Agent skill

Learning From Mistakes

The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong.

MITAuto-check: notesAI & LLM Engineering

Install Learning From Mistakes

skills CLI

$ npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install oxbshw/watch-skill learning-from-mistakes --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/learning-from-mistakes .claude/skills/learning-from-mistakes && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "learning-from-mistakes" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/learning-from-mistakes into .claude/skills/learning-from-mistakes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-from-mistakes", 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

$skill-installer install https://github.com/oxbshw/watch-skill/tree/main/skills/learning-from-mistakes

Type 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.

skills CLI

$ npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install oxbshw/watch-skill learning-from-mistakes --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/learning-from-mistakes .agents/skills/learning-from-mistakes && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "learning-from-mistakes" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/learning-from-mistakes into .agents/skills/learning-from-mistakes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-from-mistakes", 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.

skills CLI

$ npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install oxbshw/watch-skill learning-from-mistakes --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/learning-from-mistakes .cursor/skills/learning-from-mistakes && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "learning-from-mistakes" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/learning-from-mistakes into .cursor/skills/learning-from-mistakes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-from-mistakes", 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

$ gemini skills install https://github.com/oxbshw/watch-skill.git --path skills/learning-from-mistakes

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install oxbshw/watch-skill learning-from-mistakes --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/learning-from-mistakes .gemini/skills/learning-from-mistakes && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "learning-from-mistakes" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/learning-from-mistakes into .gemini/skills/learning-from-mistakes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-from-mistakes", 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.

GitHub CLI

$ gh skill install oxbshw/watch-skill learning-from-mistakes

Installs 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).

skills CLI

$ npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/learning-from-mistakes .github/skills/learning-from-mistakes && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "learning-from-mistakes" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/learning-from-mistakes into .github/skills/learning-from-mistakes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-from-mistakes", 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.

skills CLI

$ npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install oxbshw/watch-skill learning-from-mistakes --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/oxbshw/watch-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/learning-from-mistakes .opencode/skills/learning-from-mistakes && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "learning-from-mistakes" agent skill from https://github.com/oxbshw/watch-skill/tree/main/skills/learning-from-mistakes into .opencode/skills/learning-from-mistakes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "learning-from-mistakes", 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: learning-from-mistakes
GitHub stars: 469
Token cost: ~380 tokens
SKILL.md length: 141 words
Files: 1
Skills in repo: 10
Repo updated: Sep 14, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong.

AI & LLM Engineering work in your project
SKILL.md covers Report a correction, See what has been learned and The savings meter
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Learning From Mistakes is an agent skill from oxbshw/watch-skill. The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. Use this to record the correction as a lesson so future answers on similar questions improve, and to show what the system has learned and saved.

Its SKILL.md is about 380 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 AI & LLM Engineering. It works with DeepSeek. The repository describes itself as: Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic… The licence is MIT.

When your agent uses it

AI & LLM Engineering work in your project

Example prompts

“no, it actually says X”
“s the wrong timestamp”
“you misread the error code”
“/learning-from-mistakes”

Requirements

Pre-approved tools (allowed-tools): Bash, Read

What it can do on your machine

Read from SKILL.md and the folder at commit f1317c8. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
- Bash
- Read
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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

Learning From Mistakes loads about 380 tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 141 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~84
When it runs · the whole SKILL.md, loaded when a task matches: ~380

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
```
allowed-tools: Bash, Read
```

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

The full file from oxbshw/watch-skill at commit f1317c8, republished under its MIT licence (© oxbshw). 141 words, ~380 tokens.

Download SKILL.mdSave it as .claude/skills/learning-from-mistakes/SKILL.md (or your agent's skills folder).

name: learning-from-mistakes
description: The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. Use this to record the correction as a lesson so future answers on similar questions improve, and to show what the system has learned and saved.
allowed-tools: Bash, Read
version: 1.4.3
license: MIT
user-invocable: true

Learning from mistakes

When a video answer turns out wrong, the correction is worth more than an apology. Report it and Watch Skill learns locally — the mistake is classified, stored as a lesson, injected into future similar questions, and where possible the original question is immediately re-asked to confirm the lesson actually fixes it.

Report a correction

The moment the user corrects a video answer, run:

bash

watch-skill lessons add <video_id> "<question>" "<the wrong answer>" "<the correction>"

The output includes the lesson (error_class, guidance) and, when the question was re-asked, whether the corrected answer now comes back — tell the user which it was. Nothing is uploaded; lessons live in ~/.watch-skill/.

See what has been learned

bash

watch-skill lessons list

The savings meter

bash

watch-skill stats

Lifetime token economics: what text-first answering and the semantic cache have saved versus stuffing raw frames into context. Quote real numbers from it when the user asks whether any of this is worth it.

Files

Just SKILL.md in skills/learning-from-mistakes of oxbshw/watch-skill.

Open the folder on GitHubat commit f1317c8

Compare with similar skills

Learning From Mistakes 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.

Learning From Mistakes compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Learning From Mistakes this skilloxbshw/watch-skill	469	—	~380	Automated safety check: Notes	MIT	25 days ago
Dingo VerifyMigoXLab/dingo	757	—	~833	Automated safety check: Pass	Apache-2.0	11 days ago
Deepseek Helperdongsheng123132/u-claw	1.8k	—	~367	Automated safety check: Pass	MIT	3 days ago
SimPO Preference TrainingOrchestra-Research/AI-Research-SKILLs	13k	4 repos	~1.5k	Automated safety check: Pass	MIT	3 mo ago
slime RL Post-TrainingOrchestra-Research/AI-Research-SKILLs	13k	4 repos	~2.8k	Automated safety check: Pass	MIT	3 mo ago
Oracle Agent Team OrchestratorBald0Wang/DeepSeek-Oracle	187	—	~551	Automated safety check: Pass	None	7 mo ago

Similar skills

Dingo Verify
MigoXLab/dingo
A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.
757 GitHub stars~833 tokensUpdated 11 days ago
AI & LLM EngineeringAuto-check passed
Deepseek Helper
dongsheng123132/u-claw
DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw.
1.8k GitHub stars~367 tokensUpdated 3 days ago
AI & LLM EngineeringAuto-check passed
SimPO Preference Training
Orchestra-Research/AI-Research-SKILLs
Walks through aligning language models with SimPO, a reference-free preference optimization method, using accelerate configs for Mistral 7B, Llama 3 8B and math-focused models.
13k GitHub starsUsed in 4 repos~1.5k tokens
AI & LLM EngineeringAuto-check passed
slime RL Post-Training
Orchestra-Research/AI-Research-SKILLs
Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.
13k GitHub starsUsed in 4 repos~2.8k tokens
AI & LLM EngineeringAuto-check passed
Oracle Agent Team Orchestrator
Bald0Wang/DeepSeek-Oracle
Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action…
187 GitHub stars~551 tokensUpdated 7 mo ago
AI & LLM EngineeringAuto-check passed
Token Saver
lokikill123/codex-token-skills
Minimize token consumption & maximize prompt cache hit rate.
119 GitHub stars~298 tokensUpdated 3 mo ago
AI & LLM EngineeringAuto-check passed

More from oxbshw/watch-skill

All 10 skills in this repo

Asking With Evidence
oxbshw/watch-skill
The user asks a question about a video that was already watched or indexed — "what did they say about X", "what error code appears", "what happens at 2:30", "does the video show Y".
469 GitHub stars~550 tokensUpdated 25 days ago
Auto-check: notes
Configuring Vision
oxbshw/watch-skill
The user wants to connect an LLM or vision provider, already has an API key, asks "can I use OpenAI/Anthropic/Gemini/OpenRouter", wants local Ollama, or needs different cheap and strong models.
469 GitHub stars~509 tokensUpdated 25 days ago
Auto-check: notes
The Loop
oxbshw/watch-skill
The user built or changed something visual — a UI, an animation, a game, a generated video — and wants it verified, or asks "why does my UI look wrong", "check that the fix actually worked", "does…
469 GitHub stars~622 tokensUpdated 25 days ago
Auto-check: notes
Video Memory
oxbshw/watch-skill
The user asks about videos watched in the past or across sessions — "have we watched anything about X", "which video showed that error", "what did that meeting decide", "search my videos", or a…
469 GitHub stars~569 tokensUpdated 25 days ago
Auto-check: notes
Watching Videos
oxbshw/watch-skill
The user shared a video URL, a YouTube/TikTok/stream link, a local video file, a screen recording, a meeting recording, or a playlist/folder of videos — "watch this", "summarize this video", "what's…
469 GitHub stars~599 tokensUpdated 25 days ago
Auto-check: notes
Extracting Structure
oxbshw/watch-skill
The user wants structure pulled out of a watched video — "make chapters for this video", "where does the bug appear in this recording", "turn this screen recording into a bug report", "how strong is…
469 GitHub stars~490 tokensUpdated 25 days ago
Auto-check: notes

Works with

DeepSeek

Questions about Learning From Mistakes

What does Learning From Mistakes do?

The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. Learning From Mistakes is an agent skill from oxbshw/watch-skill. The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong.

When should I use Learning From Mistakes?

Learning From Mistakes fits situations like: AI & LLM Engineering work in your project.

How do I install Learning From Mistakes in Claude Code?

Run `npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a claude-code`. Or copy the skill folder (skills/learning-from-mistakes in oxbshw/watch-skill) into .claude/skills/learning-from-mistakes in your project. Claude Code loads it when a task matches its description.

How do I install Learning From Mistakes in Codex?

Run `npx skills add oxbshw/watch-skill --skill learning-from-mistakes -a codex`. Or copy the skill folder (skills/learning-from-mistakes in oxbshw/watch-skill) into .agents/skills/learning-from-mistakes in your project. Codex loads it when a task matches its description.

Can I use Learning From Mistakes 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 oxbshw/watch-skill --skill learning-from-mistakes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/learning-from-mistakes, .gemini/skills/learning-from-mistakes, .github/skills/learning-from-mistakes and .opencode/skills/learning-from-mistakes in your project.

What does Learning From Mistakes need to run?

SKILL.md names no scripts, command-line tools or credentials: Learning From Mistakes is instructions for the agent only. Its frontmatter pre-approves these tools: Bash, Read.

Does Learning From Mistakes 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 Learning From Mistakes safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Learning From Mistakes use?

Learning From Mistakes is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Learning From Mistakes use?

About 380 tokens (SKILL.md is roughly 1.5k 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 Learning From Mistakes?

Skills that share tags, products or a category with Learning From Mistakes: Dingo Verify (MigoXLab/dingo, 757 stars), Deepseek Helper (dongsheng123132/u-claw, 1.8k stars), SimPO Preference Training (Orchestra-Research/AI-Research-SKILLs, 13k stars) and slime RL Post-Training (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Learning From Mistakes?

oxbshw (a GitHub user) maintains it in oxbshw/watch-skill, which has 469 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 14, 2026.

Source: oxbshw/watch-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Learning From Mistakes

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Learning from mistakes

Report a correction

See what has been learned

The savings meter

Files

Compare with similar skills

Similar skills

More from oxbshw/watch-skill

Related

Questions about Learning From Mistakes