bosskuai-agent-introspection SKILL.md skillA

bosskuai-agent-introspection from wankimmy/bossku-superpowers is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wankimmy/bossku-superpowers/bosskuai-agent-introspection@git:20261010.cd73169

Pins git:20261010.cd73169 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wankimmy/bossku-superpowers
Path
skills/bosskuai-agent-introspection/SKILL.md
Versions recorded
3
Latest version
git:20261010.cd73169, committed Oct 10, 2026
First version recorded
Jul 16, 2026
Size
5,984 bytes
Repository stars
22
License
MIT

Use when an agent run loops, burns tokens, drifts, or returns empty/degraded results: self-debugging with failure capture, diagnosis, contained recovery, and a report.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Agent Introspection Debugging

Use this skill when an agent run is failing repeatedly, consuming tokens without progress, looping on the same tools, or drifting away from the intended task.

This is a workflow skill, not a hidden runtime. It teaches the agent to debug itself systematically before escalating to a human.

## When to Activate

- Maximum tool call / loop-limit failures
- Repeated retries with no forward progress
- Context growth or prompt drift that starts degrading output quality
- File-system or environment state mismatch between expectation and reality
- Tool failures that are likely recoverable with diagnosis and a smaller corrective action

## Scope Boundaries

Activate this skill for:
- capturing failure state before retrying blindly
- diagnosing common agent-specific failure patterns
- applying contained recovery actions
- producing a structured human-readable debug report

Do not use this skill as the primary source for:
- feature verification after code changes; use the project's verification gate (`bosskuai-laravel-verification` for Laravel)
- framework-specific debugging when a narrower bosskuai skill already exists (e.g. `bosskuai-diagnose-loop`)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wankimmy/bossku-superpowers/bosskuai-agent-introspection@sha256:39990de17a43a36c

The line at the top of this page pins the label git:20261010.cd73169, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_vmbzztclhpvtslmm.svg)](https://markdownregistry.com/a/art_vmbzztclhpvtslmm)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Jul 16, 2026 and Oct 10, 2026, about one every 43 days.

versioncommittedcommitsizeaudit
git:20261010.cd73169 latest2026-10-10 cd73169 5,984 BA view · diff
git:20260926.9bc2d602026-09-26 9bc2d60 5,987 BA view · diff
git:20260716.6355db62026-07-16 6355db6 6,243 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5984 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

wankimmy/bossku-superpowers · 22 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_vmbzztclhpvtslmm
GET https://markdownregistry.com/api/v1/resolve?ref=wankimmy/bossku-superpowers/bosskuai-agent-introspection
GET https://markdownregistry.com/api/v1/blob/39990de17a43a36cd405403009964cf734253e57085dd379e6689be5f636f00a

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wankimmy/bossku-superpowers

bosskuai Cursor rule
wankimmy/bossku-superpowers · .cursor/rules/bosskuai.mdc · BosskuAI co-founder contract — indicator, routing, ponytail, anti-slop, loop engineering, grounding.
git:20261009.037c4b1 · audit A · 22 stars
AGENTS.md@.omp AGENTS.md file
wankimmy/bossku-superpowers · .omp/AGENTS.md
git:20260802.2f685b9 · audit B · 22 stars
AGENTS.md AGENTS.md file
wankimmy/bossku-superpowers · AGENTS.md
git:20261009.037c4b1 · audit A · 22 stars
CLAUDE.md CLAUDE.md file
wankimmy/bossku-superpowers · CLAUDE.md
git:20260716.6355db6 · audit B · 22 stars
ab-testing SKILL.md skill
wankimmy/bossku-superpowers · skills/ab-testing/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program…
v2.0.0 · audit A · 22 stars
accessibility SKILL.md skill
wankimmy/bossku-superpowers · skills/accessibility/SKILL.md · Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that…
git:20260907.6a40a93 · audit A · 22 stars
ad-creative SKILL.md skill
wankimmy/bossku-superpowers · skills/ad-creative/SKILL.md · When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad…
v2.8.0 · audit A · 22 stars
ads SKILL.md skill
wankimmy/bossku-superpowers · skills/ads/SKILL.md · When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X…
v2.2.0 · audit A · 22 stars
ai-seo SKILL.md skill
wankimmy/bossku-superpowers · skills/ai-seo/SKILL.md · When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers…
v2.2.0 · audit A · 22 stars
analytics SKILL.md skill
wankimmy/bossku-superpowers · skills/analytics/SKILL.md · When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions…
v2.0.0 · audit A · 22 stars
animate-expo SKILL.md skill
wankimmy/bossku-superpowers · skills/animate-expo/SKILL.md · Build animations in React Native and Expo, making the decisions in the order that determines whether they feel right —…
git:20260907.6a40a93 · audit A · 22 stars
animate SKILL.md skill
wankimmy/bossku-superpowers · skills/animate/SKILL.md · Build an animation from scratch, making the decisions in the order that determines whether it feels right — should it…
git:20260907.6a40a93 · audit A · 22 stars

Every file in wankimmy/bossku-superpowers

Browse by kind, by grade A, or by owner.