CtrlK
BlogDocsLog inGet started
Tessl Logo

submit-solution

Guide a workshop attendee through committing their starter-agent decomposition and opening a PR with their solution + workshop feedback. Invoke when the user says "submit", "I'm done", "open a PR", or asks how to share their solution.

96

1.47x
Quality

95%

Does it follow best practices?

Impact

96%

1.47x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An efficient, highly actionable single-file workflow skill with executable commands, explicit checkpoints, conditional recovery branches, and a guardrail list. It does not over-explain and respects the context budget.

DimensionReasoningScore

Conciseness

The body is lean and directive with no padding or explanation of concepts Claude already knows ('git diff main -- agent-decomposition/agents/starter/agent.py', 'gh pr create --title ... --body-file -'); every line earns its place. Not level 2 because there is no unnecessary explanation to tighten.

3 / 3

Actionability

Provides fully executable, copy-paste-ready git/gh commands and a complete fill-in PR body template; concrete specifics like 'ls -t evals/reports/*/starter.json | head -1 | xargs cat ...' leave nothing abstract.

3 / 3

Workflow Clarity

A clearly sequenced 5-step process with explicit checkpoints and recovery branches ('If the diff is empty, they haven't edited starter — ask if they worked in a different file', 'If they don't have push rights... have them fork first') plus a 'Don't' guardrail list. Not level 2 because validation/feedback checkpoints are explicit rather than implicit.

3 / 3

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent), so this is a single-file skill under the simple-skill threshold; the body is organized into well-labeled sections (Steps 1–5, Don't) with clear navigation, which satisfies the simple-skill allowance for a 3.

3 / 3

Total

12

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 that clearly pairs a concrete capability statement with explicit, natural trigger phrases for a well-scoped niche. The only deduction is for imperative/second-person voice ('Guide...') instead of the prescribed third person ('Guides...').

Suggestions

Rewrite the description in third person to avoid the voice penalty: 'Guides a workshop attendee through committing their starter-agent decomposition and opening a PR with their solution + workshop feedback. Invoke when the user says "submit", "I'm done", "open a PR", or asks how to share their solution.'

DimensionReasoningScore

Specificity

Names concrete actions ('committing their starter-agent decomposition and opening a PR with their solution + workshop feedback') which would normally be a 3, but the imperative 'Guide a workshop attendee' is second-person/imperative voice rather than third person ('Guides...'), triggering the rubric's voice penalty of -1.

2 / 3

Completeness

Explicitly states what the skill does ('Guide a workshop attendee through committing... and opening a PR...') and an explicit trigger clause ('Invoke when the user says...'), satisfying both 'what' and 'when'.

3 / 3

Trigger Term Quality

Quotes natural user phrases '"submit", "I'm done", "open a PR"' and 'asks how to share their solution' — terms a workshop attendee would actually say, with good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

Targets a narrow niche (workshop solution submission PRs) with distinctive triggers unlikely to fire for unrelated skills; clearly distinguishable from general git/PR skills.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
anthropics/cwc-workshops
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.