Skip to content

JPeetz/agent-skills / skills/api-backend/social-har-api-connectivity

social-har-api-connectivity

Verified

Use this skill when an agent needs to connect to a social platform's API by prompting the user to pick a platform, driving Chrome to the login page, capturing all network traffic as the user logs in (handling MFA/CAPTCHA), extracting session tokens, and building a reusable posting client. The agent orchestrates; the user handles credentials. Authorized use only.

FileKindSize
CHANGELOG.mdmarkdown925 B
LICENSEother1.0 KB
SKILL.mdskill md4.9 KB
evals/evals.jsonconfig3.3 KB
scripts/chrome_capture_client.pyscript12.3 KB
scripts/har_derive.pyscript3.2 KB

CHANGELOG.md

View on GitHub
# Changelog

All notable changes to the `social-har-api-connectivity` skill.

## [1.0.0] - 2026-08-16
- Initial release.
- Combines HAR-capture API reverse-engineering with social-platform specifics:
  capture → filter → derive → verify → reuse for any social media platform's
  posting/data API.
- Includes `scripts/har_derive.py` — CLI tool that filters a captured HAR to a
  target host + action, prints minimal request shape (method, URL, headers, body),
  redacts tokens, and flags dynamic/expiring values.
- Per-platform guidance for auth, character limits, anti-automation policies, and
  embed verification (from existing `social-platform-api-integration` knowledge).
- Authorized-use guardrails, HAR-as-credential hygiene, and noise-control (live
  record filtering) baked in.
- Cross-agent compatible: any SKILL.md-compatible agent (Claude, Codex, Cursor,
  Gemini CLI, OpenClaw, Hermes Agent, and more).
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexUnverifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall