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.

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ljg-push/SKILL.md

Quality

Content

38%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 well-structured and covers conversion edge cases thoroughly, but its central workflow is delegated to Push.md/Push.sh files that are absent from the bundle, leaving the skill non-actionable as shipped. The README hard-gate is a good validation checkpoint; the missing referenced files are the main weakness.

Suggestions

Ship Workflows/Push.md and Tools/Push.sh (or inline the concrete push sequence: rsync, version bump, commit, push per branch, switch-back) so the skill is executable without external files.

Move or trim the date-stamped conversion detail ('2026-06-12 起') into a short changelog/deprecated note rather than the main flow to improve token efficiency.

Tighten the Gotchas list by consolidating the overlapping conversion-caveat bullets into a single 'conversion pitfalls' reference.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-sectioned, but the '自动转换的范围' and the long Gotchas list pad with edge-case detail, and time-sensitive markers ('2026-06-12 起' appears twice) are not isolated in a deprecated/old-patterns section.	3 / 5
Actionability	The core executable workflow is deferred to 'Workflows/Push.md' and 'Tools/Push.sh', neither of which is present in the bundle; only peripheral items (repo paths, curl notify, --skip-readme-check / --dry-run flags) are concrete.	2 / 5
Workflow Clarity	The README-consistency hard gate is a genuine validation checkpoint (abort on mismatch), but the main push sequence is not sequenced in the body — it lives only in the missing Push.md/Push.sh, so the workflow is present but not self-contained.	3 / 5
Progressive Disclosure	Sections are well organized, but the body's only real drill-down targets ('Workflows/Push.md', 'Tools/Push.sh') do not exist in references/scripts/assets — the key navigation pointer is a broken reference, mirroring the buried-reference anti-pattern.	2 / 5
	Total	10 / 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.

The description is strong across all dimensions: concrete actions, bilingual natural trigger phrases, explicit what/when, and a clear negative boundary that prevents misfires.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions tied to specific paths: 'sync to github repo (ljg-skills)', 'push master branch (org-mode)', 'switch to md branch', 'do basic markdownization then push' — comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (sync updated ljg-* skills across master and md branches) and when via a concrete 'Use when user says ...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage including the slash command and bilingual synonyms: '/ljg-push', 'push skills', '推送 skills', '同步 skills', 'sync ljg', plus the behavioral trigger 'whenever ljg-* skills get updated and need shipping'.	5 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche (ljg-* skills, specific repo) with an explicit negative boundary 'NOT FOR pushing non-ljg skills or arbitrary git repos', giving minimal conflict risk.	5 / 5
	Total	20 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
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
Path: skills/ljg-push/SKILL.md
Commit: 44f4105

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.