Crisp
Use this skill when the user wants shorter, more direct responses. Activate on: "crisp mode", "go crisp", "/crisp", "be brief", "less tokens", "cut the fluff", "shorter answers", "stop being verbose", "drop the filler", "skip the pleasantries", "no fluff", "just the answer". Do NOT activate for: "explain in detail", "walk me through", "full report", or any question answerable correctly in one sentence without the skill.
Install
npx skills add shubhamV123/crisp --skill crispgit clone --depth 1 https://github.com/shubhamV123/crisp.git /tmp/crisp
mkdir -p ~/.claude/skills
cp -r /tmp/crisp/. ~/.claude/skills/crispPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Crisp Mode Shortest complete answer. All technical substance stays. Only fluff dies. ## Persistence Active every response once triggered. Survives topic changes and long conversations. Off only when user says: "stop crisp" / "normal mode" / "be more detailed" / "full explanation". Auto-Clarity Exception = temporary suspension only, not deactivation (see below). ## Rules Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/happy to), hedging (it's worth noting/you might consider), conjunctions where removable, restating the user's request. Keep: all technical terms exact, code blocks unchanged, error messages quoted exact, numbers and specifics. Style: fragments OK. Short synonyms (fix not "implement a solution for", use not "utilize"). Causality: X -> Y. One word when one word enough. Abbreviate: DB, auth, authz, config, fn, impl, repo, env, var, dep. No headers. No bullets unless 3+ parallel items that don't flow naturally as prose. Default to shortest complete answer. Expand only if question is ambiguous or multi-part. Pattern: finding -> fix -> next step. Code tasks: prose under 3 lines. ## Auto-Clarity Exception Suspend crisp for: security warnings, irreversible/destructive operations, multi-step sequences where fragment order risks misread. Warning ends after danger stated + command shown. Everything after — tips, checklists, next steps — back to crisp. One line max after warning block. No extra caveats.
Details
- Skill name
crisp- Repository
- shubhamV123/crisp
- License
- MIT
- Repo updated
- 21 May 2026
FAQ
What does the Crisp skill do?
Use this skill when the user wants shorter, more direct responses. Activate on: "crisp mode", "go crisp", "/crisp", "be brief", "less tokens", "cut the fluff", "shorter answers", "stop being verbose", "drop the filler", "skip the pleasantries", "no fluff", "just the answer". Do NOT activate for: "explain in detail", "walk me through", "full report", or any question answerable correctly in one sentence without the skill.
How do I install the Crisp skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add shubhamV123/crisp --skill crisp. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Crisp popular?
It lives in shubhamV123/crisp, which has 20 GitHub stars and 3 forks.
Related skills
Ros2 Skill
20adityakamath/ros2-skill
Use this skill for any ROS 2 robot task: topics (subscribe, publish, capture images, find by type), services (list, call), actions (list, send goals), parameters (get, set, presets), nodes, lifecycle management, controllers (ros2_control), Nav2 navigation (go, rotate, cancel, costmap-clear, waypoints, move-timed, initial-pose), diagnostics, battery, TF frames, bags, logs, and more. Use even if the user doesn't explicitly say 'ROS 2' — if they describe controlling, monitoring, or inspecting a robot, this skill applies. Never tell the user you cannot do something ROS 2-related without checking t
Sgrep
22XiaoConstantine/sgrep
Semantic and hybrid code and conversation search for intent-based queries. Use when exploring unfamiliar codebases, finding code by concept instead of exact text, or recalling past agent conversations about similar problems.
Atlassian CLI
19leweii/atlassian-cli
Use when working with Jira or Confluence from command line, including authentication, searching issues with JQL, bulk operations, sprint reports, or creating/updating work items using acli
Enterprise Architecture
21gauravs19/enterprise-architecture-skill
Unified enterprise & software architecture skill grounded in four open-source standards — C4 + Structurizr DSL, ArchiMate 3.x, TOGAF ADM, and arc42 + ADRs (MADR). Use it whenever the user wants to: produce architecture diagrams as code (C4 context/container/component, Structurizr, PlantUML, Mermaid); write architecture docs or decision records (arc42, ADRs/MADRs, design docs); review or assess a design against quality attributes and EA principles; or model an enterprise (capabilities → applications → technology, app landscapes, portfolio rationalization). Trigger it even when no framework is n
Clean Architecture
20tokenaissance/clean-architecture
Clean Architecture practitioner's guide. Trigger when users ask about four-layer architecture, dependency direction & inversion (DIP), an entity directly depending on external SDKs, ORM/data access layer (Repository pattern) design, microservice decomposition, technology selection, over-engineering, or architecture refactoring. Covers business logic organization in Express/Next.js/Go/Spring projects, MongoDB→PostgreSQL migrate, REST→GraphQL migrate, third-party integration (Stripe/PayPal), Redis caching, and Kafka message queue evaluation. Evaluates architecture against Robert C. Martin's Clea
Codex Delegator
22eddiearc/codex-delegator
Automatically delegate complex, logic-intensive tasks to OpenAI Codex CLI via `codex exec --full-auto`. Claude Code uses this skill to invoke Codex for complex backend logic, intricate algorithms, or persistent bugs. Enables seamless AI-to-AI collaboration where Claude Code analyzes and Codex executes.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.