository.
Score 80/100
Adaptive-depth requirements analysis for AIDLC Inception. Simple features produce a 1-paragraph brief; complex features produce structured REQ-001/REQ-002 functional and…
Score 80/100
Restore saved work progress from .bdk/save-progress/ to resume a previous session. Loads referenced plans, creates TaskList items for remaining work.
Score 80/100
AUTO-TRIGGER: Apply this skill automatically when the user pastes or shares a job posting, job description, or any role they are considering applying for.
Score 80/100
Reverse brainstorm, make it worse, flip the problem, opposite approach. Ask "How could this get worse?" then invert answers into solutions.
Score 80/100
Audit and fix CLAUDE.md files using a tiered binary checklist based on official Anthropic best practices and community guidelines.
Score 80/100
Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis.
Score 80/100
Review codebase conventions — a specific domain or all domains in parallel. Use when asked to review or check conventions.
Score 80/100
Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree.
Score 80/100
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
Score 80/100
Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions
Score 80/100
Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree.
Score 80/100
Review a PR, branch or file path and recommend the highest ROI improvement opportunities. TRIGGER when the user asks if the code is ready, looks good, or is otherwise complete.
Score 80/100
Reviews GitHub pull requests for the Medusa repository. Checks PR template compliance, contribution guidelines, code conventions, and community contribution limits.
Score 80/100
Revisão de código abrangente: qualidade + compliance + segurança. Classifica achados por severidade. Combina revisão de código genérica com validação de domínio regulado.
Score 80/100
Construction 단계 실행 직전, Inception 아티팩트와 설계 문서를 교차 분석하여 12개 카테고리 기반 위험 체크포인트를 탐지한다. 비즈니스 연속성·보안·외부 통합·데이터 일관성·비용·성능·규제·가용성·장애 전파 반경·운영 복잡도·의존성 취약점·롤백 가능성을 각각 PASS/WARN/BLOCK으로 판정하고…
Score 80/100
RM-ODP 全6スキル（5 Viewpoint + Correspondence）をオーケストレーションする統合ワークフロー。 業務シナリオから Enterprise → Information → Computational → Engineering → Technology → Correspondence…
Score 80/100
Pipeline retrospective — evaluate the completed pipeline against Anthropic's 9 harness principles.
Score 80/100
Generate Rocaille-style domain warping shaders, mouse-reactive liquid logo effects, depth-map parallax heroes (Astryx-style hover-reactive statues), and stable fluid simulations…
Score 80/100
Execute operational tasks after validated implementation: runtime controls, git/PR/release flow, and governance checks.
Score 80/100
Orchestrate single-thread baton handoff across Manager -> Collaborator -> Admin -> Consultant with explicit entry/exit contracts.
Score 80/100
Implement scoped changes and produce validation evidence matching manager-defined gates.
Score 80/100
Perform independent post-execution critique, risk scoring, and recommendation synthesis without changing implementation scope.
Score 80/100
Define scope, constraints, acceptance criteria, and verification gates before implementation begins.
Score 80/100
Scaffold and clean up rough meeting notes in a vault's scratchpad/. Two modes — prep (creates a pre-meeting template from a short brief) and cleanup (reads a rough dump, asks…
Score 80/100
Run the full data science pipeline: validate raw data, preprocess, engineer features, train model, and evaluate.
Score 80/100
Create or update an operational runbook for a recurring task or procedure. Use when documenting a task that on-call or ops needs to run repeatably, turning tribal knowledge into…
Score 80/100
Save current work progress to .bdk/save-progress/ for resuming in a future session. Use when context is large, work is in progress, and you want to stop and continue later.
Score 80/100
SCAMPER, modify this concept, improve this idea, systematic improvement. Systematically explore modifications via 7 lenses: Substitute, Combine, Adapt, Modify, Put to other use,…
Score 80/100
Re-scan the codebase and refresh existing VibeFlow project contexts with current state.
Score 80/100
Scan a peer agent's content for quality issues — PSQ safety, vocabulary drift, fair witness violations — and write structured findings to transport session.
Score 80/100
Get optimal posting times and schedule content for X. Use when the user asks when to post, wants scheduling advice, or wants to queue up content at optimal times.
Score 80/100
Add schema, structured data, JSON-LD, rich snippets, schema markup, generate schema. Generates valid JSON-LD, validates existing markup, and identifies missing schema…
Score 80/100
Genera il documento preventivo su Google Docs partendo da template Becreatives e informazioni del progetto. Usare dopo la stima o con informazioni pronte.
Score 80/100
Search across all connected sources in one query. Trigger with "find that doc about...", "what did we decide on...", "where was the conversation about...", or when looking for a…
Score 80/100