Index of every page on this site: llms.txt
All skills
mvanhorn avatar

/printing-press

@9e1a8d4
Run it yourself

Set up a new integration, connector, or CLI binding for any API. Wrap or generate a ship-ready Go CLI from an OpenAPI, HAR, or Postman spec via the lean research -> generate -> build -> shipcheck loop. Use when the user says build a CLI, wrap this API, set up a new integration, add a connector, integrate with a service, or names an API by domain.

Use this Skill: https://skilld.dev/gh/mvanhorn/cli-printing-press/printing-press

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencescrowd-sniff.md

≈707 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Crowd-Sniff Implementation

When to read: This file is referenced by Phase 1.8 of the printing-press skill. Read it when the user approves crowd-sniff (mining npm SDKs and GitHub code search).

If user approves crowd-sniff

Ensure the discovery directory exists:

mkdir -p "$DISCOVERY_DIR"

Run the crowd-sniff command and capture both the spec and JSON provenance:

cli-printing-press crowd-sniff --api <api> --output "$RESEARCH_DIR/<api>-crowd-spec.yaml" --json > "$DISCOVERY_DIR/crowd-sniff-provenance.json"

If the API has a known base URL from Phase 1 research, pass it:

cli-printing-press crowd-sniff --api <api> --base-url <known-base-url> --output "$RESEARCH_DIR/<api>-crowd-spec.yaml" --json > "$DISCOVERY_DIR/crowd-sniff-provenance.json"

Report the results: "Crowd-sniff discovered N endpoints across M resources (X from npm, Y from GitHub)."

Feed into Phase 2:

  • Enrichment mode: Phase 2 will use --spec <original> --spec <crowd-spec> --name <api> to merge both
  • Primary mode: Phase 2 will use --spec <crowd-spec> directly
Write crowd-sniff discovery report

Write a structured crowd-sniff provenance report to $DISCOVERY_DIR/crowd-browser-sniff-report.md. This report preserves the discovery evidence so a future maintainer can see what community sources informed the spec.

The report must contain these sections:

  1. npm Packages Analyzed — List each SDK package examined: name, version, download count, recency. Note which packages yielded endpoints and which were empty/irrelevant.

  2. GitHub Repos Searched — The search queries used, repos matched, and freshness of each repo. Note the GitHub token status (authenticated with broader results, or unauthenticated with rate-limited results).

  3. Endpoints Discovered — A markdown table with columns: Method, Path, Source Tier (official-sdk / community-sdk / code-search), Source Count (seen in N independent sources). Sorted by source tier then frequency.

  4. Base URL Resolution — Candidates discovered and which was selected, with rationale (e.g., "Found in 3 npm packages: https://api.notion.com").

  5. Auth Patterns Detected — Authentication patterns found in SDK code (API key headers, bearer tokens, OAuth flows). Include the header name or env variable convention when visible.

  6. Parameter Name Evidence — SDK argument names, wrapper function names, examples, form labels, or source comments that clarify cryptic wire keys. Preserve endpoint-local evidence so spec enrichment can author flag_name without guessing.

  7. Coverage Summary — Total endpoints found, breakdown by source tier, and any gaps compared to the Phase 1 research brief (e.g., "Brief mentions webhooks but no webhook endpoints found in community code").

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

2 warningstoday3 checks · Risk SAFE
  • Gen Agent Trust Hubtoday

    The skill is a professional-grade development tool for generating Go-based CLIs from API specifications. It implements extensive security controls, including mandatory secret redaction, automated PII scrubbing, and dedicated code review phases that audit generated source code for security and correctness before execution.

  • Sockettoday

    3 alerts: gptAnomaly, gptSecurity

  • Snyktoday

    Risk: MEDIUM · 3 issues

Signed by skilld at 9e1a8d4. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 20 hours ago.

Activeupdated 2 weeks ago
What it can do
Runs commands Reads files Edits files Network
version
3.0.0
min-binary-version
4.35.4
created_by
user
All 10 allowed tools
BashReadWriteEditGlobGrepWebFetchWebSearchAskUserQuestionAgent

README badge

README badge for mvanhorn/cli-printing-press/printing-press