publish-package
Skill0 starsChanged 3 months agoMITView on GitHub
Prepares everything needed to publish an approved video (title options, caption, hashtags, best posting time from vault data) and measures its performance against the creator's baseline after it goes live. Use when a brand gives the green light, when the user is about to post, or when checking how a recent post performed.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- danielvm-git/bigpowerstheir own version, first seen Nov 6, 2026
- maciekuc94/sensum-ai-pipelinetheir own version, first seen Jun 13, 2026
- EmilioEsposito/opencode-claude-code-bridgetheir own version, first seen Jun 12, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- danielvm-git/bigpowers★ 288same name
- EmilioEsposito/opencode-claude-code-bridge★ 4same name
- maciekuc94/sensum-ai-pipeline★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- brand-outreachSkill
- media-kitSkill
- script-reviewSkill
- socials-connectSkill
- weekly-digestSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 31
If sponsored: mirror the outcome to the linked outreach entry (outreach_log_update notes) — that's the case study for the next pitch …
- Distinctive: line 35
Every recommendation cites its data ("Tuesday is your strongest day: 31% of views").
- Distinctive: line 36
No posting automation, ever — the human presses the button.
- Distinctive: line 37
If the platform lacks data for a step, say so and default to the creator's usual pattern rather than inventing.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
publish-package — green light → ready to post → measured
The agent owns packaging and measurement; the human posts (posting automation is deliberately out of scope — see docs/CAPABILITIES.md).
Step 1 — Assemble the package (stage: approved)
socials-mcp:profile_get(tone, keywords) +socials-mcp:pipeline_list(stage: "approved") to find the item.- Generate the package:
- Title options (3) — keyword-front-loaded, ≤80 chars, pattern-matched to the creator's top_content titles.
- Caption — hook line + 1–2 lines of context + CTA matching tone_notes; disclosure (#ad / #sponsored) FIRST if branded, per brief.
- Hashtags (5–8) — mix: 2 niche keywords from profile, 2 proven (appear in past top titles/captions), 2 broad-reach; check they're real words, no ban-list tags.
- Best posting window — data-driven:
vault_queryday-of-week viewsSELECT strftime('%w', date) AS dow, sum(value) AS v FROM account_metrics am JOIN snapshots s ON s.id=am.snapshot_id JOIN accounts a ON a.id=s.account_id WHERE a.platform=? AND am.metric='views' AND am.date IS NOT NULL GROUP BY dow ORDER BY v DESC→ recommend top day(s) + evening preference if the creator's audience skews after-work hours (note when data is thin: say "no strong signal; default to your usual slot").
- Present the package for approval; on go-ahead,
socials-mcp:pipeline_update→ keepapproved, attach package innotes.
Step 2 — At posting time (human posts)
Hand over the final copy-paste block (title / caption / tags). After they confirm it's live: pipeline_update → stage: "posted" with post_url and posted_at.
Step 3 — Measure (the part nobody does)
- 48h check-in: find the video via
top_content(days: 2) orvault_queryon title match; report early velocity vs the creator's median (top_contentdays: 30,limit: 20→ median views). Flag if it's tracking below half the median at 48h so there's time to fix the title/cover. - 7-day verdict: views, ER, watch time vs median → append a one-line outcome to the pipeline item notes (
pipeline_update), setstage: "measured". - If sponsored: mirror the outcome to the linked outreach entry (
outreach_log_updatenotes) — that's the case study for the next pitch (media-kit skill picks it up).
Rules
- Every recommendation cites its data ("Tuesday is your strongest day: 31% of views").
- No posting automation, ever — the human presses the button.
- If the platform lacks data for a step, say so and default to the creator's usual pattern rather than inventing.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.