The package manager for agent skills and context

Versioned, evaluated skills and context for agentic software development

npx tessl search

Evaluate skill

Featured skills

Install our featured skills or any skill from GitHub with Tessl package manager.

80%

anthropics/skills

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

100%

anthropics/skills

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

92%

huggingface/skills

hugging-face-cli

Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.

99%

projectbluefin/dakota

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

80%

anthropics/skills

pdf

100%

anthropics/skills

webapp-testing

92%

huggingface/skills

hugging-face-cli

99%

projectbluefin/dakota

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

Top performing skills & tiles

Discover more

Tessl analyses skills and tiles for their impact on agent success.

Invalid

devbooks-knife

devbooks-knife：把 Epic 级需求切成可拓扑排序的 Slice 队列，并落盘机读 Knife Plan（用于高风险/史诗级变更的 G3 强制闸门）。

SKILL

Invalid

devbooks-implementation-plan

devbooks-implementation-plan：从设计文档推导编码计划（tasks.md），输出可跟踪的主线计划/临时计划/断点区，并绑定验收锚点。用户说"写编码计划/Implementation Plan/tasks.md/任务拆解/并行拆分/里程碑/验收锚点"等时使用。

SKILL

Invalid

devbooks-impact-analysis

devbooks-impact-analysis：跨模块/跨文件/对外契约变更前做影响分析，产出可直接写入 proposal.md 的 Impact 部分（Scope/Impacts/Risks/Minimal Diff/Open Questions）。用户说"做影响分析/改动面控制/引用查找/受影响模块/兼容性风险"等时使用。

SKILL

Invalid

devbooks-entropy-monitor

devbooks-entropy-monitor：定期采集系统熵度量（结构熵/变更熵/测试熵/依赖熵），生成量化报告，当指标超阈值时建议重构。用户说"熵度量/复杂度趋势/重构预警/代码健康/技术债务度量"等时使用。

SKILL

Invalid

devbooks-docs-consistency

devbooks-docs-consistency：检查并维护项目文档与代码的一致性，支持增量扫描、自定义规则与完备性检查。可在变更包内按需运行或全局检查。旧名称 devbooks-docs-sync 保留为别名并输出弃用提示。

SKILL

Invalid

devbooks-design-doc

devbooks-design-doc：产出变更包的设计文档（design.md），只写 What/Constraints 与 AC-xxx，不写实现步骤。用户说"写设计文档/Design Doc/架构设计/约束/验收标准/AC/C4 Delta"等时使用。

SKILL

Invalid

devbooks-delivery-workflow

devbooks-delivery-workflow：完整闭环编排器，在支持子 Agent 的 AI 编程工具中调用，自动编排 Proposal→Design→Spec→Plan→Test→Implement→Review→Archive 全流程。用户说"跑一遍闭环/完整交付/从头到尾跑完/自动化变更流程"等时使用。

SKILL

Invalid

devbooks-convergence-audit

devbooks-convergence-audit：以证据优先、声明存疑的原则评估 DevBooks 工作流收敛性，检测"西西弗斯反模式"和"假完成"。主动验证而非信任文档声明。用户说"评估收敛性/检查升级健康度/西西弗斯检测/工作流审计"等时使用。

SKILL

Invalid

devbooks-coder

devbooks-coder：以 Coder 角色严格按 tasks.md 实现功能并跑闸门，禁止修改 tests/，以测试/静态检查为唯一完成判据。用户说"按计划实现/修复测试失败/让闸门全绿/实现任务项/不改测试"，或在 DevBooks apply 阶段以 coder 执行时使用。

SKILL

Invalid

devbooks-archiver

devbooks-archiver：归档阶段的唯一入口，负责完整的归档闭环（自动回写→规格合并→文档同步检查→变更包归档移动）。用户说"归档/archive/收尾/闭环/合并到真理"等时使用。

SKILL

Invalid

When Stuck - Problem-Solving Dispatch

Dispatch to the right problem-solving technique based on how you're stuck

SKILL

Invalid

Simplification Cascades

Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z"

SKILL

Can't find what you're looking for? Evaluate a missing skill, or if you're looking for agent context for an open source dependency, request a tile.

Browse by category

View all categories

Find exactly what you need, organized by use case.

Testing & QA

Security & compliance

Documentation generation

Debugging & error handling

API development

Web design

Database management

From our partners

Become a partner

Enterprise-ready skills from trusted publishers.

90%

webapp-testing

SKILL

93%

text-to-speech

Convert text to speech using ElevenLabs voice AI. Use when generating audio from text, creating voiceovers, building voice apps, or synthesizing speech in 74+ languages.

SKILL

84%

↑ 1.79x

cisco/software-security

A software security skill that integrates with Project CodeGuard to help AI coding agents write secure code and prevent common vulnerabilities. Use this skill when writing, reviewing, or modifying code to ensure secure-by-default practices are followed.

SKILLS

86%

terraform-stacks

Comprehensive guide for working with HashiCorp Terraform Stacks. Use when creating, modifying, or validating Terraform Stack configurations (.tfcomponent.hcl, .tfdeploy.hcl files), working with stack components and deployments from local modules, public registry, or private registry sources, managing multi-region or multi-environment infrastructure, or troubleshooting Terraform Stacks syntax and structure.

SKILL

88%

↑ 1.28x

pubnub/pubnub-app-developer

Build real-time applications with PubNub pub/sub messaging

SKILLS

93%

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

SKILL

69%

hugging-face-tool-builder

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process data.

SKILL