CtrlK
BlogDocsLog inGet started
Tessl Logo

ci-workflow-sync

FastGPT CI workflow 双轨同步。当用户修改或新增 .github/workflows/ 下的 GitHub Actions workflow 时必须触发:同步更新 .forgejo/workflows/ 对应文件保持功能一致,或判断是否需要新建 Forgejo 版本。涉及 CI、GitHub Actions、Forgejo Actions、镜像构建、container registry、artifact、workflow yaml 改动、build-* workflow、test-* workflow 时也使用此技能。即使用户只提到"改一下 CI"或"加个 workflow"也应触发。

69

Quality

85%

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

71%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 highly actionable with concrete YAML patterns and a solid validation-backed workflow, but it is over-long for a single file and repeats some content. Splitting the conversion-pattern reference and before/after fragment into a references/ file would improve progressive disclosure.

Suggestions

Move the 11-pattern '转换模式参考表' and the '完整 Before/After 片段' into a references/ file (e.g. references/conversion-patterns.md), keeping SKILL.md as an overview that links to it — this raises progressive_disclosure and trims conciseness redundancy.

Deduplicate the repeated 'Capture proxy envs from variables' block (patterns 5, 6, and 11) by defining it once and referencing it, to cut ~40 lines of repetition.

Make the validation feedback loop explicit in '同步操作流程' step 5 — add 'if validation fails, fix the YAML and re-run validation before proceeding' to push workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

Content is high-value repo-specific knowledge Claude would not already know, but the ~530-line body repeats material: the proxy-capture block recurs across patterns 5/6/11 and the '完整 Before/After 片段' largely re-shows patterns 1/2/5/7, so it could be tightened via deduplication.

3 / 5

Actionability

Eleven conversion patterns each give copy-paste-ready YAML before/after with exact env var names, plus concrete validation commands (yaml.safe_load, actionlint) and a 12-item checklist covering common build/test cases.

5 / 5

Workflow Clarity

A clear 6-step '同步操作流程' includes an explicit YAML validation checkpoint and a verification checklist, but the validate→fix→re-validate retry loop is implied rather than spelled out as explicitly as the top anchor.

4 / 5

Progressive Disclosure

Good internal section structure (decision tree, pattern table, checklist), but all detail — the 11-pattern reference and full before/after fragment — is inlined in a 530-line SKILL.md with no external reference files split out despite no bundle files existing.

3 / 5

Total

15

/

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 specific, comprehensive, and uses appropriate third-person voice with strong natural trigger terms. It cleanly answers both what the skill does and when to invoke it, with negligible conflict risk.

DimensionReasoningScore

Specificity

Names the domain and multiple concrete actions — '同步更新 .forgejo/workflows/ 对应文件保持功能一致' and '判断是否需要新建 Forgejo 版本' — with comprehensive coverage of the sync workflow.

5 / 5

Completeness

Explicitly answers both what (dual-track sync / decide whether to create a Forgejo version) and when ('当用户修改或新增 .github/workflows/...时必须触发', '即使用户只提到...也应触发') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural-term coverage including casual user phrasings ('改一下 CI', '加个 workflow') plus technical synonyms (GitHub Actions, Forgejo Actions, container registry, artifact, build-* / test-* workflow).

5 / 5

Distinctiveness Conflict Risk

Occupies a clear narrow niche — FastGPT CI dual-track GitHub↔Forgejo sync — with distinct triggers and minimal overlap risk with other skills.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (534 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
labring/FastGPT
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.