CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

environment-bootstrap

从源仓库向其他设备或用户级 Skill 目录恢复已登记的 Codex Skill,提供只读审计、显式应用、SHA-256 校验,并且不删除目标端额外文件。用于复现 Codex 工作环境、比较已安装 Skill 与备份仓库,或准备安全的跨设备恢复。

Quality

91%

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

92%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.

An exemplary operational skill body: lean, safety-first, with a fully sequenced workflow of validation checkpoints and feedback loops, an explicit output contract, and minimal verifiable evidence of success. The only shortcoming is that the apply invocation is not spelled out as a complete command.

Suggestions

Include the full apply command verbatim (e.g., 'python3 scripts/sync_skills.py --destination "<destination>" --profile core --apply') alongside the check command so step 5 is copy-paste ready.

Briefly state where scripts/validate_repo.py and sync_skills.py come from (source repo layout) so a reader can locate them without inference.

DimensionReasoningScore

Conciseness

The ~50-line body is lean and sectioned (适用范围/工作流程/安全边界/输出契约/验证) with zero padding or explanation of concepts Claude already knows; every line adds operational or safety information, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Concrete, near copy-paste commands are given for validation ('python3 scripts/validate_repo.py --strict') and the read-only check ('python3 scripts/sync_skills.py --destination "<destination>" --profile core --check'), plus a concrete destination example ('C:\Users\<user>\.codex\skills'), but the apply step is described rather than given verbatim and the referenced scripts live in the source repo rather than the bundle — minor gaps that keep it at 4 rather than 5.

4 / 5

Workflow Clarity

The 5-step sequence is explicit with validation checkpoints at every risky point: strict source validation before anything, a read-only --check baseline, user-confirmed apply, and a mandatory post-apply --check on the same destination; failure handling ('源端校验失败时停止恢复并保留原始错误') and the verification evidence block complete the feedback loop, satisfying the destructive/batch validation requirement rather than falling under its cap.

5 / 5

Progressive Disclosure

The body is short, well-organized, and delegates the cross-device checklist to a single clearly signaled one-level-deep reference ([restore-profile.md](references/restore-profile.md)) that actually exists in the bundle with no further nesting — the ideal overview-plus-one-reference structure.

5 / 5

Total

19

/

20

Passed

Description

88%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 description: third-person, concise, with a clear what and an explicit when clause enumerating three usage scenarios. Its concrete action list (audit, explicit apply, SHA-256, non-destructive) makes it specific and mostly collision-free. The main weakness is trigger-term breadth and an unstated boundary versus sibling repository-maintenance skills.

Suggestions

Add one or two natural synonyms users would say, such as '安装' or '同步/迁移' Skill, to broaden trigger coverage.

Add a short boundary clause in the description (e.g., '仓库维护和质量检查由其他 Skill 负责') to reduce overlap with repository-maintenance and quality-gate skills.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — '提供只读审计、显式应用、SHA-256 校验,并且不删除目标端额外文件' — covering restore, read-only audit, explicit apply, hash verification, and destination preservation, which matches the comprehensive-coverage anchor rather than the 4 anchor that implies minor gaps.

5 / 5

Completeness

It explicitly answers both what ('恢复已登记的 Codex Skill…提供只读审计、显式应用、SHA-256 校验…') and when ('用于复现 Codex 工作环境、比较已安装 Skill 与备份仓库,或准备安全的跨设备恢复') with three concrete trigger scenarios, matching the 5 anchor; the 4 anchor applies only when the 'when' is less explicit, which is not the case here.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ('恢复已登记的 Codex Skill', '复现 Codex 工作环境', '跨设备恢复', '比较已安装 Skill 与备份仓库'), but common synonyms users might say (安装、同步、迁移) and any file/extension cues are missing, so it fits the 'good coverage, a few natural terms missing' anchor rather than the 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The restore/apply-to-destination niche is distinct, but the read-only audit and compare-installed-vs-backup framing overlaps with repository-maintenance and quality-gate skills without a description-level boundary statement, so it fits 'mostly distinct; minor overlap risk with closely related skills' rather than the 5 anchor's 'clear niche with minimal conflict risk'.

4 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

ooooooooooooooooooop/agent-tools

Path

skills/environment-bootstrap/SKILL.md

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.