unified-taskflow
【强制】复杂任务管理系统。 AI 必须在遇到以下情况时**先读取此 SKILL.md**，再执行任何操作： - 多文件变更、规划设计、新功能开发 - 用户说"帮我想想/重构/升级/实现" 禁止使用内置 agentic_mode 的 artifact 目录处理复杂任务，必须使用项目根目录下的 .taskflow/ 目录。
Install with Tessl CLI
npx tessl i github:ooooooooooooooooooop/skills --skill unified-taskflow77
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
50%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description identifies when to use the skill but fails to clearly explain what concrete actions it performs. The mandatory/prohibition language ('【强制】', '禁止') focuses on implementation constraints rather than capabilities. The trigger terms are helpful but the overall description lacks the specificity needed to distinguish it from other planning or task management skills.
Suggestions
Add specific concrete actions the skill performs (e.g., 'Creates task breakdown files, tracks progress in .taskflow/ directory, manages dependencies between subtasks')
Expand trigger terms with more natural user phrases and include English equivalents if the skill should trigger for bilingual users
Reframe the prohibition statement as a positive capability description - explain what the .taskflow/ system does rather than what it replaces
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (complex task management) and mentions some actions like 'multi-file changes, planning design, new feature development', but lacks concrete specific actions like 'create task files, track dependencies, generate progress reports'. | 2 / 3 |
Completeness | Has a 'when' clause listing trigger scenarios (multi-file changes, planning, user phrases), but the 'what' is weak - '复杂任务管理系统' (complex task management system) doesn't explain what the skill actually does beyond managing tasks. The prohibition statement adds implementation details but not capability description. | 2 / 3 |
Trigger Term Quality | Includes some natural Chinese trigger terms users might say ('帮我想想/重构/升级/实现' - help me think/refactor/upgrade/implement), but missing common variations and the technical terms like 'taskflow' or '.taskflow/' are not natural user language. | 2 / 3 |
Distinctiveness Conflict Risk | The '.taskflow/' directory reference and prohibition against 'agentic_mode artifact' provide some distinctiveness, but 'complex task management' and triggers like 'refactor/upgrade/implement' could easily overlap with general coding or project management skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured task management skill with excellent workflow clarity and progressive disclosure. The content efficiently communicates complex multi-phase processes with clear validation checkpoints and anti-patterns. The main weakness is the lack of inline executable examples, relying instead on external templates.
Suggestions
Add a minimal inline example of what an anchor.md entry looks like rather than only referencing the template file
Include a concrete checkpoint.md update example showing the Re-grounding逐项核对 format in action
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and structured sections to convey complex workflow rules without unnecessary explanation. Every section serves a purpose and assumes Claude's competence in understanding task management concepts. | 3 / 3 |
Actionability | While the workflow phases and protocols are clearly defined with specific rules, the content lacks executable code examples. The guidance is concrete but relies on templates and reference files rather than providing copy-paste ready implementations inline. | 2 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear phases (Phase 0 → Execution → Completion), explicit validation checkpoints (Re-grounding, 3-Strike Protocol), and well-defined trigger events. The checkpoint protocol includes specific feedback loops for error recovery. | 3 / 3 |
Progressive Disclosure | Exemplary progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to detailed materials (phase0-clarification.md, governance.md, etc.). The '按需加载' section explicitly guides when to load each reference file. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.