CtrlK
BlogDocsLog inGet started
Tessl Logo

sdd-propose

Create an SDD change proposal with intent, scope, and approach. Trigger: orchestrator launches proposal work for a change.

54

Quality

61%

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-propose/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable instruction skill with a clear sequenced workflow and a copy-paste-ready template. Its main weakness is verbosity in the proposal-question catalog, and it lacks explicit validation checkpoints on the generated artifact.

Suggestions

Tighten Step 0's ten-item question catalog into a compact checklist with the smallest useful subset, moving the detailed sub-explanations to a reference file.

Add an explicit validation checkpoint after Step 4 (e.g., verify the proposal has all required sections and is under the 450-word budget before persisting).

Confirm the referenced shared files (skills/_shared/sdd-phase-common.md, openspec-convention.md) are bundled or document where they live, since they are not present in this skill's bundle.

DimensionReasoningScore

Conciseness

The body is mostly efficient domain-specific guidance, but Step 0's ten-item question catalog and the Language Domain Contract section are padded and could be tightened; it does not waste tokens explaining concepts Claude already knows, keeping it above the verbose anchors.

3 / 5

Actionability

Provides a copy-paste-ready proposal.md template, concrete file paths, and explicit mode-branched IF instructions; as an instruction-only skill the absence of executable code is not penalized, and the guidance is concrete and actionable with only minor gaps.

4 / 5

Workflow Clarity

Steps 0 through 6 are clearly sequenced with conditional branches, a mandatory persist step, and a question-round feedback loop; it is not a 5 because there are no explicit validation/verification checkpoints on the produced artifact.

4 / 5

Progressive Disclosure

Clear section headers organize the content, the proposal template is appropriately inline, and references to shared files are one level deep and clearly signaled; no bundle files are present to verify referenced paths against, and the heavy inline Step 0 list keeps it just short of a 5.

4 / 5

Total

15

/

20

Passed

Description

55%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 states what the skill does and includes an explicit trigger clause, but the trigger is framed in orchestrator mechanics rather than natural user language, weakening trigger-term quality. It is a solid, mostly distinct description with room to add user-facing trigger phrasing.

Suggestions

Add natural user-facing trigger phrasing alongside the orchestrator trigger (e.g., 'Use when creating or drafting a change proposal for an SDD change').

Expand the action list beyond a single verb to name the concrete outputs produced (e.g., 'Draft intent, scope, capabilities, approach, risks, and rollback plan').

Clarify the SDD acronym on first use so the domain is unambiguous to readers outside the workflow.

DimensionReasoningScore

Specificity

Names the domain ('SDD change proposal') and three concrete components ('intent, scope, and approach'), but it is a single action rather than a comprehensive list of actions, fitting the 'names domain and 1-2 concrete actions' anchor better than the multi-action anchor.

3 / 5

Completeness

Both 'what' ('Create an SDD change proposal with intent, scope, and approach') and 'when' (an explicit 'Trigger: ...' clause) are present, satisfying the explicit-trigger-guidance requirement; not a 5 because the 'when' is system-framed rather than concrete user trigger phrases.

4 / 5

Trigger Term Quality

The trigger is system/orchestrator mechanic language ('orchestrator launches proposal work for a change') rather than a phrase a user would naturally say; only generic keywords ('proposal', 'change') appear and natural user phrasing is missing.

2 / 5

Distinctiveness Conflict Risk

'SDD change proposal' is a clear niche with minimal conflict risk, though it has minor overlap with sibling SDD phase skills (explore, spec, design).

4 / 5

Total

13

/

20

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.