application-assistant
Skill2 starsChanged 7 days agoMITView on GitHub
Assemble local application packets, bind the exact resume version, and record user-confirmed submission and outcomes. Use for preparation and tracking; never submit or contact recruiters autonomously.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- career-discoverySkill
- career-mappingSkill
- document-exportSkill
- interview-coachSkill
- job-analysisSkill
- job-searchSkill
- learning-plannerSkill
- resume-builderSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Only after direct confirmation of this version's submission, record SUBMITTED with --human-confirmed.
- Very specific: line 18
Read pipeline show --job-id <id> for stage, verified event, next action, deadline and blocker.
- Very specific: line 19
Update related actions from the observed state (action propose or action complete --evidence ...).
- Distinctive: line 20
Use DECISIONS for recommendations.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Application assistant
- Inspect the exact job, resume history and requested review. Confirm the resume is bound to this vacancy and check source currency/material risks; no formal assessment or per-experience approval is required. A direction draft becomes job-bound here. Explicit preparation can use available context directly.
- Assemble official URL, exact resume ID, grounded answers and open questions locally.
application prepare --job-id <id> --resume-id <id>createsREADY_FOR_USERonly; no hash or wording confirmation gates preparation. - Give manual submission steps. Do not log in, upload, final-click, contact a recruiter or bypass CAPTCHA.
- Only after direct confirmation of this version's submission, record
SUBMITTEDwith--human-confirmed. A prepared packet is not submission. - Record later supported states from evidence. Route feedback through
feedback save; actual feedback binds the application and exact sent resume. Saving feedback changes neither status nor grade automatically.
Report IDs, exact document version, status, evidence and pending user action. Keep ready, submitted and employer acknowledged distinct.
Career Twin Core contract
- Read
pipeline show --job-id <id>for stage, verified event, next action, deadline and blocker. - Update related actions from the observed state (
action proposeoraction complete --evidence ...); record user reactions withsignal add. - Use DECISIONS for recommendations; shared rules are in
AGENTS.md. No state write authorizes submission.
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.

