CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sol-loop

Use when the user says "sol loop".

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/tstack/skills/sol-loop/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

96%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 an exceptionally lean, executable workflow with concrete commands, a copy-paste reviewer brief, explicit stop conditions, and error-recovery paths. The only structural headroom is that a longer skill could layer an overview or split reference material, keeping it just below top marks on progressive disclosure.

DimensionReasoningScore

Conciseness

The body is telegraphic and dense ("Do not stash, discard, or include unrelated changes", "Budget end is not approval") with zero concept explanations and no padding — every line is instruction. It clearly matches anchor 5 ("every token earns its place") rather than anchor 4, since no over-explanation exists to trim.

5 / 5

Actionability

It gives exact commands (`git status --short`, `gh pr view <n> --json baseRefName,headRefOid`, `git merge-base HEAD origin/<baseRefName>`, `delegate_task` with role/mode) plus a copy-paste round-1 brief template with severity definitions and a reply format. This is fully executable guidance covering the common cases (PR, local, no remote), matching anchor 5.

5 / 5

Workflow Clarity

Five numbered phases plus an upfront Budget section, with explicit validation checkpoints ("Run covering checks", "Re-run checks and `git diff --shortstat <base>`") and error-recovery loops (timeout/failure handling, dispute escalation after two replies, "If review grew the diff, cut first"). Clear sequence with explicit validation and feedback loops matches anchor 5.

5 / 5

Progressive Disclosure

Well-organized single-file workflow with clear section headers and no buried references, and no bundle files exist to layer. It falls short of anchor 5 because at ~114 lines there is no overview/quick-start layering or content split (e.g. the brief template or budget rules could live apart), placing it at "good structure; minor organization gaps".

4 / 5

Total

19

/

20

Passed

Description

38%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 is a pure trigger clause: highly distinctive for invocation, but it says nothing about what the skill does, so it fails as a discovery description. It matches the 'only when, no what' bad pattern despite the excellent trigger phrase.

Suggestions

State what the skill does in the description, e.g. "Runs OpenAI's GPT Sol as a reviewer over your current diff or PR in iterative rounds, applying minimal fixes until it approves."

Add natural trigger variations beyond the exact phrase, such as "Use when the user says 'sol loop' or asks to run a Sol review loop on their changes."

Combine what and when in a single sentence following the strong example pattern: capability list first, then an explicit 'Use when...' clause.

DimensionReasoningScore

Specificity

The description is only 'Use when the user says "sol loop"' — no concrete actions or capabilities are stated anywhere. It matches anchor 1 ("no concrete actions") and not anchor 2, because it does not even name the domain (Sol-based code review) explicitly.

1 / 5

Completeness

Only the 'when' is present ("Use when the user says 'sol loop'") while the 'what' is entirely absent — the exact anchor-2 pattern ("only 'when' is present without 'what'"). It is not a 3 because the 'what' is not merely weakly implied; it is completely missing.

2 / 5

Trigger Term Quality

The quoted phrase "sol loop" is a natural invocation a user would actually say, but it is the sole trigger term with no variations or synonyms (e.g. "review loop", "run Sol on this PR"). This fits anchor 3: some relevant keywords but missing common variations.

3 / 5

Distinctiveness Conflict Risk

The trigger is an exact quoted phrase ("sol loop"), which virtually no other skill would fire on, giving minimal conflict risk per anchor 5. It is not a 4 because the trigger is not merely "mostly distinct" — it is an unambiguous literal match with no overlap risk.

5 / 5

Total

11

/

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

adamsardo/tstack-marketplace

Path

plugins/tstack/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.