CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-introspection-debugging/SKILL.md

The canonical home for this skill is agent-introspection-debugging in affaan-m/ECC

SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is an efficient, well-sequenced debugging workflow with strong validation checkpoints and concrete templates throughout. Its only soft spot is progressive disclosure, where a single-file structure is appropriate but leaves no room for the one-level-deep reference pattern the top anchor rewards.

DimensionReasoningScore

Conciseness

The body is lean and instructional, using compact tables, templates, and checklists with no concept-padding or filler explaining things Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

Provides concrete, directly-usable capture/diagnosis/recovery/report templates plus a pattern table with explicit checks (e.g. ECONNREFUSED -> verify service health, URL, port); not 5 because the executable unit is template markdown rather than copy-paste runnable commands.

4 / 5

Workflow Clarity

A clear four-phase sequence (Capture -> Diagnose -> Recovery -> Report) with explicit validation checkpoints, a checklist demanding 'evidence that proves the fix worked', a success|partial|blocked result gate, and an 'Only then retry' loop, matching the 'clear sequence with explicit validation steps and feedback loops' anchor.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections with no nested references and integration pointers to sibling skills; not 5 because it is a single self-contained file with no overview-vs-detail split, though that is appropriate for a workflow skill with no bundle files.

4 / 5

Total

18

/

20

Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, third-person, and clearly pairs a what-when trigger, distinguishing itself well from sibling skills. Its main weakness is trigger-term coverage, which leans technical and omits common colloquial failure phrasings users would actually say.

Suggestions

Broaden the trigger phrase to include colloquial terms users naturally say, e.g. 'Use when an agent is stuck, looping on the same tools, spinning without progress, or failing repeatedly.'

Add at least one more distinct concrete trigger case so the 'when' clause matches multiple scenarios rather than a single situation.

DimensionReasoningScore

Specificity

Names the agent self-debugging domain and four concrete actions ('capture, diagnosis, contained recovery, and introspection reports'), matching the 'several specific actions with minor gaps' anchor; not 5 because the actions are process phases rather than a fully comprehensive set of discrete capabilities.

4 / 5

Completeness

Explicitly answers both 'what' (the four-phase debugging workflow) and 'when' ('Use when an agent run fails and you need a reproducible diagnosis instead of a retry'); not 5 because the trigger is a single specific case rather than multiple concrete trigger phrases.

4 / 5

Trigger Term Quality

Includes some relevant natural terms ('agent run fails', 'reproducible diagnosis', 'retry') but misses common user phrasings like 'agent is stuck', 'looping', or 'spinning', matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

Targets a clear niche (agent self-debugging) and explicitly distinguishes itself from verification-loop and narrower ECC skills, giving it minimal conflict risk per the 'clear niche with distinct triggers' anchor.

5 / 5

Total

16

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
affaan-m/ECC
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.