CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

adversarial-review

Challenge a triage outcome before a maintainer acts on it publicly. Use for the goldfish triage reviewer and for any independent pass that should try to refute a decision rather than restate it.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, high-signal instruction skill: every line carries project-specific review standards, concrete challenge procedures, and explicit escalation rules, with no filler. Its main gaps are the absence of executable command examples and an explicit stepwise sequence with feedback loops, plus an unverifiable external reference.

DimensionReasoningScore

Conciseness

The body is lean and entirely project-specific — e.g., 'Existing code and tests show behavior, not intent' and cited standards like 'Fix the cause that makes the bug possible... (fm #5236; pf #11998 #17266)' — with no padded explanation of concepts Claude already knows; the one time-sensitive date (2026-07-28) is confined to the 'Known smells' old-patterns section, so anchor 5 applies rather than 4.

5 / 5

Actionability

Concrete, executable procedures appear throughout — 'apply the exact regression patch in a clean checkout, then run the focused regression and a neighboring control', 'Return `maintainer` instead of deciding these yourself' — but some checks remain directional ('Establish what FastMCP promises from the protocol, released docs, history') and there are no copy-paste commands, matching anchor 4; per the scoring notes code absence is not penalized for an instruction-only skill, so it stays above anchor 3.

4 / 5

Workflow Clarity

The review procedure is well structured: a categorized challenge checklist ('The contract', 'The evidence', 'Closures', ...), an explicit escalation checkpoint ('Return `maintainer` instead of deciding these yourself'), and an embedded verification procedure for reproductions; however there is no explicit end-to-end sequence or output feedback loop, and the body (~57 lines) exceeds the under-50-line simple-skill exception, so anchor 4 fits better than 5 or 3.

4 / 5

Progressive Disclosure

A self-contained single file with well-organized sections and one clearly signaled one-level reference ([review-issue](../review-issue/SKILL.md), which does not resolve within this bundle); the 14-item maintainer-standards catalog is inline reference-style material that could arguably live in a separate file, so anchor 4 fits — good structure with minor organization gaps — rather than 5.

4 / 5

Total

17

/

20

Passed

Description

82%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: it states one concrete action in an explicit niche and pairs it with an explicit 'Use for...' trigger clause naming both the specific reviewer and the general independent-pass case. Coverage of capability variations is thin (one core action) and a few natural synonyms are missing, but conflict risk is minimal.

DimensionReasoningScore

Specificity

Names the domain ('triage outcome') and 1-2 concrete actions ('Challenge a triage outcome before a maintainer acts on it publicly', 'refute a decision rather than restate it'), which matches anchor 3; it does not list several distinct capabilities, so it is not a 4, and the actions are concrete rather than generic, so not a 2.

3 / 5

Completeness

Explicitly answers both: what ('Challenge a triage outcome before a maintainer acts on it publicly') and when ('Use for the goldfish triage reviewer and for any independent pass that should try to refute a decision rather than restate it') with concrete trigger phrases, matching anchor 5; the 'Use when' cap does not apply since an explicit trigger clause exists.

5 / 5

Trigger Term Quality

Natural phrases a user would say are present — 'triage outcome', 'maintainer', 'refute a decision', 'independent pass', 'goldfish triage reviewer' — giving good keyword coverage, though a few natural synonyms (e.g., 'second opinion', 'push back') are missing and 'goldfish' is project jargon, keeping it below anchor 5 and above anchor 3.

4 / 5

Distinctiveness Conflict Risk

'goldfish triage reviewer', 'triage outcome', and 'maintainer acts on it publicly' define a clear niche with distinct triggers and minimal conflict risk with other skills, matching anchor 5.

5 / 5

Total

17

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

PrefectHQ/fastmcp

Path

.agents/skills/adversarial-review/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.