skill-pressure-test

Interrogate a plan, decision, or design one question at a time until it holds — use to stress-test your own thinking before committing to it

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-pressure-test/SKILL.md

Quality

Content

81%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 a tight, actionable instruction-only skill with explicit checkpoints, a verification checklist, and feedback loops; it avoids padding and explains only what Claude would not already infer. Minor rhetorical trimming and the absence of file-splitting keep conciseness and progressive disclosure at 4 rather than 5.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with each bolded principle followed by concrete guidance; minor rhetorical flourishes (e.g., the "questionnaire" metaphor) could be trimmed, matching score 4 rather than the fully-lean 5.	4 / 5
Actionability	Concrete, executable guidance is given throughout, including a worked good-vs-bad question example ("What should happen when the token expires?"), matching the mostly-executable score-4 anchor; it stops short of copy-paste templates, so not a 5.	4 / 5
Workflow Clarity	The Workflow section sequences the process, the Stop Or Checkpoint Rules give explicit checkpoints, and the Verification section provides a checklist with feedback loops (reopening dependent work when evidence changes), matching the score-5 anchor.	5 / 5
Progressive Disclosure	Content is well-organized into clearly labeled sections with a single one-level reference (codex-host-adapter.md) and no nested references, matching the good-structure score-4 anchor; it does not split detail across files, so not a 5.	4 / 5
	Total	17 / 20 Passed

Description

57%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 names a clear niche and conveys both what and when, but it is weakened by second-person voice and trigger terms that are relevant yet lack the natural variations users would say. Tightening voice and adding concrete trigger phrases would lift it.

Suggestions

Rewrite in third person to avoid the "your own thinking" second-person construction (e.g., "Stress-tests a plan before the user commits to it").

Add concrete trigger phrases users would say, e.g., "Use when the user wants to pressure-test a plan, attack a design, or stress-test a decision before committing."

Include a few natural synonyms (e.g., 'pressure-test', 'attack', 'red-team') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Interrogate a plan, decision, or design one question at a time until it holds" names the domain and one core action, matching the score-3 anchor; reduced by 1 because the phrase "stress-test your own thinking" is second-person voice, per the voice penalty guideline.	2 / 5
Completeness	It states what (interrogate a plan one question at a time) and gives a when via "use to stress-test your own thinking before committing to it", satisfying both; the when-condition could be more explicit with concrete trigger phrases, matching score 4 rather than 5.	4 / 5
Trigger Term Quality	Terms like "interrogate", "stress-test", "plan", "decision", and "design" are relevant and somewhat natural, but common variations or synonyms a user might actually say are missing, matching the score-3 anchor.	3 / 5
Distinctiveness Conflict Risk	The niche of one-question-at-a-time interrogation of an existing plan is mostly distinct, with only minor overlap risk against related decision/exploration skills, matching the score-4 anchor rather than the fully-distinct score 5.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/skill-pressure-test/SKILL.md
Commit: 0093dab

Reviewed: 5 days 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.