speckit-tasks

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/speckit-tasks/SKILL.md

Quality

Content

71%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 body is a strong, highly actionable procedural skill: concrete commands, template paths, and an exemplary correct/incorrect format spec with validation steps. Its main weaknesses are the duplicated extension-hook protocol (hurting both conciseness and progressive disclosure) and a few unhandled failure branches in the workflow. Moving the hook rules into a references/hooks.md file and stating fallback behavior for missing prerequisites would bring it to the top band.

Suggestions

Extract the extension-hook protocol (parsing .specify/extensions.yml, enabled/optional/condition handling, slash-command construction) into a single referenced file (e.g. references/extension-hooks.md) and cite it once, eliminating the near-verbatim duplication between Pre-Execution Checks and Outline step 6.

Add explicit failure handling in the workflow: what to do if check-prerequisites.ps1 fails or plan.md/spec.md are missing from FEATURE_DIR.

Trim the enumerated sub-bullets in Outline steps 2-5 that restate information already covered in the Task Generation Rules section.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural instruction with no padding or explanations of concepts Claude already knows, but the ~30-line extension-hook protocol is duplicated almost verbatim in 'Pre-Execution Checks' and again in Outline step 6 (lines 24-55 vs 98-126). That is a sizeable unnecessary repetition keeping it at anchor 3 ('mostly efficient but some unnecessary content that could be tightened') rather than 4.	3 / 5
Actionability	The guidance is fully executable: an exact command ('Run .specify/scripts/powershell/check-prerequisites.ps1 -Json from repo root'), a concrete template path ('.specify/templates/tasks-template.md'), a strict task checklist format with ID/parallel/story-label rules, and four correct plus four incorrect worked examples of the format. This matches anchor 5 ('fully executable; copy-paste ready; specific examples cover the common cases').	5 / 5
Workflow Clarity	The sequence is explicit and numbered (pre-hooks → prerequisites check → load docs → generate → report → after-hooks) with validation checkpoints ('Validate task completeness', 'Format validation: Confirm ALL tasks follow the checklist format'). It is not a 5 because some checkpoints are implicit or unhandled — e.g., no instruction for what to do when check-prerequisites.ps1 fails or reports missing plan.md — leaving minor validation gaps characteristic of anchor 4.	4 / 5
Progressive Disclosure	The single file is well sectioned, but there are no bundle files (references/, scripts/, assets/ absent), and the ~60 lines of detailed extension-hook protocol — including two near-duplicate copies — are exactly the content that belongs in a one-level-deep reference file. This matches anchor 3 ('some structure but content that should be separate is inline') rather than 4, where most content is appropriately placed.	3 / 5
	Total	15 / 20 Passed

Description

50%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 a clear, single-sentence 'what' but omits any 'when to use' trigger guidance, which caps completeness and weakens trigger-term quality. It is reasonably specific about the deliverable (tasks.md) yet under-sells the skill's concrete capabilities. Adding a 'Use when...' clause with natural trigger phrases (task breakdown, implementation plan, spec-kit tasks) would lift three dimensions at once.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for a task list, task breakdown, or implementation plan for a feature, or runs /speckit-tasks after speckit-spec or speckit-plan.'

Enumerate the key capabilities in the description: 'Generate a dependency-ordered tasks.md organized by user story, with phases, parallel-execution markers, and an MVP scope, from spec.md/plan.md design artifacts.'

Include natural synonyms and artifact names users would mention (spec, plan, user stories, tasks.md, spec-kit) to improve trigger matching and distinctiveness.

Dimension	Reasoning	Score
Specificity	The description names one concrete deliverable — 'Generate an actionable, dependency-ordered tasks.md' — but does not enumerate the component actions the skill actually performs (per-story phases, dependency graphs, parallel execution examples). This matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive') rather than anchor 4, which requires several listed specific actions.	3 / 5
Completeness	The 'what' is clear (generate a dependency-ordered tasks.md from design artifacts), but there is no 'Use when...' clause or any trigger guidance, so completeness is capped at 3 per the rubric guideline. It cannot score 4, which requires both what and a present (even if imperfect) 'when'.	3 / 5
Trigger Term Quality	'tasks.md', 'feature', and 'design artifacts' are relevant keywords, but common natural phrasings users would say ('task list', 'task breakdown', 'spec', 'implementation plan', 'plan.md') are missing. Anchor 3 ('some relevant keywords but missing common variations or synonyms') fits better than 4, which expects good coverage with only a few gaps.	3 / 5
Distinctiveness Conflict Risk	'tasks.md' and the spec-kit context give it some distinctiveness, but 'based on available design artifacts' is generic and the description could overlap with other planning/task-generation or spec-driven skills. Anchor 3 ('somewhat specific but could still overlap with similar skills') is the best fit; it lacks the clear niche trigger phrases of anchor 4.	3 / 5
	Total	12 / 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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: unoplatform/uno
Path: .claude/skills/speckit-tasks/SKILL.md
Commit: e1292e0

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.