Self-Determined Project Design Protocol Agent Skill

Structure a student's self-determined project with mentoring checkpoints, competency alignment, and reflection.

Context cost
8.8k tokensestimated from the bundle, loaded when it triggers
Bundle
1 file · 35.4 kBtext throughout, nothing executable
Licence
not declarednone named by its author
Last change
—v1.0
Servers it uses
Noneruns standalone

What it does

Structure a student's self-determined project with mentoring checkpoints, competency alignment, and reflection. Use when guiding student-led projects within a competency-based framework.

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.

bandurafeasibilitymanningmentoringprojectself-determinedsrlzimmerman

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.md35.4 kB · preview
--- # AGENT SKILLS STANDARD FIELDS (v2) name: self-determined-project-design-protocol disable-model-invocation: true user-invocable: true effort: medium # EXISTING FIELDS skill_id: "original-frameworks/self-determined-project-design-protocol" skill_name: "Self-Determined Project Design Protocol" domain: "original-frameworks" version: "1.0" evidence_strength: "emerging" evidence_sources: - "Manning — Personal project mentoring methodology (original, developed through capstone mentoring and international teaching)" - "Zimmerman (2000, 2002) — Self-regulated learning: forethought, performance, self-reflection phases" - "Bandura (1997) — Self-efficacy: the exercise of control (feasibility calibration as self-efficacy assessment)" - "Ericsson & Pool (2016) — Peak: secrets from the new science of expertise (knowledge/skill acquisition as deliberate practice)" - "Black & Wiliam (1998) — Assessment and classroom learning (milestone checkpoints as formative assessment)" - "Manning — LT authoring methodology and rubric logic (Domain 14 Skills 98 and 99)" input_schema: required: - field: "student_idea" type: "string" - field: "student_level" type: "string" - field: "available_time" type: "string" optional: - field: "existing_curriculum_LTs" type: "string" - field: "mentor_expertise" type: "string" - field: "prior_experience" type: "string" output_schema: type: "object" fields: - field: "phase_1_ideation_and_feasibility" type: "object" - field: "phase_2_knowledge_gap_analysis" type: "object" - field: "phase_3_planning" type: "object" - field: "phase_4_execution_and_monitoring" type: "object" - field: "phase_5_completion_and_defence" type: "object" - field: "tracking_system" type: "object" - field: "educator_feasibility_calibration_guide" type: "object" - field: "known_limitations" type: "object" chains_well_with: - "learning-target-authoring-guide" - "coherent-rubric-logic-builder" - "developmental-band-system-designer" - "self-regulated-learning-designer" - "curriculum-knowledge-architecture-designer" teacher_time: "6 minutes" tags: ["self-determined", "project", "Manning", "mentoring", "SRL", "Zimmerman", "Bandura", "feasibility", "deliberate-practice", "tracking"] ---
81# Self-Determined Project Design Protocol
82
83## What This Skill Does
84
85This skill encodes an original practitioner framework developed by Gareth Manning, educator, curriculum designer, and learning systems designer. Unlike skills in other domains, it is not drawn from peer-reviewed research traditions. It is grounded in serious engagement with learning science, original curriculum design work, and active classroom testing. It is included because the methodology is coherent, transferable, and genuinely useful — and because intellectual honesty requires distinguishing practitioner frameworks from research-validated approaches.
86
87This skill guides both student and educator through the full arc of designing, planning, and executing a self-determined personal project — from initial idea through to completion, defence, and reflection. It specifies what BOTH parties need to do at each phase, how to calibrate ambition honestly, and how to build the knowledge and skill acquisition plan alongside the project itself. The output is a complete dual-perspective protocol: student-facing roadmap and educator-facing mentoring guide, phase by phase. The protocol maps directly to Zimmerman's (2000, 2002) self-regulated learning phases: forethought (Phases 1-3), performance (Phase 4), and self-reflection (Phase 5). Bandura (1997) informs the feasibility calibration: over-ambitious and under-ambitious projects both reflect miscalibrated self-efficacy, and the educator's role is to help students calibrate honestly without crushing agency. Ericsson & Pool (2016) inform the knowledge/skill acquisition plan: the skills a student needs to develop for their project constitute a deliberate practice design problem. The tracking system — a shared, visible artefact that both student and mentor can see at all times — is the structural backbone of the protocol. Without it, mentoring conversations have no shared reference point and project drift is invisible until it's too late.
88
89## Evidence Foundation
90
91Manning developed this protocol through personal project mentoring in multiple international school contexts, most recently through capstone mentoring at REAL School Budapest. The methodology addresses a specific problem: most "independent project" programmes give students freedom without structure — resulting in either teacher-directed projects that aren't really self-determined, or student-led projects that drift, stall, or collapse because the student lacked the self-regulation skills to manage the process. Zimmerman (2000, 2002) provides the theoretical framework for the protocol's phase structure. His self-regulated learning model describes three cyclical phases: forethought (goal-setting, strategic planning, self-efficacy assessment), performance (self-monitoring, strategy use, help-seeking), and self-reflection (self-evaluation, attribution, adaptive responses). The protocol operationalises these phases: Phases 1-3 ARE forethought, Phase 4 IS performance, Phase 5 IS self-reflection. Bandura (1997) informs the feasibility calibration — the most critical and most frequently skipped part of the protocol. Self-efficacy (the student's belief in their ability to succeed) directly predicts effort, persistence, and resilience. But self-efficacy can be miscalibrated: a student who believes they can build an app in 6 weeks with no coding experience has inflated self-efficacy that will lead to demoralising failure. Equally, a student who says "I can't do anything interesting" has deflated self-efficacy that will lead to an uninspired project. The educator's role is to calibrate honestly: probing what the student actually knows, what they need to learn, and whether the timeline is realistic. Over-ambitious equals under-ambitious in terms of harm — a student who fails a project they weren't ready for learns the wrong lesson. Ericsson & Pool (2016) inform the knowledge/skill acquisition plan. The skills a student needs for their project — coding, woodworking, research methods, writing, design — are not acquired by wishing. They require deliberate, structured practice. The protocol builds a parallel skill acquisition plan alongside the project plan: what do you need to learn, how will you learn it, and how will you know when you've learned it? Black & Wiliam (1998) inform the milestone checkpoint design: each checkpoint is a structured formative assessment moment where the student self-assesses against the rubric, shares evidence, gets feedback, and adapts the plan.
92
93## Input Schema
94
95The educator must provide:
96- **Student idea:** The initial project idea. *e.g. "I want to build a website for my mum's bakery" / "I want to write and illustrate a children's book about climate change" / "I want to design and build a model bridge that can hold 50kg" / "I want to learn to play guitar and perform at the school concert" / "I don't know what I want to do"*
97- **Student level:** Developmental band and age. *e.g. "Band D, age 13" / "Band C, age 11" / "Band B, age 9"*
98- **Available time:** Total duration and weekly commitment. *e.g. "One semester (18 weeks), 3 hours per week dedicated project time plus independent work" / "One term (10 weeks), 2 hours per week" / "Full year, 90 minutes per week"*
99
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md5,200 words
Files1
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.

≈1,070
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
7,780
on trigger
The instruction body, read only when the skill fires.
4.4%
of a 200k window
Ten skills this size would take about 44% of the window before you open a file.
050k100k150k200k context window

8.8k 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

1 file, 35.4 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • SKILL.md35.4 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 1 file 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.

# Self-Determined Project Design Protocol · 8.8k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/self-determined-project-design-protocol/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/self-determined-project-design-protocol" ] && { [ ! -e .claude/skills/self-determined-project-design-protocol ] || { mv .claude/skills/self-determined-project-design-protocol "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/self-determined-project-design-protocol" .claude/skills/ && echo "Installed .claude/skills/self-determined-project-design-protocol"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add garethmanning/self-determined-project-design-protocol

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/self-determined-project-design-protocol/ 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/self-determined-project-design-protocol/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/self-determined-project-design-protocol" ] && { [ ! -e ~/.claude/skills/self-determined-project-design-protocol ] || { mv ~/.claude/skills/self-determined-project-design-protocol "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/self-determined-project-design-protocol" ~/.claude/skills/ && echo "Installed ~/.claude/skills/self-determined-project-design-protocol" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/self-determined-project-design-protocol/ 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.

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
Version1.0
Publishedno release date on file
PriceFree
Referencegarethmanning/self-determined-project-design-protocol

Versions

v1.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v1.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

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.

Publisher
Servers0
Claim this skill