agent-health
Reads production/traces/agent-metrics.jsonl and displays a per-agent performance summary table for the current or a specified session. Highlights agents with…
Grounds framework, library, API, and platform-specific technical decisions in official documentation before implementation. Use when current docs, version-specific behavior, best practices, deprecations, or external API correctness matter.
$ npx -y skills add tranhieutt/software_development_department --skill source-driven-development --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/source-driven-developmentContext preview
The summary Claude sees to decide when to auto-load this skill.
Grounds framework, library, API, and platform-specific technical decisions in official documentation before implementation. Use when current docs, version-specific behavior, best practices, deprecations, or external API correctness matter.
name: source-driven-development type: workflow description: "Grounds framework, library, API, and platform-specific technical decisions in official documentation before implementation. Use when current docs, version-specific behavior, best practices, deprecations, or external API correctness matter." argument-hint: "[framework-library-api-or-technical-decision]" user-invocable: true allowed-tools: Read, Glob, Grep, WebSearch context: fork effort: 3 agent: technical-director when_to_use: "Use whenever a spec, plan, implementation, or review depends on framework/library/API behavior that may vary by version, deprecation status, official guidance, or platform constraints."
`source-driven-development` verifies technical correctness against authoritative external sources. It prevents agents from implementing framework, library, API, or platform patterns from stale memory.
This skill does **not** replace `spec-driven-development`. It verifies the technical decisions inside a spec, plan, or implementation.
spec-driven-development = what we are building and why source-driven-development = whether the technical pattern is correct today
Use this workflow when any decision depends on external technical truth:
state management, migrations, deployment, or testing.
"documented", or "standards-compliant" implementation.
Do not use this workflow for pure product intent, copy changes, simple local logic, naming cleanup, or code whose correctness does not depend on an external versioned source.
Use this as a verification layer:
New feature: spec-driven-development -> source-driven-development if technical docs matter -> planning-and-task-breakdown -> test-driven-development Existing spec: review-spec -> source-driven-development if technical docs matter -> planning-and-task-breakdown Implementation/review conflict: source-driven-development finds docs/spec mismatch -> spec-evolution
If official sources contradict the approved spec, do not silently change the spec or implementation. Route through `spec-evolution` and ask the user to approve the updated path.
Use the strongest available source for the specific decision:
| Priority | Source | | --- | --- | | 1 | Official framework, library, product, or API documentation | | 2 | Official migration guides, release notes, changelogs, or RFCs | | 3 | Official standards bodies or platform references such as MDN/web.dev | | 4 | Runtime compatibility data from maintained compatibility references |
Do not use community posts, Stack Overflow, tutorials, AI summaries, or memory as primary evidence when official sources are available.
State the exact decision being verified:
Decision to verify: <framework/library/API pattern> Why it matters: <risk if wrong> Affected spec/plan/code: <file/section/task if known>
If there is no concrete technical decision, return to `spec-driven-development`, `review-spec`, or `planning-and-task-breakdown`.
Read the smallest relevant files to identify versions and runtime context:
If the version cannot be determined and version affects the answer, ask the user or mark the decision as `UNVERIFIED`.
Use official docs for the specific feature, not a broad homepage. Prefer deep links to the page or section that supports the decision.
Capture:
Classify the result:
`spec-evolution` if the spec was already approved.
present options and ask.
Do not overrule local architecture automatically. If current docs and existing code disagree, surface the tradeoff:
Option A: follow current official docs Option B: match existing project convention Option C: adapt via a compatibility wrapper
For any non-obvious decision, include the evidence in the spec, plan, review, or final response:
## Source Verification **Decision:** [technical pattern] **Stack/version:** [detected version or unknown] **Sources:** [official URLs or local docs] **Result:** CONFIRMED | ADJUST | CONFLICT | UNVERIFIED **Impact:** [spec/plan/code consequence]
If the discovery reveals a durable caveat, use `annotate` to persist it.
| Thought | Required correction | | --- | --- | | "I know this API." | Memory is not evidence. Verify version-sensitive patterns. | | "The docs will take too long." | A wrong framework pattern costs more than a targeted docs check. | | "The spec already says what to use." | Specs can be technically stale; verify external truth when it matters. | | "A popular blog says this is best practice." | Use official sources first. Blogs can inform, not authorize.
Repo: tranhieutt/software_development_department
Reads production/traces/agent-metrics.jsonl and displays a per-agent performance summary table for the current or a specified session. Highlights agents with…
Provides the vendored agent-style v0.3.5 prose rule pack as a portable Claude skill. Use when installing, syncing, applying, or auditing SDD Agent-Style…
Provides Angular best practices for components, modules, services, and reactive patterns. Use when working with Angular TypeScript files, component templates,…
Records unexpected API behaviors, undocumented caveats, version bugs, or non-obvious workarounds into .claude/memory/annotations.md. Use immediately when an…
Defines REST and GraphQL API contracts including endpoints, request/response schemas, auth flows, and versioning strategy. Use when designing a new API,…
Manages the ADR (Architecture Decision Record) registry. Use when recording tech-stack choices, design patterns, or infrastructure decisions with context,…