CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

xp-predict-problems

Predict production failures and high-risk paths with a Lean/XP lens. Use when the user asks to predict failures, production risk, or edge cases.

Quality

80%

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 ./.agents/skills/xp-predict-problems/SKILL.md
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 lean, well-organized instruction-only skill with a clear single task and explicit focus and explanation requirements. Its main gaps are actionable specificity — no output format, severity ranking, or analysis method — and a small amount of trimmable persona framing.

Suggestions

Specify an output structure, e.g., 'For each predicted failure, state: failure mode, plausibility, triggering production scenario, severity (high/medium/low), and suggested mitigation.'

Add a brief analysis sequence (e.g., scan entry points and external calls first, then complexity hotspots, then weakly tested paths) so results are reproducible.

Trim the Lean/XP framing sentence ('Use small steps, clarity, and deep understanding...') or replace it with a concrete instruction.

DimensionReasoningScore

Conciseness

The body is tight and assumes competence, but "Use small steps, clarity, and deep understanding of failure modes to improve reliability" is vague framing that could be trimmed. It is not 5 because that line does not earn its tokens; not 3 because the rest is efficient with no padding.

4 / 5

Actionability

Concrete focus categories ("edge cases, data assumptions, external dependencies", "high complexity, weak tests, or unclear intent") and required explanation points give some actionable guidance, but there is no output format, severity ranking, or analysis method. It is not 4 because key execution details are missing; not 2 because the guidance goes beyond high-level hints.

3 / 5

Workflow Clarity

As a single-task skill the action is unambiguous: predict failures, focus on the listed areas, and explain plausibility, trigger scenario, and evolvability benefit. It is not 5 because there is no suggested analysis sequence or output structure; not 3 because the task and its checkpoints (the three explanation requirements) are explicit.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, needs no external references (none exist in the bundle), and is organized into clear Task/Focus/Explain sections. Per the simple-skill guidance this warrants a 5.

5 / 5

Total

16

/

20

Passed

Description

78%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 concise, well-structured description that clearly states both capability and explicit trigger conditions in third person. Its main weaknesses are limited action specificity (no method or output described) and a trigger set that misses common synonyms like "what could go wrong".

Suggestions

Add one or two more concrete actions or outputs (e.g., 'rank failure risks by severity and suggest mitigations') to raise specificity.

Expand triggers with natural synonyms users would say, such as 'what could go wrong', 'failure modes', or 'production risks'.

Clarify what 'with a Lean/XP lens' concretely changes about the output, since it currently reads as light jargon.

DimensionReasoningScore

Specificity

"Predict production failures and high-risk paths" names the domain and 1-2 concrete actions but offers no method or deliverables. It is not score 4 because it does not list several specific actions with only minor gaps.

3 / 5

Completeness

It explicitly answers both "what" ("Predict production failures and high-risk paths with a Lean/XP lens") and "when" ("Use when the user asks to predict failures, production risk, or edge cases") with concrete trigger phrases. Not 4 because the "when" clause is already explicit and specific, not merely present.

5 / 5

Trigger Term Quality

"Use when the user asks to predict failures, production risk, or edge cases" covers good natural trigger phrases. It is not 5 because common variations such as "what could go wrong", "failure modes", or "risks" are missing.

4 / 5

Distinctiveness Conflict Risk

The production-failure-prediction niche with a Lean/XP lens is mostly distinct from other skills. Not 5 because the trigger "edge cases" is broad and could overlap with general coding, code-review, or security-review skills.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

saski/arnesto

Path

.agents/skills/xp-predict-problems/SKILL.md

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.