CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sol-loop

Review a change in rounds with GPT 6.1 Sol as a separate reviewer until it approves or the budget runs out. Use when the user says "sol loop" or asks for a Sol review loop before shipping.

Quality

95%

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

100%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 exceptionally tight operational skill: dense imperative prose, exact commands, a copy-paste-ready reviewer brief, and a five-phase loop with explicit validation, failure handling, and stop conditions. It is fully self-contained with nothing that belongs in separate reference files.

DimensionReasoningScore

Conciseness

Every line is instruction with zero explanation of concepts Claude already knows ('Keep a ledger: id, severity, outcome, usage if returned. Never guess usage.'; 'A timeout, error, or no reply is not approval.'). Lean and dense throughout; nothing to trim toward anchor 4.

5 / 5

Actionability

Fully executable guidance: exact commands (`git merge-base HEAD origin/<PR base or default branch>`, `codex exec -m gpt-6.1-sol -`, `codex exec resume <SESSION_ID>`, `git diff --shortstat <base>`) and a copy-paste-ready round-1 brief template with severity definitions. Matches anchor 5 (copy-paste ready commands covering the common cases); it does not fall to anchor 4 because no key detail is missing for executing the loop.

5 / 5

Workflow Clarity

Clear five-phase sequence (Scope, Start Sol, Answer findings, Next round, Stop and ship) with explicit validation checkpoints ('never send code the change breaks', 'Re-run checks and git diff --shortstat', 'if review grew the diff, cut first') and error-recovery feedback ('On failure, cancel, confirm it stopped, and restart with the ledger'). Anchor 5; the destructive/batch cap does not apply since this is a review loop with validation present.

5 / 5

Progressive Disclosure

The skill is self-contained with no bundle files, and nothing in the body warrants extraction — the brief template, budget rules, and ledger conventions are needed on every invocation. Numbered, well-labeled sections make navigation trivial, so content is appropriately placed in a single SKILL.md, matching anchor 5's 'content appropriately split' in the trivial sense that all content belongs inline.

5 / 5

Total

20

/

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 description: it states a concrete, well-bounded capability in third person and pairs it with an explicit 'Use when' clause carrying literal user trigger phrases. The only room for improvement is broader synonym coverage in the trigger terms and slightly fuller coverage of the skill's actions.

DimensionReasoningScore

Specificity

Names a concrete mechanism ('Review a change in rounds with GPT 6.1 Sol as a separate reviewer until it approves or the budget runs out') with a precise termination condition, but covers essentially one action without mentioning the answer-findings or ship steps. Matches anchor 4 (several specific actions, minor gaps) rather than 3 because the mechanism and stopping condition are explicit, and not 5 because coverage of the skill's actions is not comprehensive.

4 / 5

Completeness

Explicitly answers both what ('Review a change in rounds with GPT 6.1 Sol as a separate reviewer until it approves or the budget runs out') and when ('Use when the user says "sol loop" or asks for a Sol review loop before shipping') with concrete trigger phrases — a direct match for anchor 5.

5 / 5

Trigger Term Quality

'sol loop', 'Sol review loop', and 'before shipping' are phrases a user would naturally say in this niche. Good keyword coverage but missing common variations such as 'run Sol on this' or 'GPT review', so it fits anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

'GPT 6.1 Sol' and 'sol loop' occupy a unique niche with distinct, unambiguous triggers; no realistic overlap with other skills. Clear match for anchor 5 (clear niche with distinct triggers, minimal conflict risk).

5 / 5

Total

18

/

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

robinebers/openusage

Path

.agents/skills/sol-loop/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.