priority-task-reader

按优先级读取任务 Skill - 从 todos.json 读取 in-progress 和 pending 任务，按 P0-P9 优先级排序

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.trae/openclaw-skills/priority-task-reader/SKILL.md

Quality

Content

50%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.

The content is well-structured and covers the skill's behavior thoroughly with concrete commands and illustrative output examples, but it is anchored to the author's local environment via hardcoded absolute paths and references bundle files (main.py, skill.json) that are not actually included. Redundant restatement of the sorting rules and absent error-handling guidance keep the mid-level scores.

Suggestions

Replace the hardcoded absolute path (cd /Users/bytedance/CS-Notes/...) with a relative path from the skill's own directory, and either ship main.py/skill.json in the bundle (e.g., scripts/) or document their expected location so the commands are executable.

Add brief validation/error handling: what to do when todos.json is missing, empty, or contains invalid priorities — this adds the checkpoints workflow_clarity currently lacks.

Merge the "重要原则" section into "优先级排序规则" and trim the decorative "=" banner lines from the output examples to remove redundancy and padding.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient (short feature list, compact command blocks), but the opening sentence duplicates the frontmatter description verbatim, and the "重要原则" section restates rules already given in "优先级排序规则" ("in-progress 优先于 pending" appears in both); the banner-heavy output examples also add padding.	3 / 5
Actionability	Concrete, flag-documented commands are provided ("python3 main.py --json --next --next-count 5") plus a config example, but every usage command hardcodes the author's machine path ("cd /Users/bytedance/CS-Notes/.trae/openclaw-skills/priority-task-reader") and invokes main.py / skill.json, which are not present in the bundle — so the guidance is not executable as written outside one machine.	3 / 5
Workflow Clarity	The "在推进todo指令中使用" section gives a clear 4-step sequence (call the skill → pick highest priority suitable task → prefer assignee AI with Feedback Required: false → execute in priority order), but no validation checkpoints exist for failure cases (missing/malformed todos.json, empty task list); anchor 3 (sequence present, checkpoints missing) fits, and the read-only nature means the destructive-cap does not apply.	3 / 5
Progressive Disclosure	The body is cleanly sectioned with no nested references, but everything is inlined (long output samples, config block) and it points to main.py and skill.json that do not exist in the bundle (no scripts/ or assets/ directories), leaving navigation to files that aren't shipped.	3 / 5
	Total	12 / 20 Passed

Description

53%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.

The description communicates a concrete, specific capability set (read/filter/sort tasks from todos.json by P0-P9 priority) but entirely lacks "when to use" trigger guidance and natural user phrasing, so it would rarely be surfaced at the right moment. Adding an explicit trigger clause (e.g., "Use when the user says 推进 todo, asks for the next task, or wants a prioritized task list") would lift the two weakest dimensions.

Suggestions

Add an explicit 'Use when...' clause covering natural triggers such as 推进 todo, 查看任务列表, 下一个任务, and prioritized todo sorting — this would raise completeness and trigger_term_quality together.

Include the natural synonyms and file artifact users would mention (todos.json, 任务列表, 下一个任务) so the description matches how users actually phrase the request.

Optionally mention the --next/--json output modes to round out capability coverage and drop the redundant "按优先级读取任务 Skill" prefix.

Dimension	Reasoning	Score
Specificity	The description names the domain (todos.json task reading) and 2-3 concrete actions ("从 todos.json 读取", filtering "in-progress 和 pending 任务", "按 P0-P9 优先级排序"), but omits half the skill's capabilities (grouping, next-task selection, JSON output), and the "按优先级读取任务 Skill" prefix is filler.	3 / 5
Completeness	The "what" is concrete (read, filter, and sort tasks from todos.json) but there is no "Use when..." clause or equivalent trigger guidance anywhere in the description, which caps completeness at 3 per the judging guidelines; the "when" is only weakly implied.	3 / 5
Trigger Term Quality	Real artifact keywords are present ("todos.json", "in-progress", "pending", "P0-P9", "优先级"), but the natural phrases a user would actually say ("任务列表", "下一个任务", "推进 todo") are missing — "推进todo" appears only in the body, never in the description.	3 / 5
Distinctiveness Conflict Risk	The todos.json / P0-P9 priority domain is specific and largely distinguishable from other skills, with only minor overlap risk against generic task-management skills; no explicit distinct triggers are given, so it falls short of anchor 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: huangruiteng/CS-Notes
Path: .trae/openclaw-skills/priority-task-reader/SKILL.md
Commit: 77c775d

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.