plan-task

Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task

Quality

68%

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 ./plugins/sdd/skills/plan-task/SKILL.md

Quality

Content

77%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 highly actionable and exceptionally clear in its multi-phase workflow with validation checkpoints, its main weakness is length and repetition across phases plus a monolithic structure that underuses progressive disclosure.

Suggestions

Extract the six per-phase judge prompts and rubrics (and the Model Selection Policy) into reference files under references/, keeping SKILL.md as an overview that links one level deep, to improve progressive disclosure and cut repetition.

Factor the repeated per-phase Decision Logic and "CRITICAL: use prompt exactly as is" notes into a single shared block referenced once, reducing token cost.

Tighten the repeated "the ONLY statement of this rule" phrasing in the Escalation/Iteration sections to a single canonical formulation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and actionable, but repeats identical Decision Logic blocks, "CRITICAL: use prompt exactly as is" notes, and "the ONLY statement of this rule" phrasing across six phases that could be factored out; not a 2 because the core guidance is not padded with concepts Claude already knows.	3 / 5
Actionability	It provides copy-paste-ready agent prompts, exact bash/git commands, a full TodoWrite JSON template, and weighted judge rubrics covering every common case.	5 / 5
Workflow Clarity	Phases are explicitly sequenced with a judge checkpoint and PASS/FAIL/MAX_ITERATIONS decision logic after each, plus retry and escalation feedback loops and a synchronization point for the parallel phases.	5 / 5
Progressive Disclosure	No bundle files exist, and the monolithic ~1300-line body inlines six detailed judge prompts/rubrics and the full Model Selection Policy that could live in one-level-deep reference files; structure is good with clear section headers and a workflow diagram, but content that should be separate is inline.	3 / 5
	Total	16 / 20 Passed

Description

58%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 states concrete capabilities clearly but omits any explicit "Use when..." trigger guidance, which caps completeness. It is specific and largely distinct from other skills.

Suggestions

Add a "Use when ..." clause naming concrete triggers (e.g., "Use when refining a draft task from /add-task, or when the user asks to plan, parallelize, or add verification rubrics to a task spec").

Include natural synonyms and the file pattern users reference, e.g. "plan a task", "task spec", ".specs/tasks/draft/*.md", to widen trigger coverage.

Mention the promote/draft-to-todo outcome alongside refine/parallelize/verify for more comprehensive capability coverage.

Dimension	Reasoning	Score
Specificity	Three concrete actions are named ("Refine, parallelize, and verify") on a defined object ("draft task specification"), matching the anchor for several specific actions with minor gaps; not a 5 because coverage omits decompose/promote.	4 / 5
Completeness	The "what" is clear, but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Relevant terms like "draft task specification", "implementation-ready", "parallelize", and "verify" appear, but common natural synonyms ("plan", "spec") and file extensions are absent.	3 / 5
Distinctiveness Conflict Risk	The niche (refining a draft task spec into an implementation-ready task) is fairly distinct with minimal overlap risk; not a 5 only because adjacent planning commands could marginally overlap.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1338 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: NeoLabHQ/context-engineering-kit
Path: plugins/sdd/skills/plan-task/SKILL.md
Commit: 8539779

Reviewed: 5 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.