lightrun-live-runtime-debugging

Diagnose live bugs and incidents that require runtime evidence from a running service using Lightrun MCP. Use when static analysis or logs cannot explain the failure mechanism, when a hypothesis must be tested against live values or control flow, or when resuming Lightrun async actions. For latency, timeout, deadline, SLO, or hang diagnosis, use lightrun-slow-execution-diagnosis when available; if unavailable, continue here with best-effort evidence. Do not use for one-off production measurements (use lightrun-ask-prod when available; otherwise report the measurement-scope gap), pull-request review, code changes, setup, or deployment.

Quality

83%

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

Quality

Content

78%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 a lean, action-oriented debugging workflow with clear sequencing, validation checkpoints, and well-structured one-level references. It is strong across all dimensions; conciseness, actionability, and workflow clarity sit at 4 due to minor tightening/checklist-integration opportunities rather than real deficiencies.

Suggestions

Consolidate the validation and feedback-loop guidance (preflight, post-result reassessment, error mitigation) into one explicit validate→fix→retry checklist to push workflow_clarity toward 5.

Tighten the Action Error Mitigation bullets by merging the redundant no-hit/timeout sub-points to improve conciseness.

Add a one-line pointer near the Quick Use Guide to the handoff outcome branches so the end-to-end flow is navigable from a single section.

Dimension	Reasoning	Score
Conciseness	The body is dense, imperative, and free of concept over-explanation (no 'what is MCP' padding); every section delivers actionable guidance. A few mitigation bullets could be tightened, placing it at 4 rather than a fully lean 5.	4 / 5
Actionability	Concrete, executable guidance throughout — 'read [MCP tool discovery](references/mcp-tool-discovery.md) and complete its source-discovery preflight', explicit async activation gates, and structured handoff fields — with only minor gaps, fitting the 4 anchor; absence of code is not penalized for this instruction-only skill.	4 / 5
Workflow Clarity	A clear 7-step Quick Use Guide plus validation checkpoints (preflight failure returns a blocker, 'reassess information gain' after each result, cleanup) and explicit error-recovery feedback loops cover most checkpoints; it stops short of a single integrated validate→fix→retry checklist, so 4 not 5.	4 / 5
Progressive Disclosure	Two one-level-deep references (references/mcp-tool-discovery.md, references/async-actions.md) are both real files, clearly signaled via markdown links in context, with detail appropriately split out and a well-organized overview body — matching the 5 anchor.	5 / 5
	Total	17 / 20 Passed

Description

87%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 well-crafted: it states concrete capabilities, provides explicit 'Use when...' trigger guidance, and sharply distinguishes itself from sibling Lightrun skills via routing and exclusions. Minor trigger-term and specificity gaps keep two dimensions at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain (live runtime debugging) and several concrete actions — 'Diagnose live bugs and incidents that require runtime evidence', 'tested against live values or control flow', 'resuming Lightrun async actions' — with only minor coverage gaps, fitting the 4 anchor better than the fully comprehensive 5.	4 / 5
Completeness	Explicitly answers both what ('Diagnose live bugs and incidents that require runtime evidence from a running service using Lightrun MCP') and when ('Use when static analysis or logs cannot explain the failure mechanism...') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Strong natural incident-debugging keywords ('live bugs', 'incidents', 'runtime evidence', 'latency, timeout, deadline, SLO, or hang') with synonyms grouped together; a few common phrasings a user might say are missing, so 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	Actively routes to sibling skills (lightrun-slow-execution-diagnosis, lightrun-ask-prod) and lists explicit exclusions (no PR review, code changes, setup, deployment), giving a clear niche with minimal conflict risk per the 5 anchor.	5 / 5
	Total	18 / 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: lightrun-platform/lightrun-ai
Path: skills/lightrun-live-runtime-debugging/SKILL.md
Commit: d2b954c

Reviewed: 2 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.