daily
Skill0 starsChanged 2 months agoMITView on GitHub
The scheduled daily run. Finds new jobs, researches the top ones, finds contacts, drafts outreach, checks for replies and follow-ups, and writes a summary Alex can read in two minutes.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- tadeurosa-ai/claude-code-setuptheir own version, first seen Nov 16, 2026
- matthewwong525/WongStacktheir own version, first seen Nov 15, 2026
- TJaenichen/claude-code-harnesstheir own version, first seen Nov 15, 2026
- galiprandi/job-seekertheir own version, first seen Nov 14, 2026
- qbeka/jev-job-searchtheir own version, first seen Nov 12, 2026
- elfrost/ai-patchlabtheir own version, first seen Nov 9, 2026
Used with
Projects with it also use monthly, weekly and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
gaiaaiagentSkillmonthly
Generate a monthly digest distilling weeklies into trend analysis and narrative arcs
Also in 3 projects that use this
gaiaaiagentSkillweekly
Generate a weekly digest rolling up dailies into higher-level pattern analysis
Also in 9 projects that use this
anombyte93Skilldiscover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.
Also in 3 projects that use this
VercelSkillsetup
Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- baojie/shiji-kb★ 3.4ksame name
- kstonekuan/tambourine-voice★ 394same name
- qbeka/jev-job-search★ 368same name
- serejaris/personal-corp-os★ 244same name
- serejaris/ris-claude-code★ 244same name
- earlyaidopters/second-brain★ 193same name
- kv0906/pm-kit★ 138same name
- galiprandi/job-seeker★ 136same name
- saksham10arora-dotcom/everything-claude-codex★ 96same name
- alirezarezvani/gaios★ 50same name
12 more not listed
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 repository7 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- draft-outreachSkill
- find-contactsSkill
- find-jobsSkill
- followupsSkill
- research-companySkill
- send-emailSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
The self-send exception: After writing pipeline/daily-summary.md, run
- Very specific: line 39
Run /followups first, in reply-check mode: look for Gmail replies to sent emails and update the pipeline.
- Very specific: line 42
Write pipeline/daily-summary.md (overwrite it) with, in this order:
- Distinctive: line 44
Follow-ups drafted and waiting for approval.
- Very specific: line 54
Put the draft file path on the last line, for reference rather than as the way in.
- Distinctive: line 58
Keep everything except the drafts under 40 lines.
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Daily run
This runs unattended. It never sends anything to anyone but Alex. It reads, researches, drafts, and logs, and it has exactly one send permission:
The self-send exception. After writing pipeline/daily-summary.md, run
python3 scripts/build_daily_report.pyIt reads the summary plus the pipeline CSVs and today's draft files and writes daily-email.html,
job-search-<date>.pdf, job-search-tracker-<date>.xlsx and report-meta.json into
pipeline/report/. It then copies the PDF and the tracker into the iCloud Drive folder
~/Library/Mobile Documents/com~apple~CloudDocs/JobSearch/, links them from the HTML body, and
deletes generated reports there older than 30 days. Do not hand-build any of the three files.
Then email it to alex.rivera@example.com and no one else, with htmlBody set to the
contents of daily-email.html, body set to the plain markdown summary as the text alternative,
and subject Job search daily — <date>.
Do not attach anything. The PDF and the tracker reach Alex through iCloud Drive, and the email
links to them. Attaching would mean inlining about 40KB of base64 into the send call, which is what
made an earlier run drop the files silently. If report-meta.json shows published empty, say in
the email that the files could not be written to iCloud and give their paths under pipeline/report/
instead.
That single address is the entire exception. A PreToolUse hook (scripts/guard-gmail-send.py)
enforces it and will deny any send that names another recipient, including one added in cc or bcc.
Outreach to a contact never goes out here, in any channel. LinkedIn drafts are pasted by Alex
himself. Email to a contact goes only through /send-email, only for a draft Alex has marked
approved, and only with Alex present. If the summary email fails to send, say so in the log and
carry on; the summary file is still the record.
- Run
/followupsfirst, in reply-check mode: look for Gmail replies to sent emails and update the pipeline. Draft due follow-ups. - Run
/find-jobs. - Take the top 3 new jobs by score. For each:
/research-company, then/find-contacts, then/draft-outreachfor the single best contact. Stop at 10 total drafts for the day. - Write
pipeline/daily-summary.md(overwrite it) with, in this order:- Replies received (name, company, one-line gist). If any, put "You have replies" as the first line.
- Follow-ups drafted and waiting for approval.
- New roles found today, top 5 with score and link.
- New outreach drafted, in full. Alex reads and copies these on his phone, so never make him
open a file. For each draft give, in this order:
- person's name and title, company, and the job id
- the LinkedIn connection note, verbatim, in its own fenced code block
- the LinkedIn message, verbatim, in its own fenced code block
- the cold email, verbatim, subject line included, only if one was written
- the send date and the local time window, with the time zone named
- any pre-send check on one line: a title to confirm, a req to apply to first
Put the draft file path on the last line, for reference rather than as the way in. Still write
the draft file and still log its row in
pipeline/outreach.csvas usual.
- Anything that needs Alex's input: contacts you couldn't identify, claims you weren't sure you could make, a posting that looked good but had a sponsorship question.
- Pipeline counts: roles pursuing, messages out, awaiting reply, replies this week.
- Keep everything except the drafts under 40 lines. The verbatim drafts are exempt from that limit: never truncate, paraphrase, or summarise a draft to save space. No preamble.
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.

