Skip to content

sergebulaev/linkedin-skills / .codex-marketplace/linkedin-skills

linkedin-marketing

Verified

Plan, draft, audit, and publish LinkedIn posts and comments. Use when the user wants to write a viral LinkedIn post, draft a comment or reply on any LinkedIn post URL, audit a draft against 2026 algorithm heuristics, remove AI tells, extract hook formulas from viral posts, or plan a week of content. Powered by the Publora API for publishing. User provides post/comment URLs, skill drafts content, user approves, then publishes.

lib/approval.py

View on GitHub
"""Approval gate helpers.

Every skill that posts to LinkedIn MUST present a draft to the user and wait
for explicit approval before calling Publora. This file is a thin conventions
layer, not runtime enforcement — skills should call `render_approval_card`
to format the draft consistently and then stop until the user says go.
"""
from __future__ import annotations
from typing import Optional


def render_approval_card(
    *,
    kind: str,  # "post" | "comment" | "reply" | "reaction"
    preview_text: str,
    target_url: Optional[str] = None,
    reaction_type: Optional[str] = None,
    char_count: Optional[int] = None,
    extra_context: Optional[dict] = None,
) -> str:
    """Format a standardized approval card for the user to review.

    The card MUST contain:
    - What the action is (post / comment / reply / reaction)
    - The full preview text
    - Target URL if applicable
    - A clear prompt: "reply YES to post or suggest edits"
    """
    lines = [f"## Draft ready for approval — {kind}", ""]
    if target_url:
        lines.append(f"**Target:** {target_url}")
    if reaction_type:
        lines.append(f"**Reaction:** `{reaction_type}`")
    if char_count is None:
        char_count = len(preview_text)
    lines.append(f"**Chars:** {char_count}")
    lines.append("")
    lines.append("**Preview:**")
    lines.append("")
    for pl in preview_text.splitlines() or [""]:
        lines.append(f"> {pl}")
    lines.append("")
    if extra_context:
        lines.append("**Context:**")
        for k, v in extra_context.items():
            lines.append(f"- **{k}**: {v}")
        lines.append("")
    lines.append("Reply **post** / **yes** to publish, or suggest edits.")
    return "\n".join(lines)
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall