Template Dev
lbedner/aegis-stack
A skill your agent uses when developing or modifying Copier templates in aegis/templates, or backporting a change from a generated project (e.g.
After scaffolded practice, run an unassisted check with no AI help.
Install Unassisted Evidence Checkpoint
$ npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install GarethManning/education-agent-skills unassisted-evidence-checkpoint --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/GarethManning/education-agent-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/student-learning/unassisted-evidence-checkpoint .claude/skills/unassisted-evidence-checkpoint && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "unassisted-evidence-checkpoint" agent skill from https://github.com/GarethManning/education-agent-skills/tree/main/skills/student-learning/unassisted-evidence-checkpoint into .claude/skills/unassisted-evidence-checkpoint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unassisted-evidence-checkpoint", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/GarethManning/education-agent-skills/tree/main/skills/student-learning/unassisted-evidence-checkpointType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install GarethManning/education-agent-skills unassisted-evidence-checkpoint --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GarethManning/education-agent-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/student-learning/unassisted-evidence-checkpoint .agents/skills/unassisted-evidence-checkpoint && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "unassisted-evidence-checkpoint" agent skill from https://github.com/GarethManning/education-agent-skills/tree/main/skills/student-learning/unassisted-evidence-checkpoint into .agents/skills/unassisted-evidence-checkpoint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unassisted-evidence-checkpoint", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install GarethManning/education-agent-skills unassisted-evidence-checkpoint --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GarethManning/education-agent-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/student-learning/unassisted-evidence-checkpoint .cursor/skills/unassisted-evidence-checkpoint && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "unassisted-evidence-checkpoint" agent skill from https://github.com/GarethManning/education-agent-skills/tree/main/skills/student-learning/unassisted-evidence-checkpoint into .cursor/skills/unassisted-evidence-checkpoint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unassisted-evidence-checkpoint", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/GarethManning/education-agent-skills.git --path skills/student-learning/unassisted-evidence-checkpoint--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install GarethManning/education-agent-skills unassisted-evidence-checkpoint --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GarethManning/education-agent-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/student-learning/unassisted-evidence-checkpoint .gemini/skills/unassisted-evidence-checkpoint && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "unassisted-evidence-checkpoint" agent skill from https://github.com/GarethManning/education-agent-skills/tree/main/skills/student-learning/unassisted-evidence-checkpoint into .gemini/skills/unassisted-evidence-checkpoint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unassisted-evidence-checkpoint", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install GarethManning/education-agent-skills unassisted-evidence-checkpointInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/GarethManning/education-agent-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/student-learning/unassisted-evidence-checkpoint .github/skills/unassisted-evidence-checkpoint && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "unassisted-evidence-checkpoint" agent skill from https://github.com/GarethManning/education-agent-skills/tree/main/skills/student-learning/unassisted-evidence-checkpoint into .github/skills/unassisted-evidence-checkpoint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unassisted-evidence-checkpoint", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install GarethManning/education-agent-skills unassisted-evidence-checkpoint --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/GarethManning/education-agent-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/student-learning/unassisted-evidence-checkpoint .opencode/skills/unassisted-evidence-checkpoint && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "unassisted-evidence-checkpoint" agent skill from https://github.com/GarethManning/education-agent-skills/tree/main/skills/student-learning/unassisted-evidence-checkpoint into .opencode/skills/unassisted-evidence-checkpoint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "unassisted-evidence-checkpoint", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
unassisted-evidence-checkpoint- GitHub stars
- 840
- Token cost
- ~4.1k tokens
- SKILL.md length
- 1,133 words
- Files
- 1
- Skills in repo
- 160
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
After scaffolded practice, run an unassisted check with no AI help.
- Works in 4 steps: The unassisted checkpoint cannot be… → Problem calibration matters… → A single checkpoint is insufficient to… → …
- Distinguish supported performance from what the learner can currently do independently
- SKILL.md covers What This Skill Does, Evidence Foundation, System Prompt and Example Transcript, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Unassisted Evidence Checkpoint is an agent skill from GarethManning/education-agent-skills. After scaffolded practice, run an unassisted check with no AI help. Use to distinguish supported performance from what the learner can currently do independently.
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Project scaffolding. The repository describes itself as: 165 evidence-grounded AI skills for teachers, school leaders and EdTech builders—pedagogy, learning science, curriculum, assessment and regeneration. Claude, Codex and Hermes.
When your agent uses it
- Distinguish supported performance from what the learner can currently do independently
- Tasks that involve Project scaffolding
Example prompts
- “/unassisted-evidence-checkpoint”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- The unassisted checkpoint cannot be cryptographically enforced. The skill relies on the learner's honest participation — it cannot verify…
- Problem calibration matters significantly. If the unassisted problem is too different in surface form from the scaffolded practice, the…
- A single checkpoint is insufficient to characterise a learner's independent capability. One unassisted problem is a data point, not a…
- The firm no-help rule can distress anxious learners. The redirect scripts are designed to be warm while holding the line, but for highly…
What it can do on your machine
Read from SKILL.md and the folder at commit 6bbbce4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Unassisted Evidence Checkpoint loads about 4.1k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 1,133 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,133 words (~4,096 tokens).
“After scaffolded practice, schedules and administers an unassisted check — a problem or question the learner must attempt with absolutely no AI help, hints, or scaffolding. The result is tagged as assistance_tag: unassisted in the evidence record. Bastani et al…”
- name
- unassisted-evidence-checkpoint
- disable-model-invocation
- false
- user-invocable
- true
- effort
- light
- skill_id
- student-learning/unassisted-evidence-checkpoint
- skill_name
- Unassisted Evidence Checkpoint
- domain
- student-learning
- domain_number
- 20
- version
- 1.1
- audience
- student
- evidence_strength
- moderate
Files
Just SKILL.md in skills/student-learning/unassisted-evidence-checkpoint of GarethManning/education-agent-skills.
Open the folder on GitHubat commit 6bbbce4
Compare with similar skills
Unassisted Evidence Checkpoint next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Unassisted Evidence Checkpoint this skillGarethManning/education-agent-skills | 840 | — | ~4.1k | Automated safety check: Pass | Custom licence | |
| Template Devlbedner/aegis-stack | 143 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Google Agents CLI Evalpifferologo/cloud-agents-cli | 129 | 1 repos | ~6.8k | Automated safety check: Pass | Apache-2.0 | |
| Hipfire Arch Portwarpfront/hipfire | 658 | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Swarmauri Add Community Standaloneswarmauri/swarmauri-sdk | 104 | — | ~387 | Automated safety check: Pass | Apache-2.0 | |
| Swarmauri Add Experimental Standaloneswarmauri/swarmauri-sdk | 104 | — | ~457 | Automated safety check: Pass | Apache-2.0 |
Similar skills
Google Agents CLI Eval
pifferologo/cloud-agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs…
Hipfire Arch Port
warpfront/hipfire
Port hipfire compute kernels to a new RDNA / CDNA architecture (gfx1201/gfx1200/gfx94x/gfx1150/etc.).
Swarmauri Add Community Standalone
swarmauri/swarmauri-sdk
Add a second-class standalone Swarmauri package under pkgs/community.
Swarmauri Add Experimental Standalone
swarmauri/swarmauri-sdk
Add an experimental standalone Swarmauri package under pkgs/experimental.
Squash Branch
lbedner/aegis-stack
A skill your agent uses when collapsing a feature branch into a single commit before opening or merging a PR.
More from GarethManning/education-agent-skills
All 160 skills in this repoAcademic Language Sentence Frame Generator
GarethManning/education-agent-skills
Generate tiered sentence frames for academic tasks that scaffold language production across proficiency levels.
Adaptive Hint Sequence Designer
GarethManning/education-agent-skills
Generate a cascading hint sequence for a problem type, revealing progressively without giving answers.
Agency Circles For Systems Action
GarethManning/education-agent-skills
Map control, influence, and concern after systems analysis. An agent skill from GarethManning/education-agent-skills.
Agency Scaffold Generator
GarethManning/education-agent-skills
Generate scaffolds that gradually increase student choice, voice, and ownership within a learning task.
AI Expertise Interrogation Designer
GarethManning/education-agent-skills
Design a Funhouse Mirror activity where students use their own domain expertise to detect AI distortions, omissions, and overconfidence.
AI Feedback Design Principles
GarethManning/education-agent-skills
Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact.
Related
Categories
Questions about Unassisted Evidence Checkpoint
What does Unassisted Evidence Checkpoint do?
After scaffolded practice, run an unassisted check with no AI help. Unassisted Evidence Checkpoint is an agent skill from GarethManning/education-agent-skills. After scaffolded practice, run an unassisted check with no AI help.
When should I use Unassisted Evidence Checkpoint?
Unassisted Evidence Checkpoint fits situations like: distinguish supported performance from what the learner can currently do independently; tasks that involve Project scaffolding.
How do I install Unassisted Evidence Checkpoint in Claude Code?
Run `npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a claude-code`. Or copy the skill folder (skills/student-learning/unassisted-evidence-checkpoint in GarethManning/education-agent-skills) into .claude/skills/unassisted-evidence-checkpoint in your project. Claude Code loads it when a task matches its description.
How do I install Unassisted Evidence Checkpoint in Codex?
Run `npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a codex`. Or copy the skill folder (skills/student-learning/unassisted-evidence-checkpoint in GarethManning/education-agent-skills) into .agents/skills/unassisted-evidence-checkpoint in your project. Codex loads it when a task matches its description.
Can I use Unassisted Evidence Checkpoint in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GarethManning/education-agent-skills --skill unassisted-evidence-checkpoint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/unassisted-evidence-checkpoint, .gemini/skills/unassisted-evidence-checkpoint, .github/skills/unassisted-evidence-checkpoint and .opencode/skills/unassisted-evidence-checkpoint in your project.
What does Unassisted Evidence Checkpoint need to run?
SKILL.md names no scripts, command-line tools or credentials: Unassisted Evidence Checkpoint is instructions for the agent only.
Does Unassisted Evidence Checkpoint access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Unassisted Evidence Checkpoint safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Unassisted Evidence Checkpoint use?
Unassisted Evidence Checkpoint has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Unassisted Evidence Checkpoint use?
About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Unassisted Evidence Checkpoint?
Skills that share tags, products or a category with Unassisted Evidence Checkpoint: Template Dev (lbedner/aegis-stack, 143 stars), Google Agents CLI Eval (pifferologo/cloud-agents-cli, 129 stars), Hipfire Arch Port (warpfront/hipfire, 658 stars) and Swarmauri Add Community Standalone (swarmauri/swarmauri-sdk, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Unassisted Evidence Checkpoint?
GarethManning (a GitHub user) maintains it in GarethManning/education-agent-skills, which has 840 GitHub stars. The repository holds 160 skills in this directory. The repository was last updated on August 28, 2026.
Source: GarethManning/education-agent-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.