deepchat-sdd

Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable RFC and an explicit execution path. Skip trivial style fixes, small localized logic changes, routine docs edits, and simple bugs unless the developer asks for SDD. Use plan.md as the only separate tracker when needed, default to implementation-first validation, and ask before optional GitHub issue sync unless the developer explicitly requested sync.

Quality

85%

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

Quality

Content

82%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.

A well-structured, highly actionable process skill with a clear sequenced workflow and concrete commands/paths. Minor redundancy across sections and an implicit rather than explicit validation retry loop keep it just short of top marks.

Dimension	Reasoning	Score
Conciseness	Lean for a process skill and assumes Claude's intelligence (no boilerplate about RFCs or Vue), but the tasks.md prohibition and GitHub issue eligibility rules are each restated across sections and could be tightened.	4 / 5
Actionability	Provides concrete executable guidance throughout: exact folder taxonomy, file names (spec.md/plan.md), labels ([feature]/[bug]), the Closes #NNN PR pattern, and copy-paste commands (pnpm run format/i18n/lint/typecheck).	5 / 5
Workflow Clarity	A clear 13-step sequenced workflow with review and quality-gate checkpoints, but the validate->fix->retry feedback loop is implied rather than stated explicitly for the step-13 checks.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with a single one-level reference to the deepchat-sdd-cleanup skill and no nested references; the GitHub Issue Sync section is sizable enough it could arguably live in its own reference.	4 / 5
	Total	17 / 20 Passed

Description

87%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.

A strong, specific description that clearly states what it does and when to use it, with explicit skip conditions and concrete process actions. Trigger-term coverage is good though a few synonyms are missing.

Dimension	Reasoning	Score
Specificity	Lists several concrete process actions ("durable RFC and an explicit execution path", "Use plan.md as the only separate tracker", "implementation-first validation", gating GitHub issue sync) rather than vague language, but the capabilities are procedural and a few are described at a high level.	4 / 5
Completeness	Explicitly answers both what ("durable RFC and an explicit execution path") and when ("Use before substantial DeepChat ... changes") with concrete trigger phrases plus explicit skip guidance.	5 / 5
Trigger Term Quality	Strong natural-term coverage ("code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes") that a developer would actually say; a few common synonyms (e.g. "bug fix") are absent.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (DeepChat SDD with RFC + plan.md workflow) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ThinkInAIXYZ/deepchat
Path: .agents/skills/deepchat-sdd/SKILL.md
Commit: fa769d4

Reviewed: 2 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.