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.

66

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 dense, concrete, and clearly sequenced, with real commands, flags, and a strong README-consistency validation gate. Its weaknesses are the heavy inline accumulation of mdize conversion minutiae and historical gotcha detail (including dated changes that belong in a changelog), and its references to Workflows/Push.md and Tools/Push.sh, which are absent from the provided bundle.

Suggestions

Move the fine-grained mdize conversion rules (the '自动转换的范围' bullet list and the mdize-related Gotchas) into a dedicated reference file (e.g. references/mdize-rules.md) and keep only a short summary plus the few rules that must be checked every push.

Relocate dated incident history ('2026-06-12 起', the resolved bug-pattern Gotchas like '互斥格式句不能只替换格式名') to an 'old patterns' / changelog section or drop them, so SKILL.md carries only currently operative instructions.

Ensure the referenced Workflows/Push.md and Tools/Push.sh are actually shipped in the skill bundle (or inline the essential steps in the 工作流 section), since the whole workflow currently depends on files that are not present.

DimensionReasoningScore

Conciseness

Mostly efficient — hardcoded paths, a compact branch-difference table, and terse examples — but the '自动转换的范围' section and the 18-bullet Gotchas list encode extremely fine-grained historical incident detail ('互斥格式句不能只替换格式名…', '输出契约不只在 Markdown 文档里…') that reads as accumulated changelog rather than current instruction, and inline time-sensitive dates ('2026-06-12 起') are not isolated in a deprecated/old-patterns section. This matches 'Mostly efficient but includes some unnecessary explanation or could be tightened'; it is not 4 because several Gotchas entries could be consolidated or moved out, and not 2 because nothing explains concepts Claude already knows.

3 / 5

Actionability

Concrete, executable material throughout: exact repo paths and URL ('SKILLS_REPO="$HOME/code/ljg-skills"', 'git@github.com:lijigang/ljg-skills.git'), runnable flags ('/ljg-push --skip-readme-check', '--dry-run'), a copy-paste curl notification block, and a precise README-gate procedure. This matches 'Mostly executable guidance; concrete code or commands with minor gaps' — the gap is that the core execution is delegated to 'Workflows/Push.md' and 'Tools/Push.sh', whose contents are not shown in the bundle. Not 5 for that same reason; not 3 because what is written is real commands and specifics, not pseudocode.

4 / 5

Workflow Clarity

The sequence is clearly stated and ordered — README consistency gate (hard gate that aborts on mismatch), master push first, then md conversion/push, then auto-switch back to master — with the rationale ('md 分支的 markdown 化基于 master 的 org 版本做转换'), plus a --dry-run checkpoint and pre-commit residual audits. This matches 'Clear sequence with most checkpoints present; minor validation gaps'. Not 5 because the actual step list lives in the referenced 'Workflows/Push.md', which is not available in the bundle, so the fine-grained steps and error-recovery loops cannot be confirmed; not 3 because explicit validation (README gate, dry-run, audits) is present for this batch operation.

4 / 5

Progressive Disclosure

The body has good section structure (仓库路径, 分支差异, 工作流, README 一致性, 自动转换范围, Examples, Gotchas), but it references 'Workflows/Push.md' and 'Tools/Push.sh' and neither file exists in the bundle (no references/, scripts/, or assets/ directories at all), and ~30 lines of intricate mdize conversion rules that belong in a dedicated reference file are inlined in SKILL.md. This matches 'Some structure but could be better organized; references present but not clearly signaled; content that should be separate is inline'. Not 4 because the referenced files are missing from the bundle and the inlined conversion-rule bulk is exactly the content the 4-anchor says should be placed out; not 2 because sections are well-labeled and navigable rather than a monolithic wall.

3 / 5

Total

14

/

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 a strong example: it states the concrete multi-branch sync pipeline, gives explicit bilingual trigger phrases and a situational trigger, and closes with a NOT-FOR boundary. All four rubric dimensions are clearly met at the top anchors.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — '把 ~/.agents/skills/ljg-* 里所有更新过的 skills 同步到 github repo', '先推 master 分支', '再切 md 分支…做基础 markdown 化后推' — covering the full pipeline (detect, sync, push master, convert, push md). This matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage'; a 4 would require minor gaps in coverage, but sync, both branches, and the conversion step are all named.

5 / 5

Completeness

It explicitly answers 'what' (syncs updated ljg-* skills to the ljg-skills github repo, pushing master then a markdown-ized md branch) and 'when' ('Use when user says /ljg-push, push skills, … or whenever ljg-* skills get updated and need shipping'). This matches the anchor 'Clearly and explicitly answers both what AND when with concrete trigger phrases'; 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Trigger coverage includes the literal command '/ljg-push' plus natural phrases in two languages — 'push skills', '推送 skills', '同步 skills', 'sync ljg' — plus the situational trigger 'whenever ljg-* skills get updated and need shipping'. This matches the anchor for comprehensive coverage including synonyms; a 4 would mean a few natural terms are missing, but both English and Chinese variants are present.

5 / 5

Distinctiveness Conflict Risk

It is scoped to a named repo ('ljg-skills'), named skill family ('ljg-*'), and adds an explicit exclusion — 'NOT FOR pushing non-ljg skills or arbitrary git repos' — which minimizes conflict with generic git/push skills. This matches 'Clear niche with distinct triggers; minimal conflict risk'; 4 would require minor overlap risk, but the NOT-FOR clause closes that.

5 / 5

Total

20

/

20

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.

Validation — 13 / 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.