CtrlK
BlogDocsLog inGet started
Tessl Logo

homelab-sre-agent

Applies Site Reliability Engineering practices to homelab operations including SLOs, toil reduction, and incident management.

51

Quality

56%

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 ./skills/homelab-sre-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 and token-efficient with a clear incident workflow, but it lacks executable specifics — no commands, scripts, or templates turn the SRE responsibilities into action. Adding concrete tooling examples and validation checkpoints would materially raise the score.

Suggestions

Add executable specifics: sample SLO YAML/promql burn-rate queries, an Ansible task snippet for toil automation, and a post-mortem template.

Insert validation checkpoints into the incident workflow (e.g., verify mitigation restored the SLO before proceeding to root-cause analysis).

Annotate the Google SRE Book reference with when to consult each chapter rather than leaving a bare URL.

DimensionReasoningScore

Conciseness

The body uses lean bullet/numbered lists and avoids explaining concepts Claude already knows (no definition of SLOs or toil); the only trimmable redundancy is the intro line restating the frontmatter description.

4 / 5

Actionability

Guidance is directive but high-level ('Define availability and latency targets', 'Propose automation ... scripts, cron jobs, Ansible tasks') with no executable commands, code, templates, or concrete tooling specifics, matching the 2-anchor's high-level hints missing specific steps.

2 / 5

Workflow Clarity

The incident-management section is a clear 6-step sequence (Detect → Triage → Mitigate → Root cause → Post-mortem → Action items), but it has no explicit validation checkpoints or feedback loops, matching the 3-anchor of sequenced steps with missing checkpoints.

3 / 5

Progressive Disclosure

The skill is well-organized into clearly headed sections and is short enough (~45 lines) that inline content is appropriate; the single external reference (Google SRE Book URL) is clearly signaled, leaving only minor organization gaps (the bare URL lacks context on when to consult it).

4 / 5

Total

13

/

20

Passed

Description

58%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 clearly names its niche, but it omits any explicit trigger guidance ('Use when...'), capping completeness at 3 and limiting trigger-term quality. It is solid but not exemplary.

Suggestions

Add a 'Use when ...' clause with concrete triggers (e.g., 'Use when managing homelab reliability, setting SLOs, reducing toil, or running incident reviews').

Include natural user phrasings and synonyms such as 'error budget', 'post-mortem', 'on-call', and 'uptime' to broaden trigger coverage.

Expand the action list toward comprehensive coverage (e.g., mention error-budget tracking, post-incident reviews, hardening) to reach the 5-anchor.

DimensionReasoningScore

Specificity

Names the domain ('homelab operations') and several concrete SRE actions ('SLOs, toil reduction, and incident management'), sitting between the 3-anchor (1-2 actions) and 5-anchor (comprehensive list), with minor coverage gaps.

4 / 5

Completeness

Clearly states 'what' (applies SRE practices including SLOs, toil, incidents) but provides no 'Use when...' trigger guidance, so per the rubric completeness is capped at 3.

3 / 5

Trigger Term Quality

Contains relevant SRE terms ('Site Reliability Engineering', 'SLOs', 'toil', 'incident management') but lacks common user-spoken variations and synonyms; not the comprehensive natural-phrase coverage of the 4/5 anchors.

3 / 5

Distinctiveness Conflict Risk

The 'homelab' + 'SRE' niche is distinct with minimal conflict risk, though the listed companion skills (monitoring-analyst, change-planner) indicate minor overlap with closely related skills.

4 / 5

Total

14

/

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
pvnkmnk/AgenticSelfHostSkills
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.