SKILLEMALL.ai
GitHub ↗ RU Sign in

CB claude-api

Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`; user asks for the Claude API, Anthropic SDK, or Managed Agents; user adds/modifies/tunes a Claude feature (caching, thinking, compaction, tool use, batch, files, citations, memory) or model (Opus/Sonnet/Haiku) in a file; questions about prompt caching / cache hit rate in an Anthropic SDK project. SKIP: file imports `openai`/other-provider SDK, filename like `*-openai.py`/`*-generic.py`, provider-neutral code, general programming/ML.

davila7/claude-code-templates Agent Skills author: davila7 MIT 48 files body ≈ 7 982 tokens Open the sourcegithub.com↗ analyzed 6 d ago

Build, debug, and optimize Claude API / Anthropic SDK apps.

As a process B 73/100 · Nearly there — weak spots: running it twice

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
83/100
safety, quality, tests
Safety 60%
86
Quality 40%
78
Run on models
none yet
Process rating
B
73/100
Nearly there
Running it twice w 4
30
Tools and files w 18
60
Steps w 15
60
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 14

✓ No critical or high findings

Medium and low: 14
  • low Secrets in code secret-high-entropy-token go/claude-api.md:348
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Also available: `WebF…ram`, `Memo…ram`, `Tool…ram`, `Tool…ram`.
    quoted
  • low Secrets in code secret-high-entropy-token go/claude-api.md:421
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Other edit types: `Beta…ram`, `Beta…ram`.
    quoted
  • low Secrets in code secret-high-entropy-token php/claude-api.md:375
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    **Server-side tools** (bash, web_search, text_editor, code_execution) are GA and work on both paths — `Anthropic\Messages\Tool…124` / `WebS…209` / `Tool…728` / `Code
    quoted
  • low Secrets in code secret-high-entropy-token php/managed-agents/README.md:46
    High-entropy token-like string (may be an id, hash or a credential)
    use Anthropic\Beta\Agents\Beta…ams;
  • low Secrets in code secret-high-entropy-token php/managed-agents/README.md:54
    High-entropy token-like string (may be an id, hash or a credential)
    Beta…ith(
  • low Secrets in code secret-high-entropy-token php/managed-agents/README.md:294
    High-entropy token-like string (may be an id, hash or a credential)
    use Anthropic\Beta\Agents\Beta…ams;
  • low Secrets in code secret-high-entropy-token php/managed-agents/README.md:311
    High-entropy token-like string (may be an id, hash or a credential)
    Beta…ith(type: 'agen…401'),
  • low Secrets in code secret-high-entropy-token python/claude-api/files-api.md:99
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    file_info = client.beta.files.retrieve_metadata("file…V8w")
    quoted
  • low Secrets in code secret-high-entropy-token python/claude-api/files-api.md:107
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    client.beta.files.delete("file…V8w")
    quoted
  • low Secrets in code secret-high-entropy-token python/claude-api/files-api.md:115
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    file_content = client.beta.files.download("file…V8w")
    quoted
  • low Secrets in code secret-high-entropy-token shared/error-codes.md:39
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "request_id": "req_…7Fy"
    quoted
  • low Secrets in code secret-high-entropy-token shared/managed-agents-api-reference.md:338
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "request_id": "req_…RnE"
    quoted
  • low Secrets in code secret-high-entropy-token typescript/claude-api/files-api.md:84
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    await client.beta.files.delete("file…V8w", {
    quoted
  • low Secrets in code secret-high-entropy-token typescript/claude-api/files-api.md:93
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "file…V8w",
    quoted

Files scanned: 48. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7982 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 153, 181, 188, 310, 316): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 73/100

  • 30Running it twice. 29 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Steps. 53 steps, 8 vague phrases
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 7982 tokens
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 5 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +3Description length 744: enough signal without eating the budget
  • +4Structure: 21 headings
  • +3Step-by-step instructions: 53 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.