sdd-tasks

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

Quality

66%

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

70%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 skill delivers a well-sequenced, actionable workflow with strong validation checkpoints and a concrete artifact template. Its weaknesses are token redundancy around the forecast fields and reliance on out-of-bundle references with no progressive file split.

Suggestions

Deduplicate the Review Workload Forecast: keep the exact plain-text guard lines (the contract) and trim the redundant table fields to remove repeated 400-line / chain-strategy / decision entries, improving conciseness.

Either inline the relevant parts of _shared/sdd-phase-common.md (Sections A/C/D) or ship them as bundled reference files under references/ so the skill is self-contained and references are one level deep and verifiable.

Move the full task-file template and phase-organization guidelines into a bundled reference file (e.g., references/tasks-template.md) referenced from SKILL.md to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept-explaining fluff, but the Review Workload Forecast fields appear redundantly in both a table and as exact plain-text guard lines, and the skill is lengthy (~256 lines) for a single-artifact task, so it could be tightened.	3 / 5
Actionability	A full copy-paste tasks.md template, a task-quality table with concrete ✅/❌ examples, exact plain-text guard lines, and per-mode persistence rules give mostly executable guidance; minor gaps are the {placeholder} template fields and dependence on the external _shared/sdd-phase-common.md for Sections A/C/D.	4 / 5
Workflow Clarity	A clear five-step sequence (Load, Analyze, Write, Persist, Return) with a flagged MANDATORY persistence step, validation checkpoints (threat-matrix RED tests before production tasks, forecast guard), and feedback loops (regeneration preserves numbering; ask user on chain strategy) matches the top anchor.	5 / 5
Progressive Disclosure	No bundle files exist, and the referenced files (skills/_shared/sdd-phase-common.md, openspec-convention.md) live outside this skill's bundle and are unverifiable; internal structure is good but the full template and phase guidelines are inlined rather than split into reference files.	3 / 5
	Total	15 / 20 Passed

Description

62%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 purpose and an explicit trigger, but the trigger is framed in internal orchestration jargon rather than natural user language, and it names only one concrete action. Tightening to list specific task-planning actions and a user-facing "Use when…" phrase would raise specificity and completeness.

Suggestions

List 2-3 concrete task-planning actions (e.g., "produce a phased tasks.md, forecast review workload, recommend chained PR splits") to lift specificity from 3 to 4-5.

Reframe the trigger as a natural user-facing phrase ("Use when breaking an SDD change into implementation tasks" or "when planning phased implementation work") to improve trigger term quality.

Add common synonyms/variations (task breakdown, implementation plan, phased task list) so the trigger matches how users actually phrase the request.

Dimension	Reasoning	Score
Specificity	"Break an SDD change into implementation tasks" names the SDD domain and one concrete action (break into tasks), but does not list several specific actions — matching the anchor for naming a domain plus 1-2 concrete actions.	3 / 5
Completeness	Both "what" (break an SDD change into implementation tasks) and "when" (Trigger: orchestrator launches task planning) are explicitly present; the trigger is concrete but operator-internal rather than a user-facing "Use when…" phrase, placing it just below the top anchor.	4 / 5
Trigger Term Quality	"Trigger: orchestrator launches task planning for a change" provides an explicit trigger, but the terms are internal jargon (orchestrator, SDD change) rather than natural user phrases and lack common synonyms or variations.	3 / 5
Distinctiveness Conflict Risk	"SDD change" / "implementation tasks" carves a fairly distinct niche with minimal conflict against unrelated skills, though it could overlap slightly with sibling SDD phase skills.	4 / 5
	Total	14 / 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: 71cf25f

Reviewed: 4 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.