stress-plan

Use when an implementation plan has just been written and before any code is written — hands the plan to a second model in a fresh context to attack it, then requires every finding to be closed or rejected in writing. Invoked by new-feat at the end of its planning step and by orchestrate once per phase, and worth running on its own for any plan whose assumptions have not been checked against the code.

Quality

84%

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

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.

A highly actionable, well-sequenced process skill with copy-paste-ready prompts and strong validation gating. Its main weakness is conciseness: the motivating war stories, while concrete, add length the checks do not strictly require.

Suggestions

Trim or footnote the illustrative war stories (vite minify, sourcemap, six-apps, GDPR erasure, dual-write build dir) so each check states the rule first and keeps the anecdote optional.

Consider moving the three Step-1 checks into a short checklist format so the verification criteria scan as items rather than prose.

If the attacker prompt is reused across skills, factor it into a referenced snippet to reduce body length and support progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of explanations Claude already knows, but several illustrative war stories (the vite minify no-op, the sourcemap leak, the six-apps issue, the GDPR erasure path, the dual-write build directory) pad the guidance beyond what the checks strictly require and could be tightened.	3 / 5
Actionability	Provides copy-paste-ready guidance: a verbatim attacker prompt, a named model ('fable'), concrete output paths (PLAN-REVIEW.md), explicit skip/never-skip criteria, and a specific escalation recipe (label needs:decision).	5 / 5
Workflow Clarity	Steps 0–4 plus Finish are clearly sequenced with explicit validation checkpoints — 'No implementation starts while a finding is open. Silence is not a rejection.' — three finding outcomes, re-run triggers, and a verify-by-breaking-input feedback loop for guards.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested or buried references, and appropriately self-contained since no bundle files exist; scored 4 rather than 5 because it is a single ~120-line file rather than an overview pointing to one-level-deep reference files.	4 / 5
	Total	17 / 20 Passed

Description

87%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, specific description that clearly states what the skill does and when to use it, with concrete trigger phrasing and a distinct niche. It is slightly below the top specificity anchor because the named actions are process-level rather than a comprehensive enumerated list.

Dimension	Reasoning	Score
Specificity	Names concrete actions — 'hands the plan to a second model in a fresh context to attack it' and 'requires every finding to be closed or rejected in writing' — giving several specific actions rather than vague claims, though it stops short of enumerating the sub-steps the body covers.	4 / 5
Completeness	Explicitly answers both what (attack the plan via a second model, close/reject every finding in writing) and when ('Use when an implementation plan has just been written and before any code is written') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Uses natural trigger phrases a user would say — 'implementation plan', 'before any code is written', 'plan whose assumptions have not been checked against the code' — with good coverage, though a few common synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — second-model plan red-teaming with mandatory finding closure — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	18 / 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: xchromo/osn
Path: .claude/skills/stress-plan/SKILL.md
Commit: 5438649

Reviewed: ~11 hours 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.