axiom-sre

Expert SRE investigator for incidents and debugging. Uses hypothesis-driven methodology and systematic triage. Can query Axiom observability when available. Use for incident response, root cause analysis, production debugging, or log investigation.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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.

A high-quality, actionable SRE playbook with strong workflow sequencing and validation feedback loops. Its two weaknesses are mild repetition of the discovery rule and reference files that are named in the body but absent from the bundle.

Suggestions

Create the missing reference/ files referenced in the body (apl.md, grafana.md, metrics.md, memory-system.md, query-patterns.md, etc.) or remove the dangling references so progressive disclosure navigation resolves.

Consolidate the 'discover before querying' guidance into one canonical location instead of restating it across Golden Rule #9, Section 1, and Section 4.A Step 0.

Trim motivational framing ('You stay calm under pressure', 'Every incident leaves the system smarter') to keep the opening as lean as the protocol sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with tight numbered protocols, tables, and executable code, and it largely assumes Claude's competence; docked one point because the 'discover before query' rule is restated across Golden Rule #9, Section 1, and Section 4.A Step 0, and a few motivational lines ('You stay calm under pressure') add mild padding.	4 / 5
Actionability	Fully executable guidance throughout — concrete bash invocations (scripts/init, scripts/discover-axiom), copy-paste APL blocks, explicit flag requirements, and a worked Tool Reference section covering the common cases.	5 / 5
Workflow Clarity	The investigation protocol is a clearly sequenced loop (Discover → Code Context → Hypothesize → Execute → Verify → Record) with explicit validation checkpoints and feedback loops (self-heal on 404, conclusion-validation self-check, 'Stuck: 3 queries → re-read discovery'); the bug-fix protocol requires proving the test fails first.	5 / 5
Progressive Disclosure	The body acts as an overview and cleanly signals one-level-deep reference files (apl.md, grafana.md, metrics.md, etc.) with an index, but the referenced reference/ directory does not exist in the bundle, so the signaled navigation points to missing material.	3 / 5
	Total	17 / 20 Passed

Description

90%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.

A strong, well-targeted description that answers what and when with natural trigger phrases and a distinct niche. Its only mild weakness is specificity: the named actions lean methodological rather than enumerating concrete operations.

Dimension	Reasoning	Score
Specificity	Names the SRE domain and a couple of concrete actions ('query Axiom observability', 'systematic triage', 'hypothesis-driven methodology'), but the actions are largely methodological rather than discrete concrete operations, leaving coverage non-comprehensive.	3 / 5
Completeness	Clearly answers both 'what' ('Expert SRE investigator... Uses hypothesis-driven methodology') and an explicit 'when' ('Use for incident response, root cause analysis, production debugging, or log investigation').	5 / 5
Trigger Term Quality	Comprehensive natural phrases users would actually say — 'incident response', 'root cause analysis', 'production debugging', 'log investigation' — covering synonyms and overlap variants.	5 / 5
Distinctiveness Conflict Risk	A clear niche (SRE incident investigation backed by Axiom observability) with distinct triggers and minimal overlap with unrelated skills.	5 / 5
	Total	18 / 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
skill_md_line_count	SKILL.md is long (518 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: openclaw/clawhub
Path: .agents/skills/axiom-sre/SKILL.md
Commit: 694ff71

Reviewed: 1 day 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.