CtrlK
BlogDocsLog inGet started
Tessl Logo

ljg-push

把 ~/.agents/skills/ljg-* 里所有更新过的 skills 同步到 github repo (ljg-skills),先推 master 分支(org-mode 输出风格),再切 md 分支(markdown 输出风格)做基础 markdown 化后推。Use when user says '/ljg-push', 'push skills', '推送 skills', '同步 skills', 'sync ljg', or whenever ljg-* skills get updated and need shipping. NOT FOR pushing non-ljg skills or arbitrary git repos.

62

Quality

75%

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 ./skills/ljg-push/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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.

The body is information-dense and operationally focused with a genuine validation gate, but it leans on referenced files (Workflows/Push.md, Tools/Push.sh) that are missing from the bundle, weakening actionability, workflow clarity, and navigation. Tightening the inline date handling and either bundling or inlining the referenced workflow would lift the score.

Suggestions

Bundle the referenced Workflows/Push.md and Tools/Push.sh (or inline their essential steps) so the main workflow is executable without broken references.

Move the '2026-06-12 起' migration detail into a clearly labeled 'History / old patterns' or 'Deprecated' section so time-sensitive information does not dilute the active instructions.

Surface the master→md→switch-back sequence with explicit validation checkpoints inline (e.g., abort-on-README-drift style gates for each branch push) rather than relying on the absent Push.md.

DimensionReasoningScore

Conciseness

The body is mostly lean and operational without explaining concepts Claude already knows, but inline time-sensitive detail ('2026-06-12 起含 org 文件本体') is not isolated in a deprecated/old-patterns section, which the rubric penalizes.

2 / 3

Actionability

Concrete elements exist (the notify curl block, --dry-run/--skip-readme-check flags, hardcoded repo paths), but the core execution path defers to 'Tools/Push.sh' which is not present in the bundle, leaving the main instructions incomplete.

2 / 3

Workflow Clarity

The README consistency gate is an explicit validation checkpoint and branch ordering is stated ('master 必须先推'), yet the detailed step sequence lives in the absent 'Workflows/Push.md' rather than inline, so checkpoints for the main flow are not directly visible.

2 / 3

Progressive Disclosure

Sections are well organized, but the only external references ('Workflows/Push.md', 'Tools/Push.sh') point to files that do not exist in the bundle (no references/scripts/assets directories), so navigation is broken rather than one-level-deep and clearly signaled.

2 / 3

Total

8

/

12

Passed

Description

100%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, specific description that clearly states capabilities, provides natural multilingual triggers, and draws an explicit boundary against misuse. It fully satisfies the what/when/which-skill requirements.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — sync updated ljg-* skills to the github repo, push master (org-mode), switch to md branch and markdown-ize before pushing — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (sync/push both branches) and when via a clear 'Use when…' clause with enumerated triggers.

3 / 3

Trigger Term Quality

Covers natural user phrases in both English and Chinese ('/ljg-push', 'push skills', '推送 skills', '同步 skills', 'sync ljg') that a user would naturally say when needing this skill.

3 / 3

Distinctiveness Conflict Risk

Tightly scoped to ljg-* skills with an explicit negative boundary ('NOT FOR pushing non-ljg skills or arbitrary git repos'), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

Passed

Validation

81%

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

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 missing

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

16

Passed

Repository
lijigang/ljg-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.