CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

antithesis-skills-feedback

File a bug report or feedback on the Antithesis skills by opening a pre-filled GitHub issue URL (skill name, skill version, agent, short summary). Load when the user wants to report a problem with, or give feedback on, any Antithesis skill. Does not auto-submit — presents the URL for the user to review.

Quality

94%

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

92%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.

An excellent, highly actionable single-purpose skill: it provides the exact URL, every pre-fillable field with fill guidance, a complete example, an explicit length-limit contingency with escalation, and a clear do-not-auto-submit guard. The only trims available are the duplicated leave-blank guidance and the hardcoded skill version in the body.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no explanations of concepts Claude already knows, and each section earns its tokens. Minor trimmable redundancy keeps it below the top anchor: the leave-blank guidance for `expected` and `context` is stated both in the field table and again in step 8, and the body hardcodes a time-sensitive skill version ("2026-10-21 4f8d80b") that duplicates the frontmatter and conflicts with step 2's instruction to obtain the version via `git rev-parse`. Efficient with minor instances that could be trimmed — anchor 4, not 5.

4 / 5

Actionability

Fully executable guidance: the exact base URL, a complete field table with types and what to fill, the exact command (`git -C <skills-repo> rev-parse --short HEAD`), explicit percent-encoding rules, a concrete 2000-character limit, and a copy-paste-ready example URL covering the common case. Matches the top anchor; nothing is left as vague direction.

5 / 5

Workflow Clarity

Eight clearly sequenced steps with an explicit conditional checkpoint for the URL-length failure mode and an escalation path (shorten fields → drop `agent-explanation` → drop `what-happened`), plus an explicit safety guard ("Do NOT auto-submit... Open the URL (or print it if no browser is available)"). This is a non-destructive single task, so no destructive-operation validation cap applies, and the error-recovery branch matches the top anchor.

5 / 5

Progressive Disclosure

The skill is self-contained (~65-line body, no references/, scripts/, or assets/ bundles exist, and none are needed), organized into clear sections (Base URL → Pre-filling fields → How to construct → URL length limit → Example URL → Presenting to the user). Per the simple-skill guidance, a short skill with no need for external references scores 5 with well-organized sections.

5 / 5

Total

19

/

20

Passed

Description

92%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 the concrete action (opening a pre-filled GitHub issue), enumerates the pre-filled fields, gives an explicit load condition with natural trigger phrasing, and honestly bounds its behavior (no auto-submit). The only gap is a few missing trigger synonyms such as "file an issue" or "bug".

DimensionReasoningScore

Specificity

The description names the concrete mechanism ("opening a pre-filled GitHub issue URL") and enumerates exactly what gets pre-filled ("skill name, skill version, agent, short summary"), while explicitly bounding behavior ("Does not auto-submit — presents the URL for the user to review"). This matches the anchor for multiple specific concrete actions with comprehensive coverage; there are no minor gaps that would drop it to 4.

5 / 5

Completeness

It explicitly answers both halves: what ("File a bug report or feedback on the Antithesis skills by opening a pre-filled GitHub issue URL") and when ("Load when the user wants to report a problem with, or give feedback on, any Antithesis skill") with concrete trigger phrases. Neither half could be more explicit, so it matches the top anchor rather than anchor 4.

5 / 5

Trigger Term Quality

"Load when the user wants to report a problem with, or give feedback on, any Antithesis skill" provides good natural trigger terms ("report a problem", "give feedback", "bug report"), but common variations like "file an issue", "open an issue", or "bug" are absent. This fits good keyword coverage with a few natural terms missing, above anchor 3 (which expects missing common variations entirely) but below anchor 5's synonym-level comprehensiveness.

4 / 5

Distinctiveness Conflict Risk

The trigger is tightly scoped to "any Antithesis skill" bug reports and feedback — a clear niche with distinct triggers that no other skill would plausibly match. Minimal conflict risk, matching the top anchor.

5 / 5

Total

19

/

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

antithesishq/antithesis-skills

Path

antithesis-skills-feedback/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.