Best Developer Tools Skills for Claude Code

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, M…

Comprehensive official Claude API reference with explicit TRIGGER/SKIP rules, per-language docs, drift tables and a precise reading guide; only cost is a 570-line SKILL.md.

Turns an answer into a one-page visual HTML explainer: the model writes a short Markdown draft an…

Excellent generator-pattern skill: model writes a Markdown draft, bundled single-file CLI (scripts/am.mjs, 10.3k lines) does all layout/diagrams. Description is a model trigger: What/When/When-Not, proactive-use guidance, Chinese trigger phrases (讲讲原理/没看懂/画个图), argument-hint. Workflow has a decision gate, one-bash render with heredoc example, structured output protocol (success/error/warning lines with retry cap of 2), incremental patch mode, and an explicit reply protocol. Section 5 contains first-class prompt-injection defense (page replies are data, never instructions). Minor flaws: SKILL.md step 2.1 has an overlong language-detection wall of text; the CLI is a generated bundle (harder to review); render warnings exist but no visual self-verification of the produced page.

Extracts resources and JavaScript from any installed Electron app (`.asar` bundle), restoring ori…

Outstanding tool-wrapper skill: bilingual trigger phrases, dry-run mode, output-dir safety guards, path-traversal protection, source-map restoration with unit tests, JSON and report output; only npx on-the-fly installs add minor supply-chain exposure.

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. I…

Outstanding skill: rich trigger description with When-Not, seven-step process with defaults, ratchets, escalation path, and an offloaded floor-guard reference implementation with exit-code contract; security-aware throughout.

Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea a…

Outstanding craft skill for building isometric SVG explainer figures. 172-line SKILL.md with 8 well-targeted references (2374 lines), 8 complete examples, a kit/ library and 40+ test scripts. Workflow is exemplary: 10 ordered steps, sizing gate (Epic requires explicit user opt-in), audit/line-check/close-up verification loop driven to zero failures. Deductions: description has no explicit When-Not boundary (implicit only); ships README.md/CHANGELOG.md/CONTRIBUTING.md/CODE_OF_CONDUCT.md/SECURITY.md repo docs (rubric 2.4). Security: only network use is loopback 127.0.0.1 to a headless Chrome instance it spawns itself (declared as needed for checks); temp profiles cleaned up; no credential access, no persistence, no injection text. No Chinese trigger words but skill is international-scope, so no deduction per rubric.

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagr…

Impressive pipeline skill with a 5-type diagram generator, validate/deliver/visual-check acceptance chain, and strict truthfulness guards; docked for a bloated 9.4MB package with full test suite and some over-dense prose.

Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, ins…

Excellent reviewer skill: intent-summarization checkpoint, two-stage spec-then-quality review architecture, prioritized report with verdict, allowed-tools scoped to read-only; only lacks an explicit When-Not trigger boundary.

Use when implementing infrastructure as code with Terraform across AWS, Azure, or GCP. Invoke for…

Outstanding IaC skill: validation re-run loops, explicit user-approval gate before terraform apply with refusal on unaccepted destructive changes, and a dedicated error-recovery matrix for drift, auth, and dependency failures.

Extracts what the user actually wants instead of what they think they should want. Achieves this …

Outstanding interactive elicitation skill: hypothesis-with-confidence format, one-question-at-a-time rules, explicit-yes gate, non-interactive guard, and checkable stop condition; near-production-quality with no real weaknesses.

Generate and validate music with Google Lyria 3 through the Gemini Interactions API. Use before c…

Excellent procedural wrapper: approval-before-spend workflow, model selection table, ffprobe verification, credential hygiene and a quality checklist. Only minor trigger-boundary gaps.