Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Social Post Approval — measured AI agent skill | DecimalAI

alephic-ai/social-post-approval

SkillScore100Maintained

Turn read-only TweetClaw exports into source notes for approval-gated social publishing workflows.

by alephic-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Marketing & Content pack

decimalai skills pull alephic-ai-social-post-approval

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/alephic-ai-social-post-approval/SKILL.md

Raw file: /s/alephic-ai-social-post-approval/SKILL.md ↗ · machine-readable summary at /s/alephic-ai-social-post-approval.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3d ago

Yes — +14% lift-10% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	-27%	0%
case-09	✗→✓	▲ Improved	37%	0%
case-10	✗→✓	▲ Improved	-27%	0%
case-01	✓→✓	＝ Same ✓	-7%	0%
case-02	✓→✓	＝ Same ✓	-33%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

alephic-ai / skref

tests/fixtures/sample-skills/social-post-approval/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/2/2026Version v1

Skill contents

SKILL.md

Social Post Approval

Use this skill when an agent needs to prepare review notes from TweetClaw export data before a human approves a social post. Treat the export as evidence only.

Read the exported rows or objects.
Extract the post text, source URL, account handle, timestamp, and metrics.
Summarize why the post is relevant to the requested campaign.
Flag missing attribution, unclear consent, sensitive claims, or unsupported

metrics.

Return a draft approval note with the source fields cited.

Do not publish, schedule, delete, or edit social content. Stop if the workflow requires live account access.

Want to see if alephic-ai/social-post-approval would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.