CtrlK
BlogDocsLog inGet started
Tessl Logo

jules

Delegate coding tasks to Google Jules AI agent for asynchronous execution. Use when user says: 'have Jules fix', 'delegate to Jules', 'send to Jules', 'ask Jules to', 'check Jules sessions', 'pull Jules results', 'jules add tests', 'jules add docs', 'jules review pr'. Handles: bug fixes, documentation, features, tests, refactoring, code reviews. Works with GitHub repos, creates PRs.

73

Quality

92%

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 highly actionable, well-structured command reference with complete executable examples and a clear workflow sequence; minor gains available from deduplicating repeated snippets and adding a diff-verification step before the auto-commit flow.

Suggestions

Factor out the repeated `git diff --name-only HEAD~3` file-gathering snippet into a single shared variable or helper so the 'Add Tests' and 'Add Documentation' templates don't duplicate it verbatim.

Add an explicit validation checkpoint in the Git Integration flow (e.g. `git diff --stat` review or a sanity check) between `jules remote pull --apply` and `git add -A && git commit` to catch bad applies before they are committed.

Consider moving the AGENTS.md template block and the template-prompt recipes into a `references/` file so the main SKILL.md body stays a lean overview.

DimensionReasoningScore

Conciseness

Mostly lean command/code reference with little over-explanation, but the git-diff file-gathering pattern is repeated verbatim across the 'Add Tests' and 'Add Documentation' templates and could be factored out.

4 / 5

Actionability

Fully executable, copy-paste-ready bash and curl examples (full JSON payloads, complete poll-until-complete loops, git apply/commit flow) covering the common CLI and API cases.

5 / 5

Workflow Clarity

Clear setup->create->monitor->retrieve sequence with explicit poll-loop state checks (COMPLETED/FAILED) and auth/repo verification, but the git apply-then-commit flow lacks a verify-diff checkpoint before committing.

4 / 5

Progressive Disclosure

Single well-organized file with clear section headers and easy navigation; no external references are needed for this cheat-sheet style, though the AGENTS.md template and template-prompt blocks could optionally be split out.

4 / 5

Total

17

/

20

Passed

Description

100%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: third-person voice, concrete capabilities, an explicit 'Use when user says' trigger clause with many natural phrasings, and a clear niche that avoids overlap with other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Handles: bug fixes, documentation, features, tests, refactoring, code reviews' and 'creates PRs') with comprehensive coverage rather than vague language.

5 / 5

Completeness

It explicitly answers both what ('Delegate coding tasks to Google Jules AI agent for asynchronous execution') and when ('Use when user says: ...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

The 'Use when user says:' clause enumerates many natural phrases users would actually say ('have Jules fix', 'delegate to Jules', 'jules add tests', 'jules review pr'), giving comprehensive keyword coverage including synonyms.

5 / 5

Distinctiveness Conflict Risk

The Google Jules niche and 'Jules'-prefixed triggers make it clearly distinguishable from other skills with minimal conflict risk.

5 / 5

Total

20

/

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 missing, 1 deeper-than-1-level

Warning

Total

15

/

16

Passed

Repository
sanjay3290/ai-skills
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.