best-practices — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited best-practices (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
The user's argument may be a question or an imperative. Imperatives ("refine X", "set up Y") determine what Phase 2 does, not whether Phase 1 happens. Phase 1 always runs.
Red flags indicating you are about to skip research:
| Thought | Reality |
|---|---|
| "I already know this" | Training data goes stale. Config keys get renamed, APIs get deprecated. |
| "The user said to act" | The imperative scopes Phase 2, it does not eliminate Phase 1. |
| "This is a simple lookup" | A 30-second search costs nothing. A wrong recommendation costs a debugging round-trip. |
Break the topic into 2-4 specific queries targeting distinct aspects (libraries, patterns, configuration, pitfalls). For single-library lookups, call find-docs or WebSearch directly without subagents.
Dispatch one subagent per query in a single message so they run in parallel. Each uses find-docs (Context7) and WebSearch. Be concrete in each subagent prompt: pass library names, version constraints, and the user's specific context. Vague prompts produce vague results.
<subagent_prompt_template> <context> The user wants to [user's task]. We need the latest, authoritative guidance on [specific aspect]. </context>
<task> Research best practices for: [specific query]
Use the find-docs skill to look up [library/tool] documentation, then use WebSearch to find recent guides and recommendations for "[specific search query]". </task>
<output_format> Report in under 300 words. Include:
If you cannot find authoritative guidance on a point, say so explicitly rather than guessing. </output_format> </subagent_prompt_template>
Phase check: If no research results have arrived yet, STOP. You are still in Phase 1. Go back to step 2.
After all subagents return, merge using these criteria:
If a subagent failed or returned empty, note the gap and proceed with the results you have. Do not block synthesis waiting for a straggler.
Deliver to the user in this structure:
find-docs fails with quota errors, fall back to WebSearch only and note the limitation.find-docs and WebSearch fail, say so explicitly rather than falling back to training data.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.