lightrun-slow-execution-diagnosis

Diagnose performance incidents in running services with Lightrun MCP: slow endpoints, latency or SLO regressions, timeouts, deadline-exceeded errors, hangs, and slowness that is intermittent, sporadic, occasional, happens only sometimes, or appears only under load. Use when diagnosing a performance incident; prefer this over lightrun-live-runtime-debugging, including for mixed slow-and-incorrect cases. Use slow-execution snapshots when a duration boundary separates problematic executions; use focused active-path snapshots or call stacks for known hangs that may not reach an end marker. Select the narrowest code section, derive an evidence-based threshold, and correlate captured state with code and telemetry. Use lightrun-live-runtime-debugging for non-performance diagnosis and lightrun-ask-prod for one-off timing, when available; otherwise report the scope gap. Do not use for pull-request review, code changes, setup, deployment, or post-deployment performance validation.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

77%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 well-structured, actionable, and clearly sequenced with validation checkpoints and feedback loops. Its main weakness is progressive disclosure: it references bundle files that are not present, breaking navigation to the detail it depends on.

Suggestions

Add the missing references/mcp-tool-discovery.md and references/slow-execution-snapshot-workflow.md files, or remove the references and inline the essential steps so the skill is self-contained.

Trim governing parentheticals like 'Treat exposed schemas and descriptions as authoritative' to improve token efficiency.

Make the non-threshold capture path as concrete as the slow-execution quickstart by showing a representative regular-snapshot create call.

Dimension	Reasoning	Score
Conciseness	Lean imperative prose with no basic-concept padding and an efficient quickstart block; a few governing clauses ('Treat exposed schemas and descriptions as authoritative') could be trimmed. Not a 5 because minor tightening remains.	4 / 5
Actionability	Provides a concrete copy-paste execution_duration_create({...}) call with real parameters and named poll branches; mostly executable but the surrounding guidance stays somewhat abstract, leaving minor gaps versus fully copy-paste-ready across all cases.	4 / 5
Workflow Clarity	Sequenced phases (Preflight, Checkpoint, evidence path, target selection, runtime support, capture, return) with an explicit checkpoint ('Proceed to evidence-path selection only after source discovery passes') and feedback loops for create/retry and action disposition on destructive runtime actions.	5 / 5
Progressive Disclosure	The body signals two one-level-deep references (references/mcp-tool-discovery.md, references/slow-execution-snapshot-workflow.md), but the references/ directory does not exist in the bundle, so the referenced paths are missing despite being clearly signaled.	3 / 5
	Total	16 / 20 Passed

Description

100%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 exemplary: it states concrete capabilities, comprehensive natural trigger terms with synonyms, explicit what/when guidance, and clear boundaries against sibling skills. It is dense without padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions—'Select the narrowest code section, derive an evidence-based threshold, and correlate captured state with code and telemetry'—plus specific snapshot types and error classes, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (diagnose performance incidents via snapshots/thresholds) and when ('Use when diagnosing a performance incident; prefer this over lightrun-live-runtime-debugging') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms with synonyms: 'slow endpoints, latency or SLO regressions, timeouts, deadline-exceeded errors, hangs' and 'intermittent, sporadic, occasional, happens only sometimes...under load'.	5 / 5
Distinctiveness Conflict Risk	Names sibling skills (lightrun-live-runtime-debugging, lightrun-ask-prod) and explicit exclusions ('Do not use for pull-request review, code changes, setup, deployment'), carving a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: lightrun-platform/lightrun-ai
Path: skills/lightrun-slow-execution-diagnosis/SKILL.md
Commit: d2b954c

Reviewed: about 6 hours 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.