sdd-tasks

Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.

Quality

53%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./internal/assets/skills/sdd-tasks/SKILL.md

Quality

Content

62%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 a well-sequenced, actionable instruction skill with concrete templates and guard contracts, though it carries some repetition and relies on shared reference files that are not bundled. It is strong on execution guidance and slightly less lean and modular than ideal.

Suggestions

Move the large task-file template and phase-organization guidelines into a referenced file (e.g., tasks-template.md) to reduce inlined bulk and deepen progressive disclosure.

De-duplicate the Review Workload Forecast (the table and plain-text lines repeat the same fields) so the guard contract appears once.

Add an explicit validate->fix->retry loop for the tasks artifact (e.g., 'if forecast is High, re-split work units until each PR clears the 400-line guard before persisting') to strengthen workflow feedback.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with tight tables and checklists, but the Review Workload Forecast section and chain-strategy explanations repeat guidance and the template restates the plain-text guard lines twice, adding some padding that could be trimmed.	3 / 5
Actionability	It gives concrete, executable guidance via a full task-file template, specific ✅/❌ examples, exact plain-text guard lines, and named persistence paths, with only minor gaps (some placeholders remain template-only).	4 / 5
Workflow Clarity	Five sequenced steps with explicit checkpoints (mandatory persist step, guard contract before apply, decision needed flags) provide a clear validated workflow; it stops short of explicit validate->fix->retry feedback loops for the batch task-writing operation.	4 / 5
Progressive Disclosure	Structure is decent with labeled sections and shared-phase references, but key shared contracts (Section A/B/C/D, sdd-phase-common.md, openspec-convention.md) are referenced without those bundle files present here, and a large inlined template and rules block could live in a separate reference file.	3 / 5
	Total	14 / 20 Passed

Description

43%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 clearly conveys a single concrete action within a specific niche but is light on trigger terms and lacks an explicit user-facing 'Use when' clause. It reads more as an internal delegate instruction than a user-invocable trigger.

Suggestions

Add an explicit 'Use when...' clause with natural user phrasings (e.g., 'Use when breaking a design into implementation tasks or planning a phased delivery').

Expand specificity by listing 2-3 concrete actions (e.g., 'Analyze the design, identify files and dependency order, and produce a phased tasks.md with review workload forecast').

Add common synonyms like 'implementation plan', 'task breakdown', or 'work-unit split' to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The phrase 'Break an SDD change into implementation tasks' names a concrete domain and one action (producing implementation tasks), but lists no granular concrete actions such as analyzing design or writing phases.	3 / 5
Completeness	It states clearly what the skill does but the 'when' is only weakly implied via 'Trigger: orchestrator launches task planning for a change' rather than an explicit 'Use when...' clause aimed at a user, which caps completeness at 3.	3 / 5
Trigger Term Quality	The only natural trigger phrasing is 'task planning', which is a single generic keyword; common user phrasings like 'break down tasks' or 'implementation plan' are largely absent and it leans on internal jargon ('SDD change', 'orchestrator').	2 / 5
Distinctiveness Conflict Risk	The SDD-scoped task planning niche is fairly specific and unlikely to broadly conflict, but it overlaps with adjacent SDD phases (apply, design) and the trigger is orchestrator-driven rather than user-distinguishable, leaving moderate overlap risk.	3 / 5
	Total	11 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: Gentleman-Programming/gentle-ai
Path: internal/assets/skills/sdd-tasks/SKILL.md
Commit: a245f26

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.