CtrlK
BlogDocsLog inGet started
Tessl Logo

sdd-tasks

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

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

77%

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 with concrete templates, exact paths, and a clear validated workflow, but it is somewhat verbose through repeated forecast restatements and relies on inline material that a reference bundle could offload.

Suggestions

De-duplicate the Review Workload Forecast: define the field set once and reference it from the template, rules, and return summary instead of restating all fields each time.

Move the large task-file template and phase-organization guidelines into a references/ file (e.g., TASK_TEMPLATE.md) to improve progressive disclosure and shrink the inline body.

Inline the specific Section A/B/C/D mechanics from sdd-phase-common.md (or confirm that file ships in the bundle) so persistence/retrieval steps are self-contained rather than only referenced.

DimensionReasoningScore

Conciseness

The body is mostly prescriptive, but the Review Workload Forecast is restated four times (template table, rules, plain-text contract, return summary) and the gate/language-domain prose adds length that could be tightened.

2 / 3

Actionability

It supplies copy-paste-ready task file templates, exact artifact paths (sdd/{change-name}/tasks, openspec/changes/{change-name}/tasks.md), an exact plain-text guard contract, and a good/anti-example rules table — concrete and executable.

3 / 3

Workflow Clarity

A clear five-step sequence (Load → Analyze → Write → Persist → Return) is given with a MANDATORY persist checkpoint, RED-test-before-production ordering, and an explicit base-retargeting validation for feature-branch chains.

3 / 3

Progressive Disclosure

Shared-file references (sdd-phase-common.md Sections A–D, openspec-convention.md) are one-level-deep and clearly signaled, but the ~250-line body keeps large templates/tables inline and no reference bundle exists to split them into.

2 / 3

Total

10

/

12

Passed

Description

52%

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 cleanly answers both what and when with an explicit trigger, but its trigger terms are technical jargon rather than natural user language and it is only moderately distinct from sibling SDD phase skills.

Suggestions

Add natural trigger phrasing a user or orchestrator would actually say (e.g., "Use when planning implementation tasks for an SDD change") rather than relying on internal "orchestrator launches task planning" jargon.

List the concrete outputs more specifically (e.g., "produce a phased tasks.md with work-unit PR splits and a 400-line review forecast") to raise specificity.

Differentiate from sibling SDD skills by naming the unique deliverable (task breakdown / tasks.md) versus proposal/spec/design.

DimensionReasoningScore

Specificity

Names the SDD domain and one concrete action ("Break an SDD change into implementation tasks") but lists no further specific actions, matching the anchor that names a domain and some actions without being comprehensive.

2 / 3

Completeness

It explicitly states both what it does ("Break an SDD change into implementation tasks") and when via an explicit trigger clause ("Trigger: orchestrator launches task planning for a change"), satisfying both what and when.

3 / 3

Trigger Term Quality

The trigger phrase "orchestrator launches task planning for a change" is internal jargon a user would not naturally say; the skill is also delegate-only/user-invocable:false, so it lacks natural user keywords.

1 / 3

Distinctiveness Conflict Risk

The SDD task-breakdown niche is somewhat specific, but the description could still overlap with sibling SDD phase skills (proposal, spec, design, apply) since nothing strongly differentiates it from them.

2 / 3

Total

8

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

Total

15

/

16

Passed

Repository
Gentleman-Programming/gentle-ai
Reviewed

Table of Contents

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.