CtrlK
BlogDocsLog inGet started
Tessl Logo

chaos-dr-test

Use when working with Chaos Engineering steps inside a Harness pipeline. Covers ChaosFault, ChaosProbe, ChaosAction steps (DRTest stages), the Chaos step (DRTest stages), and DRTest stage/pipeline structure. Use when the user asks to add, modify, or create chaos steps, fault injection, probes, or disaster recovery test pipelines. Do not use for standalone Chaos Experiment create or edit; use chaos-experiment for those. Trigger phrases: DR test, DRTest pipeline, disaster recovery test, chaos step, ChaosFault step, ChaosProbe step, ChaosAction step.

69

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, actionable body with concrete MCP call patterns, a YAML scaffold, and solid validation guidance for destructive pipeline updates. Its main weakness is a broken reference to a missing scope-establishment.md file that the workflow marks as mandatory.

Suggestions

Add the missing references/scope-establishment.md file (or inline its scope rules) so the mandatory 'establish org/project scope before mutating calls' step is actually resolvable; also fix the ../../references/scope-establishment.md link path.

De-duplicate the tool-result-verification and full-replace-PUT warnings — state each once in the relevant section and cross-reference rather than repeating across the MANDATORY block, Performance Notes, and Troubleshooting.

Surface the key step-building mechanics (or a condensed checklist) inline in the body so the core task is executable without first opening references/components.md.

DimensionReasoningScore

Conciseness

The body is largely lean and rule-driven without explaining concepts Claude already knows, but the tool-result-verification rule and the full-replace-PUT caution are each restated across the MANDATORY block, Performance Notes, and Troubleshooting — minor redundancy that could be trimmed. Not 5 due to this repetition; not 3 because there is no concept padding.

4 / 5

Actionability

Concrete MCP call signatures with argument patterns (e.g. harness_create(resource_type="chaos_dr_test", org_id=..., body={...})) and a copy-paste-ready YAML scaffold make the guidance executable; the gap is that the core step-population mechanics are delegated to references/components.md rather than shown inline. Not 5 because the primary task detail lives in the reference; not 3 because what is inline is concrete and runnable.

4 / 5

Workflow Clarity

A clear sequence is present — Step 0 intent detection, routing to create/edit, then the shared step-building hub — with explicit validation (fetch current YAML before the full-replace PUT; wait for the tool's confirmed response before reporting success) and a troubleshooting feedback loop for erased fields. Not 5 because the detailed execution steps are distributed across the reference files rather than fully sequenced in the body; the destructive-operation validation cap is satisfied.

4 / 5

Progressive Disclosure

Structure is good with one-level-deep references to components.md, create.md, and edit.md (all present and clearly signaled), but the body cites references/scope-establishment.md for the mandatory scope-establishment step and that file does not exist in the bundle (the markdown link also uses a stray ../../ path). A broken reference to a critical prerequisite file undermines navigation. Not 4 because a missing mandatory reference is more than a minor organization gap; not 2 because most structure and references are sound.

3 / 5

Total

15

/

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.

A strong description that clearly states what the skill does, when to use it, and how it differs from the related chaos-experiment skill. It provides concrete trigger phrases with natural synonyms and stays in the appropriate imperative/third-person voice.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and entities — 'add, modify, or create chaos steps, fault injection, probes, or disaster recovery test pipelines' and names the specific step types (ChaosFault, ChaosProbe, ChaosAction, Chaos) — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

It explicitly answers both 'what' ('Covers ChaosFault, ChaosProbe, ChaosAction steps... and DRTest stage/pipeline structure') and 'when' ('Use when working with Chaos Engineering steps inside a Harness pipeline', 'Use when the user asks to add, modify, or create...'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

An explicit 'Trigger phrases' list supplies natural synonyms a Harness user would say — 'DR test', 'DRTest pipeline', 'disaster recovery test', 'chaos step' — alongside the component-name triggers, covering the natural phrasing space comprehensively.

5 / 5

Distinctiveness Conflict Risk

A clear niche (DR Test pipelines with DRTest stages) plus explicit boundary guidance — 'Do not use for standalone Chaos Experiment create or edit; use chaos-experiment for those' — minimizes conflict with the sibling skill.

5 / 5

Total

20

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
harness/harness-ai
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.