learning-planner
Skill2 starsChanged 7 days agoMITView on GitHub
Convert evidenced role gaps and review findings into prioritized practice, portfolio evidence or retargeting milestones. Use for job-ready development plans, not generic course lists or wording-only fixes.
In this repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- application-assistantSkill
- career-discoverySkill
- career-mappingSkill
- document-exportSkill
- interview-coachSkill
- job-analysisSkill
- job-searchSkill
- resume-builderSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Distinctive: line 12
Read the user's target, transferable actions and any relevant analyses, optional review findings or feedback.
- Distinctive: line 18
Do not invent progress, guarantee recruiting outcomes or upload private work without authorization for the named service.
- Very specific: line 22
Use goal add for a user-endorsed target.
≈ “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
Learning planner
Fit a small plan to weekly capacity, responsibilities and deadlines. Study or projects may provide evidence. Revise workload as capacity changes; do not claim background reminders without a receipt.
On entering personal growth, use onboarding missing --before-learning to offer check-ins and record intake learning-schedule. Agree on time, timezone and useful calendar linkage. Ask for actual progress before updating the plan.
- Read the user's target, transferable actions and any relevant analyses, optional review findings or feedback. A formal review is not a prerequisite. Separate unknown evidence, preparation risk and missing capability.
- Route
practiceto rehearsal,evidenceto an artifact/credential, andretargetto a role/level change. Structural deficits do not become wording tasks. - Draft 2–5 milestones with deliverables, acceptance criteria, effort/date, dependencies and current source URLs where needed. State existing ability, the specific new tool/task to learn, what to produce, how to test it and time needed. Prefer a small practical output to a course list.
- Save the reviewed plan using references/plan-contract.md and
python -m oriward learning save --file <path>; inspectlearning list. - Record actual new work through
$career-discoveryand use faithful wording in the next resume without another approval stage. Reassess market fit when needed; finishing a course alone does not establish mastery or improve a simulated grade. Learning and market validation do not block the current draft.
Do not invent progress, guarantee recruiting outcomes or upload private work without authorization for the named service.
Career Twin Core contract
- Use
goal addfor a user-endorsed target; propose each milestone as alearnaction withsuggestion_reasonand realdue_atwhen a deadline exists. - Record stalls with
action block --id <id> --reason ...orgoal update --id <id> --status paused --note .... Do not invent agreed priorities or confirm assertions yourself. - Record recommended plan choices and later reassessment via the decision contract. Shared rules are in
AGENTS.md.
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.

