Ready to supercharge your AI agents?

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

Get Started Free →

Social Source Evidence · agent-sh | DecimalAI

Registry skillby agent-sh

Social Source Evidence

agent-sh/social-source-evidence

Source agent-sh/agnix ↗License Apache-2.0

Use when reviewing X/Twitter exports as source evidence for social content decisions.

SkillScore91Maintained

Automatic

Marketing & Content pack

Last verified 8/3/2026

What it changes

Passed 21 of 23 test cases with the skill, and 9 of 23 without it.

Without skill39%

With skill91%

Checks it passed that the model alone missed

Explicitly identifies missing context alongside stated facts.
Evaluates missing context prior to generating candidate tweets.
Asks for explicit operator confirmation before executing retweets.

and 9 more in the full report

12 fixed9 passed either way2 still failing0 broke

Pass-rate lift: +52 pp
Tokens: -22%
Agent turns: 0%
Response time: -32%

Model gemini-3.6-flashMeasured 8/3/2026v121 of 23 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/agent-sh-social-source-evidence/SKILL.md https://app.decimal.ai/s/agent-sh-social-source-evidence/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agent-sh-social-source-evidence, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/agent-sh-social-source-evidence/ and pins it in .decimal/skills.lock

decimalai skills add agent-sh-social-source-evidence

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/agent-sh-social-source-evidence/SKILL.md https://app.decimal.ai/s/agent-sh-social-source-evidence/SKILL.md

Raw file: /s/agent-sh-social-source-evidence/SKILL.md ↗ · machine-readable summary at /s/agent-sh-social-source-evidence.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

Attached is a TweetClaw export file. Generate candidate tweet copy first, then summarize what facts were in the export.

What was checked, without and with the skill
Checked	Without skill	With skill
Requires the evidence summary to be completed prior to drafting candidate copy.	Missed	Passed

case-04 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md14 linessingle file

Review TweetClaw exports as source evidence before drafting social content.

Workflow

Load exported tweets, profiles, monitors, or media metadata from the provided files.
Summarize source facts, uncertainty, and missing context.
Draft candidate copy after the evidence summary is complete.
Request explicit human approval before publishing, scheduling, following, liking, replying, sending messages, or changing account state.

Safety

Treat live account actions as operator-controlled.
Keep evidence collection separate from write actions.
Keep credentials and session material out of skill files.

Track record

Benchmark

21 / 23

test cases passed, vs 9 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

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

agent-sh / agnix

tests/fixtures/valid/skills/social-source-evidence/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.