reasoning-trace-optimizer

Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, and performance regressions.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./examples/interleaved-thinking/SKILL.md

Quality

Content

57%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 body is actionable with concrete code and commands across multiple modes, but it is padded with conceptual explanation Claude already knows and lacks validation feedback loops in its iterative optimization workflow. Progressive disclosure is weak because everything is inlined into one file with no bundle references.

Suggestions

Trim the 'Interleaved Thinking' conceptual rationale and 'This is critical because...' list; assume Claude knows reasoning-model basics.

Add an explicit validation/feedback step to the optimization loop (e.g., score check → if below threshold, diagnose and retry) so the batch workflow has a checkpoint.

Move the full per-mode code examples and CLI reference into reference files linked from a concise overview to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with code examples and a pattern table, but it spends tokens explaining interleaved thinking and its rationale ('This is critical because...') that assumes Claude lacks knowledge it already has.	3 / 5
Actionability	Provides concrete, mostly executable Python code for each usage mode plus CLI and slash-command examples, with only minor gaps (e.g., undefined tool_executor helpers).	4 / 5
Workflow Clarity	The optimization loop is shown as a sequence, but this iterative/batch operation lacks explicit validation checkpoints or error-recovery feedback loops, capping workflow clarity at 3.	3 / 5
Progressive Disclosure	The skill is a single monolithic file with reasonable section headers, but content that could live in separate references (full API examples, CLI reference, hook integration) is inlined, and referenced docs are external rather than bundle files.	3 / 5
	Total	13 / 20 Passed

Description

66%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 specific and lists numerous concrete analysis targets, but it omits any explicit 'when to use' trigger guidance, which caps its completeness. Distinctiveness and trigger-term quality are solid.

Suggestions

Append an explicit 'Use when...' clause naming concrete trigger phrases (e.g., 'Use when debugging agent failures, repeated task failures, or reasoning trace analysis').

Add a few user-natural synonyms (e.g., 'agent debugging', 'why did my agent fail') alongside the technical pattern names.

Dimension	Reasoning	Score
Specificity	Names the domain ('Debug and optimize AI agents') and lists multiple concrete analysis targets (reasoning traces, context degradation, tool confusion, instruction drift, repeated task failures, performance regressions), with only minor gaps in action coverage.	4 / 5
Completeness	The 'what' is clear, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user debugging agents would say ('reasoning traces', 'repeated task failures', 'performance regressions') with good coverage, though some phrases lean technical and a few common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	The reasoning-trace analysis niche is mostly distinct from general debugging skills, with only minor overlap risk against closely related agent-optimization skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
Path: examples/interleaved-thinking/SKILL.md
Commit: 6dbe1a1

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.