CtrlK
BlogDocsLog inGet started
Tessl Logo

working-with-jj

Expert guidance for using JJ (Jujutsu) version control system. Use when working with JJ, whatever the subject. Operations, revsets, templates, debugging change evolution, etc. Covers JJ commands, template system, evolog, operations log, and interoperability with git remotes.

81

1.26x
Quality

75%

Does it follow best practices?

Impact

90%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./working-with-jj/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

Highly actionable and concise command reference for JJ, but workflow clarity is capped by missing validation/feedback steps for batch and destructive operations, and progressive disclosure is weakened by a broken reference to a non-existent revsets.md file.

Suggestions

Add explicit validation checkpoints and feedback loops for risky/batch operations (e.g. run `jj log`/`jj diff` to verify after `jj split`, `jj rebase`, or `jj absorb`, and confirm with the user before destructive batch transforms).

Fix or remove the broken `references/revsets.md` reference — either add the file or point to the existing `references/command-syntax.md` section that covers revsets.

Tighten the Common Pitfalls section to command-only examples, moving rationale into the existing reference files to reduce inline verbosity.

DimensionReasoningScore

Conciseness

Mostly lean with executable command tables and minimal concept re-explanation, but a few sections (e.g. inline comments and the Common Pitfalls exposition) could be trimmed; it does not over-explain basics Claude already knows.

4 / 5

Actionability

Provides copy-paste-ready, fully executable commands across essential, additional, revset, and recovery operations with inline annotations covering the common cases.

5 / 5

Workflow Clarity

Commands are well-categorized but multi-step and risky/batch operations (jj split, jj rebase, jj absorb, jj-batch-desc, jj-checkpoint) lack explicit validation checkpoints or feedback loops; the batch/destructive cap applies and holds this at 3.

3 / 5

Progressive Disclosure

Structure with separate references/ and scripts/ bundles is reasonable, but the body references `references/revsets.md` which does not exist in the bundle, a broken one-level reference that undermines navigation.

3 / 5

Total

15

/

20

Passed

Description

78%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, specific description that clearly identifies the JJ niche and provides an explicit use-trigger. It is held back from top marks only by trigger-term variety and slightly generic "when" phrasing.

DimensionReasoningScore

Specificity

Lists several concrete capability areas — "Operations, revsets, templates, debugging change evolution" and "JJ commands, template system, evolog, operations log, and interoperability with git remotes" — giving broad coverage with only minor gaps; not quite the exhaustive enumeration of a 5.

4 / 5

Completeness

Provides a clear "what" ("Expert guidance for using JJ...") and an explicit "Use when working with JJ" trigger, satisfying both halves; the "when" could be more specific about concrete trigger scenarios rather than a broad catch-all.

4 / 5

Trigger Term Quality

Includes natural terms users would say ("JJ", "Jujutsu", "version control", "git remotes") but lacks common synonyms/extensions and variety that would push it to a 5.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (JJ/Jujutsu specifically) with distinct triggers and minimal overlap risk with git-focused skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
YPares/agent-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.