Publish Sign in

Career Development Plan Agent Skill

Develop the career-development and training components of a career award or fellowship — candidate background and career goals, training…

Install this skill Read the source first Free Written by joshua-d-campbell
Context cost
4.4k tokensestimated from the bundle, loaded when it triggers
Bundle
2 files · 17.6 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Develop the career-development and training components of a career award or fellowship — candidate background and career goals, training gap analysis, development activities and timeline, mentor/sponsor team assembly, mentor and sponsor statements, institutional commitment, referee letter strategy, and the RCR training plan. Use whenever the grant is a career development award (NIH K01/K08/K23/K25/K99-R00, NSF CAREER, foundation career awards) or a graduate/postdoctoral fellowship (NIH F30/F31/F32, NSF GRFP), or the user mentions a career plan, candidate statement, mentoring team, sponsor…

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

productivity
Filed under

Productivity & Workflow

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md8.6 kB · preview
--- name: grant-career-plan ---
6# Career Development Plan
7
8On a career award or fellowship the applicant *is* the project: reviewers fund a trajectory, not just a study, and they weight the candidate, the mentoring, and the training plan as heavily as the science. (Fellowships call the mentor the *sponsor* — the terms below map directly.) The document set stands or falls on one coherence chain: **stated training gaps → chosen development activities → mentor expertise covering each gap → research plan as the training vehicle → the five-year career goal**. Every classic career-award critique is a break in that chain — a named training area no mentor covers, an activity unconnected to the goal, a research plan sized for a funded lab rather than one trainee.
9
10Read _agent/project-config.md first (run grant-setup if missing) and confirm the award type is recorded as career-development. Career-award files live in 09_career/ (add the folder to the standard structure if absent), versioned per the schema. Agency differences are substantial — read references/agency-variants.md for the mechanism in play before drafting. The candidate's statements follow _agent/style-profile.md and are checked against its *Directives* list before delivery; mentor, sponsor, and institutional statements are written in *their* authors' voices, not the candidate's (shared convention 5).
11
12## Maintain the training map
13
14Create _agent/notes/training-map.md early: one row per training gap — the gap, the activity that closes it, the mentor or resource that covers it, the aim that exercises it, the year it happens. This table is the audit instrument for the whole document set; every section below reads from and writes to it, and the final coherence check walks it row by row.
15
16## Step 1 — Candidate and career goals
17
18Elicit: career stage and prior training, key publications, and the specific independent identity five years out ("an independent PI studying X using Y approaches" — a goal a reviewer can picture, not "continue growing as a scientist"). Draft the candidate background as a trajectory narrative, not CV prose: prior work framed as deliberate preparation, gaps named plainly as the next steps. Candidates often resist stating gaps; push back — on a career award an applicant with no training gaps has no case for the mechanism, and reviewers read honest gap analysis as self-awareness, not weakness.
19
20## Step 2 — Gap analysis and development activities
21
22Keep gaps concrete and few (typically 3–4): specific techniques or fields, plus professional skills (lab leadership, grant and personnel management, responsible mentoring). Every activity maps to a gap and carries a time allocation and year — named coursework, technique training in a specific lab, structured writing programs. Generic filler ("attend seminars," "read the literature") carries no weight and dilutes the real plan. Build the timeline with training front-loaded, research effort growing across years, and explicit independence markers: first corresponding-author paper, first R01 (or equivalent) submission, transition milestones. NIH fellowships additionally require an "Activities Planned Under This Award" percent breakdown by year (research, coursework, clinical, professional development) — it must sum sensibly and match the training narrative word for word, because reviewers cross-check the two.
23
24## Step 3 — Mentor team
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md1,236 words
Files2
Licencenot declared
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈180
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
4,220
on trigger
The instruction body and 1 supporting file, read only when the skill fires.
2.2%
of a 200k window
Ten skills this size would take about 22% of the window before you open a file.
050k100k150k200k context window

4.4k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

2 files, 17.6 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md8.6 kB
  • references/agency-variants.md9.0 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 2 files you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Career Development Plan · 4.4k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/career-development-plan/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/career-development-plan" ] && { [ ! -e .claude/skills/career-development-plan ] || { mv .claude/skills/career-development-plan "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/career-development-plan" .claude/skills/ && echo "Installed .claude/skills/career-development-plan"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add joshua-d-campbell/career-development-plan

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/career-development-plan/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/career-development-plan/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/career-development-plan" ] && { [ ! -e ~/.claude/skills/career-development-plan ] || { mv ~/.claude/skills/career-development-plan "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/career-development-plan" ~/.claude/skills/ && echo "Installed ~/.claude/skills/career-development-plan" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/career-development-plan/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as grant-career-plan in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, career-development-plan.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencejoshua-d-campbell/career-development-plan

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

JD
joshua-d-campbell

Publishes on mcprush.

0 servers listed31 skills listednot claimed
Profile
Publisher
Servers0
Claim this skill