⚙️ Operations

okteto/lessons

Verified by SkillsAuth

tools

Record a lesson learned after a user correction, or review existing lessons at session start

nwave-ai/nw-review-workflow

Verified by SkillsAuth

testing

Detailed review process, v2 validation checklist, and scoring methodology for agent definition reviews

nwave-ai/nw-five-whys-methodology

Verified by SkillsAuth

tools

Toyota 5 Whys methodology with multi-causal branching, evidence requirements, and validation techniques

aiskillstore/thinking-partner

Verified by SkillsAuth

tools

思考拍档 - 陪你从混沌中理清局面，锁定核心问题，拆解卡点，共创解法，落地行动

aiskillstore/prescriptive-actions

Verified by SkillsAuth

development

Use when the user asks for recommendations, next steps, best approaches, or “what should I do” guidance to achieve a goal or fix a problem.

nhadaututtheky/memory-intake

Verified by SkillsAuth

tools

Structured memory creation workflow. Converts messy notes, conversations, and unstructured thoughts into well-typed, tagged, confidence-scored memories. Uses 1-question-at-a-time clarification to avoid cognitive overload.

aifinlab/payment-failure-attribution

Verified by SkillsAuth

data-ai

对支付失败交易进行归因分析，识别错误码分布与高频失败模式，辅助故障定位与体验优化

aifinlab/claims-material-check

Verified by SkillsAuth

testing

当用户需要检查理赔材料是否齐全时使用此 skill。适用于理赔申请前材料预审、缺失材料提醒、材料规范性检查等场景。

nowledge-co/working-memory

Verified by SkillsAuth

tools

Load your current context at session start. Shows what you were working on, active priorities, and unresolved flags. Also trigger when resuming after a break or when the user asks what am I working on.

nowledge-co/nowledge-mem

Verified by SkillsAuth

tools

Search, save, and manage knowledge across all your AI tools through Nowledge Mem.

jochenyang/skills-audit

Verified by SkillsAuth

testing

List all installed skills with line counts and analyze for improvement opportunities. Use when user wants to review, optimize, or clean up their skill collection.

alexanys/feishu-mcp

Verified by SkillsAuth

tools

飞书全能 MCP - 创建/编辑文档、插入图表、管理表格、搜索知识库。整合社区版+官方 MCP，适配 Moltbot/Clawdbot。

octavehq/library

Verified by SkillsAuth

development

Browse, search, create, and update Octave library entities (personas, products, segments, competitors, proof points, references) and Motions / Motion Playbooks / Motion ICP cells. Use when user says "show my personas", "list products", "create a competitor", "update this segment", "search the library", "list motions", "show the motion ICP for [persona]", or references any entity type by name.

oduffy-delphi/lessons-trim

Verified by SkillsAuth

documentation

DEPRECATED ALIAS — invokes coordinator:lesson-triage in project-local mode. Periodic maintenance of lessons files (trim stale entries, merge duplicates, clean feature-scoped files). Invoked by /update-docs (Phase 6) or standalone. Removal due 2026-05-26 (one cadence cycle after lesson-triage ship).

nhouseholder/think-efficiently

Verified by SkillsAuth

testing

Prevents wasted tokens — pointless actions, analysis paralysis, redundant work, and disproportionate effort. Always-on efficiency filter.

nhouseholder/skill-manager

Verified by SkillsAuth

tools

Prevents skill overload. Weight class limits, conflict resolution, stack cap at 75. Always-on meta-skill.

murillodutt/cellm/skills/spec-router

Verified by SkillsAuth

development

Passive CellmOS work classifier — routes each action to trivial (just do it), query (research first), or spec (create check in DB) before execution. Activates before non-trivial work to prevent ungoverned changes. Inactive on TRIVIAL work (single file edit under 50 LOC with clear intent), on read-only operations, on conversational turns with no code change, and on already-spec-tracked work where the spec is active.

murillodutt/cellm/skills/mantras

Verified by SkillsAuth

testing

Four CELLM work process mantras as mental gates — verify, best path, document, resolve. Active by default for state-changing actions with non-trivial scope or irreversible side-effects. Trivial actions pass silently.

nicsuzor/eval

Verified by SkillsAuth

testing

Agent session quality assessment — merged into /qa as Agent Session Evaluation mode

nicsuzor/active-loop

Verified by SkillsAuth

tools

Iterative improvement protocol — declare a measurable target, run cycles via /loop, experiment, measure, learn, and accumulate work in a DRAFT PR.