authenticity-pass

Solid

Pre-publish human-signal gate for social media drafts. Use when /linkedin or /x-com is about to publish a post, or when asked to run an authenticity check on any draft file.

AI & Automation 20 stars 11 forks Updated yesterday GPL-3.0

Install

View on GitHub

Quality Score: 77/100

Stars 20%
44
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Authenticity Pass A mandatory pre-publish gate. Reads the draft, scores it against three human-signal markers, and returns a structured PASS or BLOCK verdict with specific remediation. The cold-reader loop (in `/linkedin` and `/x-com`) handles style, register, and audience fit. This gate handles one thing only: does this content carry signal that proves a human with real experience wrote it? ## Input **Called by `/linkedin`:** reads `/tmp/linkedin-post.txt` **Called by `/x-com`:** reads `/tmp/x-post.txt` **Called directly:** reads the file path given as argument, or prompts if none. If the file doesn't exist or is empty, return BLOCK with reason "no draft found." --- ## The three human-signal markers ### 1. METRIC A specific, defensible number. Vague intensifiers don't count. | COUNTS | DOES NOT COUNT | |--------|----------------| | "8s → 600ms" | "significantly faster" | | "412 restarts in a week" | "restarted many times" | | "30% fewer impressions" | "fewer impressions" | | "200 to 3,000 followers in 4 months" | "huge growth" | | "$53k per violation" | "large fines" | | "5 hours/week" | "a few hours" | ### 2. CONSTRAINT An acknowledged limitation, failure, or honest tradeoff. The post must admit something didn't work, costs something, only applies under conditions, or was a hard call. | COUNTS | DOES NOT COUNT | |--------|----------------| | "broke in prod until we added X" | pure success framing | | "only works if Y is true" | "works great" | | "costs 3× more ...

Details

Author
tomcounsell
Repository
tomcounsell/ai
Created
5 years ago
Last Updated
yesterday
Language
Python
License
GPL-3.0

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

linkedin-post-performance-critic

Cold-read a LinkedIn post draft and audit it across 6 dimensions (hook, structure, scannability, specificity, CTA, voice). Returns a score per dimension, the 2 most important fixes, and a rewrite of the weakest section. Use BEFORE publishing, when the user wants a sanity check from a critic that does not love everything they write. Requires the Taplio MCP, which reads the user's real voice, audience, and niche benchmarks to ground the audit instead of guessing.

5 Updated 1 weeks ago
TaplioOfficial
AI & Automation Solid

linkedin-post-writer

Draft a new LinkedIn post from scratch using one of 16 2026 hook formulas (anaphora, R.I.P., year-pivot, time-anchor, curiosity-gap, contrarian, emotional cold-open, named-gratitude, and more), picked by engagement goal (comments, reposts, likes, saves). Runs the humanizer pass and schedules via Publora on approval. Use when the user asks to write a post, needs a hook, or wants a proven format. Not for reviewing existing drafts (use linkedin-humanizer --mode audit).

449 Updated 5 days ago
sergebulaev
AI & Automation Solid

linkedin-humanizer

Scrub AI tells from any text draft OR audit a finished post against the 2026 algorithm heuristic checklist. Tier-based rewriter (forensic / strict / aesthetic / all) plus `--mode audit` for detection-only pass-fail review covering length, hook, CTA, format penalties, AI vocab. Sub-tools: emoji-pattern detector, multi-detector spread tester (GPTZero, Originality.ai, ZeroGPT, Sapling, Copyleaks), rule explainer. Triggers on "humanize", "de-AI", "review this draft", "audit before posting", "is this ready".

449 Updated 5 days ago
sergebulaev