Agent skill

Introspect

Agent self-debugging and recovery. An agent skill from softspark/ai-toolkit.

Apache-2.0Auto-check passedDevelopment

Install Introspect

skills CLI

$ npx skills add softspark/ai-toolkit --skill introspect -a claude-code

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

GitHub CLI

$ gh skill install softspark/ai-toolkit introspect --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/softspark/ai-toolkit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/skills/introspect .claude/skills/introspect && 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 "introspect" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/introspect into .claude/skills/introspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "introspect", 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/softspark/ai-toolkit/tree/main/app/skills/introspect

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 softspark/ai-toolkit --skill introspect -a codex

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

GitHub CLI

$ gh skill install softspark/ai-toolkit introspect --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/app/skills/introspect .agents/skills/introspect && 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 "introspect" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/introspect into .agents/skills/introspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "introspect", 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 softspark/ai-toolkit --skill introspect -a cursor

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

GitHub CLI

$ gh skill install softspark/ai-toolkit introspect --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/app/skills/introspect .cursor/skills/introspect && 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 "introspect" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/introspect into .cursor/skills/introspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "introspect", 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/softspark/ai-toolkit.git --path app/skills/introspect

--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 softspark/ai-toolkit --skill introspect -a gemini-cli

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

GitHub CLI

$ gh skill install softspark/ai-toolkit introspect --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/softspark/ai-toolkit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/app/skills/introspect .gemini/skills/introspect && 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 "introspect" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/introspect into .gemini/skills/introspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "introspect", 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 softspark/ai-toolkit introspect

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 softspark/ai-toolkit --skill introspect -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .github/skills && cp -r skills-src/app/skills/introspect .github/skills/introspect && 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 "introspect" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/introspect into .github/skills/introspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "introspect", 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 softspark/ai-toolkit --skill introspect -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 softspark/ai-toolkit introspect --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/softspark/ai-toolkit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/app/skills/introspect .opencode/skills/introspect && 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 "introspect" agent skill from https://github.com/softspark/ai-toolkit/tree/main/app/skills/introspect into .opencode/skills/introspect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "introspect", 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: introspect
GitHub stars: 179
Token cost: ~1.8k tokens
SKILL.md length: 918 words
Files: 1
Skills in repo: 112
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Agent self-debugging and recovery. An agent skill from softspark/ai-toolkit.

Works in 5 steps: Capture Failure State → Classify the Failure Pattern → Diagnose Root Cause → …
Making repeated errors
SKILL.md covers Step 1: Capture Failure State, Step 2: Classify the Failure…, Step 3: Diagnose Root Cause and Step 4: Select Recovery Action, plus 6 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Introspect is an agent skill from softspark/ai-toolkit. Agent self-debugging and recovery. Use when stuck in loops, making repeated errors, or quality degrades. Triggers: introspect, self-debug, stuck, loop, why failing.

Its SKILL.md is about 1.8k 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 Debugging. The repository describes itself as: Professional-grade AI coding toolkit: 94 skills, 44 agents, multi-platform (Claude, Cursor, Windsurf, Copilot, Gemini, Cline, Roo Code, Aider, Augment, Antigravity, Codex CLI… The licence is Apache-2.0.

When your agent uses it

Making repeated errors
Quality degrades

Example prompts

“/introspect”

Requirements

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

Workflow steps

5 steps, taken from the step headings in SKILL.md.

Capture Failure State
Classify the Failure Pattern
Diagnose Root Cause
Select Recovery Action
Produce the Introspection Report

What it can do on your machine

Read from SKILL.md and the folder at commit d64db2b. 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:
- Read
- Grep
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 markdown).
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

Introspect loads about 1.8k tokens when it runs. Until then it costs about 44 tokens; SKILL.md has 918 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~44
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

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

The full file from softspark/ai-toolkit at commit d64db2b, republished under its Apache-2.0 licence (© softspark). 918 words, ~1,820 tokens.

Download SKILL.mdSave it as .claude/skills/introspect/SKILL.md (or your agent's skills folder).

name: introspect
description: Agent self-debugging and recovery. Use when stuck in loops, making repeated errors, or quality degrades. Triggers: introspect, self-debug, stuck, loop, why failing.
allowed-tools: Read, Grep
user-invocable: true
effort: low
argument-hint: [symptom or 'stuck']
agent: debugger
context: fork

Agent Self-Debugging

$ARGUMENTS

Structured self-analysis for when the agent is stuck, looping, or producing degraded output.

Step 1: Capture Failure State

Before diagnosing, gather the facts. Answer each question concisely:

Question	Answer
Last goal/task	What was the agent trying to accomplish?
Actions taken	List the last 3-5 actions in order
Errors or unexpected results	What went wrong? What was expected vs actual?
Attempt count	How many times has this been tried?
Time spent	Rough estimate of effort so far

Step 2: Classify the Failure Pattern

Identify which pattern matches the current situation:

Pattern	Symptoms	Common Cause
Loop	Same action repeated 3+ times	Missing exit condition, wrong approach
Drift	Actions diverge from original goal	Lost context, scope creep
Assumption Error	Working with wrong mental model	Didn't read code, assumed behavior
Tool Misuse	Wrong tool for the job	Grep when should Read, Bash when should Edit
Context Overflow	Forgetting earlier findings	Too much context, need compaction
Wrong Abstraction	Over-engineering simple task	Premature abstraction, YAGNI violation
Missing Information	Can't proceed without data	Need to ask user, read more code

Pick the single best match. If multiple apply, pick the root cause pattern (the one that, if fixed, would resolve the others).

Step 3: Diagnose Root Cause

Answer these three questions:

What assumption was wrong? — Identify the specific belief that led to failure.
What information was missing? — What would have prevented the failure if known earlier?
What would a fresh start look like? — If starting over with current knowledge, what would the first action be?

Step 4: Select Recovery Action

Choose the smallest recovery action and apply the smallest possible fix — do not restart from scratch unless absolutely necessary:

Pattern	Recovery Action
Loop	Stop. Change approach entirely — different tool, different strategy, different angle.
Drift	Re-read the original user request verbatim. Reset scope to exactly what was asked.
Assumption Error	Read the actual code, file, or docs. Do not guess. Verify the mental model.
Tool Misuse	Switch to the correct tool. Read instead of Grep for full context. Edit instead of Bash for file changes.
Context Overflow	Summarize all findings so far in 5 bullet points. Compact and continue.
Wrong Abstraction	Delete the abstraction. Do the simplest, most direct thing that works.
Missing Information	Ask the user exactly ONE specific question. Do not guess.

Step 5: Produce the Introspection Report

Output exactly this format:

markdown

## Introspection Report

**Pattern:** [Loop|Drift|Assumption Error|Tool Misuse|Context Overflow|Wrong Abstraction|Missing Information]
**Root Cause:** [1-2 sentence diagnosis]
**Recovery Action:** [Specific next step]
**Confidence:** [HIGH|MEDIUM|LOW]

### What happened
[Brief timeline of actions taken — 3-5 bullet points max]

### What went wrong
[Specific diagnosis — what assumption failed, what was missed]

### What to do next
[ONE concrete action — not a plan, a single next step]

Rules

MUST name a specific failure pattern (Loop / Drift / Assumption Error / Tool Misuse / Context Overflow / Wrong Abstraction / Missing Information) — vague self-diagnosis is useless
MUST ground the diagnosis in concrete evidence (action traces, error messages, tool outputs) — not in feelings or hunches
NEVER retry the exact same action. If it failed once, it will fail again. Change something.
NEVER continue a loop "hoping it will work this time". Hope is not a strategy.
CRITICAL: after 3 failed attempts, escalate to the user with a concrete report of what was tried, what failed, and what you need — do not keep flailing
MANDATORY: the recovery action is ONE concrete next step, not a multi-phase plan. If you need a plan, use /plan.

Show full SKILL.md (407 more words)Show less

Gotchas

"Introspection" invoked mid-task can itself become a procrastination loop — spending effort diagnosing instead of acting. If the report takes longer to write than the next concrete action, skip the report and just change approach.
Context overflow is often invisible from inside the session — the model cannot reliably detect its own forgetting. External signals (user frustration, repeated explanations of the same fact) are the real diagnostic.
"Wrong abstraction" is frequently misdiagnosed as "Missing information". If adding data does not unlock the next step but simplifying the code does, the abstraction is the problem.
Ask-the-user is the escape hatch but it has a cost: user context-switching, latency, fatigue. Use it when you truly cannot proceed, not as a habit to avoid commitment.
The "fresh start" thought experiment works best when written down. Articulating "if starting over, my first action would be X" out loud often reveals the current approach's sunk-cost fallacy.

Self-Correction Checklist

These rules are non-negotiable during recovery:

Never retry the exact same action. If it failed once, it will fail again. Change something.
Never continue a loop "hoping it will work this time." Hope is not a strategy.
Prefer reading code over guessing behavior. Open the file. Read the function. Check the types.
When in doubt, ask the user rather than making assumptions. One specific question beats three wrong guesses.
A 2-line fix is better than a 50-line refactor. Solve the immediate problem first.
Check if the goal is still correct before optimizing the approach. Sometimes the task itself needs clarification.
If stuck for more than 3 attempts, escalate. Tell the user what you tried, what failed, and what you need.

When NOT to Use

For debugging user code (not agent self-debugging) — use /debug
For analyzing past sessions to find patterns — use /mem-search or /instinct-review
For writing a recovery plan that spans multiple steps — use /plan
When the user has already described the failure — respond directly, skip the structured introspection
As a procrastination mechanism — if the next action is obvious, take it instead of writing a report

Quick Self-Check (Use Before Retrying Anything)

Before taking the next action after introspection, answer:

Is this action different from what I already tried?
Am I working on the original goal, not a tangent?
Do I have enough information to succeed, or am I guessing?
Is this the simplest approach that could work?

If any answer is "no", stop and address that first.

Files

Just SKILL.md in app/skills/introspect of softspark/ai-toolkit.

Open the folder on GitHubat commit d64db2b

Compare with similar skills

Introspect 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.

Introspect compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Introspect this skillsoftspark/ai-toolkit	179	—	~1.8k	Automated safety check: Pass	Apache-2.0	yesterday
Trellis Session Insightmindfold-ai/Trellis	15k	4 repos	~1.7k	Automated safety check: Pass	AGPL-3.0	8 days ago
Native Data FetchingCherryHQ/cherry-studio-app	4k	6 repos	~2.9k	Automated safety check: Notes	MIT	4 days ago
Aoti Debugpytorch/pytorch	104k	1 repos	~1.7k	Automated safety check: Pass	Custom licence	today
Herdr Throwaway Reproductionherdrdev/herdr	43k	—	~2.4k	Automated safety check: Pass	Apache-2.0	yesterday
Systematic Debuggingultralisp/ultralisp	258	51 repos	~2.4k	Automated safety check: Pass	None	24 days ago

Similar skills

Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
15k GitHub starsUsed in 4 repos~1.7k tokens
DevelopmentAuto-check passed
Native Data Fetching
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
4k GitHub starsUsed in 6 repos~2.9k tokens
DevelopmentAuto-check: notes
Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
104k GitHub starsUsed in 1 repo~1.7k tokens
DevelopmentAuto-check passed
Herdr Throwaway Reproduction
herdrdev/herdr
Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.
43k GitHub stars~2.4k tokensUpdated yesterday
DevelopmentAuto-check passed
Systematic Debugging
ultralisp/ultralisp
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes
258 GitHub starsUsed in 51 repos~2.4k tokens
DevelopmentAuto-check passed
OpenLogi macOS Permissions Triage
AprilNEA/OpenLogi
Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.
23k GitHub stars~2.5k tokensUpdated 4 days ago
DevelopmentAuto-check: notes

Questions about Introspect

What does Introspect do?

Agent self-debugging and recovery. An agent skill from softspark/ai-toolkit. Introspect is an agent skill from softspark/ai-toolkit. Agent self-debugging and recovery.

When should I use Introspect?

Introspect fits situations like: making repeated errors; quality degrades.

How do I install Introspect in Claude Code?

Run `npx skills add softspark/ai-toolkit --skill introspect -a claude-code`. Or copy the skill folder (app/skills/introspect in softspark/ai-toolkit) into .claude/skills/introspect in your project. Claude Code loads it when a task matches its description.

How do I install Introspect in Codex?

Run `npx skills add softspark/ai-toolkit --skill introspect -a codex`. Or copy the skill folder (app/skills/introspect in softspark/ai-toolkit) into .agents/skills/introspect in your project. Codex loads it when a task matches its description.

Can I use Introspect 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 softspark/ai-toolkit --skill introspect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/introspect, .gemini/skills/introspect, .github/skills/introspect and .opencode/skills/introspect in your project.

What does Introspect need to run?

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

Does Introspect 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 Introspect 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 Introspect use?

Introspect is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Introspect use?

About 1.8k tokens (SKILL.md is roughly 7.3k 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 Introspect?

Skills that share tags, products or a category with Introspect: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Aoti Debug (pytorch/pytorch, 104k stars) and Herdr Throwaway Reproduction (herdrdev/herdr, 43k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Introspect?

softspark (a GitHub user) maintains it in softspark/ai-toolkit, which has 179 GitHub stars. The repository holds 112 skills in this directory. The repository was last updated on October 7, 2026.

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

Install Introspect

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Agent Self-Debugging

Step 1: Capture Failure State

Step 2: Classify the Failure Pattern

Step 3: Diagnose Root Cause

Step 4: Select Recovery Action

Step 5: Produce the Introspection Report

Rules

Gotchas

Self-Correction Checklist

When NOT to Use

Quick Self-Check (Use Before Retrying Anything)

Files

Compare with similar skills

Similar skills

More from softspark/ai-toolkit

Related

Questions about Introspect