deepchat-sdd

Use before substantial DeepChat code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes that need a durable spec. Skip trivial style fixes, small localized logic changes, routine docs edits, and simple bugs unless the developer asks for SDD. Classify substantial work into feature SDD, complex-bug issue spec, or architecture SDD; ask before optional GitHub issue sync unless the developer explicitly requested sync.

Quality

100%

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

100%

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 concise, actionable governance skill with concrete paths, artifacts, commands, and a clearly sequenced workflow with explicit checkpoints. It is well organized as a single file with appropriately signaled one-level references.

Dimension	Reasoning	Score
Conciseness	The body is lean and rule-driven with no padding of concepts Claude already knows; every section states constraints and actions directly, matching the lean-and-efficient anchor; not 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	Provides concrete, copy-ready guidance: specific folder paths (docs/features/<goal>/, docs/issues/<goal>/, docs/architecture/<goal>/), named artifacts (spec.md, plan.md, tasks.md), exact commands (pnpm run format/i18n/lint), labels ([feature], [bug]), and 'Closes #NNN'; not 2 because details are complete and executable rather than pseudocode-like.	3 / 3
Workflow Clarity	A clearly sequenced 10-step workflow with explicit gating checkpoints such as 'Resolve every [NEEDS CLARIFICATION] marker before implementation' and 'Run pnpm run format, i18n, lint before handoff', plus a classify/inspect-before-asking loop; not 2 because checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	A single self-contained SKILL.md organized into well-labeled sections with one-level, clearly signaled references (a sibling deepchat-sdd-cleanup skill and a project doc docs/architecture/agent-system.md) and no nested indirection; not 2 because structure and navigation are clean with no inline material that belongs elsewhere.	3 / 3
	Total	12 / 12 Passed

Description

100%

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 precise, third-person description that clearly states what the skill does and when to use it, with concrete actions and natural trigger terms. It is well scoped to the DeepChat SDD workflow and avoids vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions including 'code, configuration, documentation, test, build, feature, issue, refactor, or architecture changes' and 'Classify substantial work into feature SDD, complex-bug issue spec, or architecture SDD', matching the anchor for multiple specific concrete actions; not 2 because the action coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what (classify work, produce a durable spec, optionally sync issues) and when ('Use before substantial ... changes'), with an explicit trigger clause; not 2 because 'when' is stated explicitly rather than merely implied.	3 / 3
Trigger Term Quality	Uses natural terms a developer would say ('code', 'feature', 'issue', 'refactor', 'architecture', 'test', 'build', 'GitHub issue') with good coverage of variations; not 2 because common phrasings are well represented rather than missing.	3 / 3
Distinctiveness Conflict Risk	Narrowly scoped to the DeepChat SDD process with distinct triggers ('durable spec', 'SDD') and explicit skip conditions, making it unlikely to fire for unrelated skills; not 2 because the niche is clearly bounded rather than overlapping.	3 / 3
	Total	12 / 12 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: b8dbc89

Reviewed: about 7 hours 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.