Individual skill
social-content-performance
Not available
Meta/muse-agent/skills/social-content-performance/SKILL.md
Source commit a2d33761e49b98f6ec1b48f12143264eb9b4ff4f
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Instructions only
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
Standard SKILL.md format has not been attested at this commit. No installation command is available; inspect the source.
Repository context
- Repository stars (not skill ratings)
- 71,160
- Repository last updated
- Nov 10, 2026
- License
- CC0-1.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai Repository topic
- anthropic Repository topic
- chatbot Repository topic
- chatgpt Repository topic
- claude Repository topic
- claude-code Repository topic
- codex Repository topic
- gemini Repository topic
- generative-ai Repository topic
- google Repository topic
Declared tags are partial or unavailable.
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 5,745 bytesreferences/presenting-results.mddoc · 1,925 bytesskill.yamlasset · 884 bytes
Read excerpt
# Social Content Performance
## Scope the question
- For a caption or hashtag request with no analysis question, write from the user's brief and the material they supply, return the draft and stop. Do not fetch account data or establish a reporting period for this branch. The remaining analysis steps apply only to performance questions.
- For a performance question, identify the network, the account and what the user wants to learn, such as which posts reached the most people, how a launch landed or what to post next. Settle the reporting period and timezone before fetching anything.
- Analyze only accounts the user manages. Take the account from the connector's own account list, ask which one to use when several fit, and stop when a named account is not returned rather than substituting another.
- Comparisons with competitors, peers or industry norms use Social Competitor Analysis, which `muse.skill_search` finds when this session has it. Public figures cannot fill a gap in the user's private metrics.
## Gather the evidence
- Retrieve the posts in scope with their publication times and permalinks, then the metrics the question needs. Preserve each connector's returned metric display names exactly rather than replacing them with generic labels or labels from memory.