add-task

creates draft task file in .specs/tasks/draft/ with original user intent

Quality

41%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugins/sdd/skills/add-task/SKILL.md

Quality

Content

64%

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

The skill provides actionable, concrete guidance for creating draft task files with good examples and clear output format. However, it suffers from an internal contradiction (Step 5 references `.specs/tasks/todo/` while constraints mandate `.specs/tasks/draft/`), moderate verbosity with repeated information across sections, and the success criteria largely restates earlier content. The type table and examples are well-done but the document could be more concise.

Suggestions

Fix the contradiction between Step 5 (creates in `.specs/tasks/todo/`) and the constraints/expected output (which reference `.specs/tasks/draft/`) — pick one and be consistent throughout.

Remove the success criteria checklist or significantly trim it, as it mostly restates instructions already given in earlier sections.

Add a concrete command or method for the uniqueness verification step (e.g., `ls .specs/tasks/*/add-validation-login-form.*` or similar).

Trim the 'Analyze Input' section — Claude doesn't need instructions on how to parse a user request or identify task types from context.

Dimension	Reasoning	Score
Conciseness	The skill is moderately verbose. The directory structure explanation (draft/todo/in-progress/done/scratchpad) is repeated implicitly through the document. The type classification table, file naming conventions, and multiple examples are useful but could be tightened. Some sections like 'Analyze Input' explain things Claude can infer. The success criteria checklist largely restates what was already said.	2 / 3
Actionability	The skill provides concrete, executable guidance: a specific bash command to run, exact file naming patterns, a complete markdown template for the task file, and specific output format. The examples are copy-paste ready with real file paths and content.	3 / 3
Workflow Clarity	Steps are clearly numbered and sequenced (1-5), but there's a contradiction: Step 5 says to create in `.specs/tasks/todo/` while constraints say 'Do NOT create files outside `.specs/tasks/draft/`' and the expected output references `.specs/tasks/draft/`. This inconsistency is a significant workflow clarity issue. The uniqueness verification step (check across folders) lacks a concrete command or method.	2 / 3
Progressive Disclosure	The content is well-structured with clear sections and headers, but it's a monolithic document (~150 lines) that could benefit from separating the type classification table and examples into referenced files. No bundle files are provided, so there's no progressive disclosure structure. For a skill of this complexity, inline content is borderline acceptable but slightly long.	2 / 3
	Total	9 / 12 Passed

Description

17%

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 is too terse and internally focused, relying on project-specific path conventions rather than natural language that would help Claude select this skill appropriately. It lacks a 'Use when...' clause and doesn't include trigger terms users would naturally use. The single action described is narrow but not well-explained.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'create a task', 'draft a spec', 'capture requirements', 'new task', or 'plan work'.

Include more natural keywords users would say, such as 'task', 'spec', 'requirement', 'plan', 'ticket', or 'work item'.

Expand the 'what' portion to explain the purpose and content of the draft task file, e.g., 'Captures and structures a user's request into a draft task specification file, preserving original intent and context.'

Dimension	Reasoning	Score
Specificity	It names a specific action ('creates draft task file') and a specific location ('.specs/tasks/draft/'), but only describes one action and doesn't elaborate on what the task file contains beyond 'original user intent'.	2 / 3
Completeness	It partially answers 'what' (creates a draft task file) but has no explicit 'when' clause or trigger guidance. The absence of a 'Use when...' clause caps this at 2 per the rubric, and the 'what' is also weak, so it scores 1.	1 / 3
Trigger Term Quality	The description lacks natural keywords a user would say. Terms like 'draft task file' and '.specs/tasks/draft/' are internal/technical jargon. Users would more likely say 'create a task', 'spec', 'plan', or 'write up requirements'.	1 / 3
Distinctiveness Conflict Risk	The specific file path '.specs/tasks/draft/' provides some distinctiveness, but 'task file' and 'user intent' are vague enough to potentially overlap with other task management or planning skills.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: NeoLabHQ/context-engineering-kit
Commit: 3711edf

Reviewed: 20 days 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.