CtrlK
BlogDocsLog inGet started
Tessl Logo

unified-taskflow

面向真正复杂任务的重型管理系统,使用 anchor、checkpoint、design、恢复和验收追踪。 仅在用户明确要求使用 unified-taskflow、taskflow、.taskflow,或任务确实需要跨多轮、多文件、多阶段的可恢复记录时使用。 不用于小修、普通优化、普通重构、单个 Skill 小改、日常 bug fix,或 task-mode-router / minimal-implementation 已足够处理的任务。

69

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

Highly actionable, well-sequenced content with explicit validation checkpoints and an exemplary one-level-deep reference structure. The sole weakness is moderate redundancy from restating the same core rules in three places.

Suggestions

Consolidate the cross-stage reasoning, Phase 0, anchor immutability, and 3-strike rules into a single canonical location, and have the anti-patterns table reference them rather than restate them, to cut redundant tokens.

The top CAUTION '核心规则' box and the '触发判断' section overlap on the 'don't流程化普通任务' rule; keep one as the trigger gate and trim the other to a pointer.

DimensionReasoningScore

Conciseness

Content is dense and does not explain concepts Claude already knows, but core rules (no cross-stage reasoning, no Phase 0 skip, anchor immutability, 3-strike) are restated across the top CAUTION box, the trigger/workflow sections, and the anti-patterns table, which could be tightened.

3 / 5

Actionability

Provides copy-paste executable validation commands, exact CLI behavior boundaries (--project-path, --json, --help exit 0, path-component rules), and concrete checkpoint/anchor field specs with referenced templates.

5 / 5

Workflow Clarity

Phase 0 → Elastic Execution → Completion is clearly sequenced with explicit validation gates (完备性门禁, re-grounding against Done-when, validate commands) and a 3-Strike→DEADBAND feedback loop with checklists in the anti-patterns table.

5 / 5

Progressive Disclosure

A lean overview with a 按需加载 section and a 引用文件 table pointing one level deep to real bundle files (4 references, 3 templates, 2 scripts), all verified to exist, with clear navigation and no nesting.

5 / 5

Total

18

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-scoped description that explicitly states both purpose and trigger conditions, and actively disambiguates from related skills. Its only weakness is that named capabilities are artifact nouns rather than concrete action verbs.

DimensionReasoningScore

Specificity

Names the domain and several concrete capabilities ('anchor、checkpoint、design、恢复和验收追踪'), but these are artifact nouns rather than a comprehensive list of action verbs, leaving minor coverage gaps.

4 / 5

Completeness

Clearly answers both what ('面向真正复杂任务的重型管理系统,使用 anchor、checkpoint、design、恢复和验收追踪') and when with concrete trigger phrases and explicit negative-when guidance.

5 / 5

Trigger Term Quality

Includes explicit natural triggers users would say ('使用 unified-taskflow、taskflow、.taskflow') plus scenario terms ('跨多轮、多文件、多阶段'), but a few common synonyms for long/complex-task workflows are absent.

4 / 5

Distinctiveness Conflict Risk

Defines a clear heavyweight-task niche with distinct name triggers and actively disambiguates from sibling skills ('不用于... task-mode-router / minimal-implementation 已足够处理的任务'), minimizing conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 3 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
ooooooooooooooooooop/personal-ai
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.