CtrlK
BlogDocsLog inGet started
Tessl Logo

arn-spark-stress-premortem

This skill should be used when the user says "pre-mortem", "premortem", "risk analysis", "stress premortem", "failure analysis", "what could go wrong", "pre mortem", "investigate failure", "failure modes", or wants to stress-test a product concept by applying Gary Klein's pre-mortem methodology to identify hypothetical failure root causes, early warning signals, and mitigation strategies. Produces a pre-mortem report with 3 root causes across distinct failure dimensions and recommended concept updates.

74

Quality

92%

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

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a well-structured, actionable orchestration skill with clear sequencing, validation feedback loops, and appropriate offloading of detail to reference files. The main weakness is redundancy: the root-cause/adversarial requirements are repeated across the task spec, validation step, and error-handling section.

Suggestions

Consolidate the adversarial/root-cause requirements so they are stated once (e.g., in the investigation task) and referenced by Step 4 and Error Handling rather than restated in each place.

Remove or trim the Agent Invocation Guide table, which currently contains only one real row and a speculative "future" row that adds no actionable value.

Tighten the opening four-step summary, which largely previews the Workflow section that immediately follows it.

DimensionReasoningScore

Conciseness

Mostly efficient and free of basic-concept padding, but the adversarial/root-cause requirements are restated across Step 3's investigation task, Step 4's validation, and the Error Handling section, and the Agent Invocation Guide table adds little value (one real row plus a speculative "future" row).

2 / 3

Actionability

Highly actionable for an instruction-only skill: concrete paths, a named agent (arn-spark-forensic-investigator) with model dispatch, a literal context-block format, a 6-column recommendation schema, and copy-paste-ready retry phrasing.

3 / 3

Workflow Clarity

Six clearly sequenced steps with an explicit validation checkpoint and feedback loop in Step 4 (validate → retry with adversarial instruction → proceed and note gap), plus a dedicated Error Handling section covering the main failure modes.

3 / 3

Progressive Disclosure

Step 1 explicitly loads two one-level-deep references (premortem-protocol.md and premortem-report-template.md), both of which exist in ./references/, keeping the body an overview while detailed protocol and template live in separate files.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong across all dimensions: it states concrete outputs, provides an extensive list of natural trigger phrases, covers both what and when, and occupies a distinctive niche. Its only weakness is mild verbosity in the trigger list and the passive "This skill should be used when the user says" framing.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "identify hypothetical failure root causes, early warning signals, and mitigation strategies" and "Produces a pre-mortem report with 3 root causes across distinct failure dimensions and recommended concept updates" — matching the anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ("Produces a pre-mortem report with 3 root causes...") and when ("This skill should be used when the user says..."), satisfying the explicit-triggers anchor for both.

3 / 3

Trigger Term Quality

Strong coverage of natural terms a user would say — "pre-mortem", "premortem", "risk analysis", "failure analysis", "what could go wrong", "failure modes" — including common spelling variants, matching the good-coverage anchor.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Gary Klein's pre-mortem methodology for product concepts) with distinctive triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
AppsVortex/arness
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.