agentleFS
Sign inStart free
yevhens-hueyevhens-hue/claude-skills-starter-kit/skills/agent-introspection-debugging/SKILL.md

agent-introspection-debugging

Skill4 starsChanged 3 months agoMITView on GitHub

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use unified-memory, brand-discovery and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • gongyijie85Skill

    unified-memory

    Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.

    Also in 3 projects that use this

  • ysyecustSkill

    brand-discovery

    Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand tension across 8 modules using laddering, 5 Whys, and projective techniques. Produces a resumable session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).

    Also in 3 projects that use this

  • ysyecustSkill

    competitive-platform-analysis

    Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong to, and which sources to mine. First step in the three-skill competitive pipeline; precedes benchmark-methodology.

    Also in 3 projects that use this

  • mturacSkill

    mle-workflow

    Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

    Also in 4 projects that use this

  • InfopibeSkill

    everything-claude-code

    Also in 3 projects that use this

  • junimnjwSkill

    agent-harness-construction

    Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

    Also in 3 projects that use this

  • +2 more from ysyecust

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 23 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Scenario C (Missing Credentials): Run without API keys. Verify graceful failure log and administrator alert dispatch.

    line 17
  2. Distinctive:

    Document Verified Components (tested empirically under failure assertions).

    line 20
  3. Distinctive:

    Document Unverified Gaps (edge cases requiring additional test coverage).

    line 21

“Common” is measured: kept by at least 6 in 10 of the 23 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

🕵️ Agent Introspection & Failure Injection Debugging Skill

This skill governs structured self-debugging and failure injection testing for AI agents and distributed systems.

🛠️ Failure Injection Protocol

  1. Synthetic Failure Scenarios:
    • Scenario A (Database Timeout): Simulate PostgreSQL / Redis connection drop. Verify fallback memory cache triggers cleanly.
    • Scenario B (Rate Limit 429): Inject simulated LLM HTTP 429 response. Verify exponential backoff retry logic.
    • Scenario C (Missing Credentials): Run without API keys. Verify graceful failure log and administrator alert dispatch.
  2. System Recovery & Verification Map:
    • Document Verified Components (tested empirically under failure assertions).
    • Document Unverified Gaps (edge cases requiring additional test coverage).

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free