bootcamp-guide

operator 新手训练营引导模式。 Use when: thread 有 bootcampState（系统自动注入，不需要手动加载）。 Not for: 非训练营线程、老用户。

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cat-cafe-skills/bootcamp-guide/SKILL.md

Quality

Content

77%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 highly actionable with a clearly sequenced, validated workflow, but it is held back by redundancy across the overview and per-message sections and by being a single large file with no progressive disclosure.

Suggestions

Collapse the overlap between '整体流程概览' and the per-MSG sections so each phase's detail lives in one place, and consolidate the repeated '你不需要…' / '⛔ STOP' / '⛔ 禁止 @co-creator' reminders into a single shared rules block.

Extract the bulky 16-option rich-block card configuration and the per-phase reply scripts into a reference file (e.g. references/phases.md) referenced one level deep, so SKILL.md stays a lean overview.

Move the skip matrix and phase-name list into a reference and link to them, keeping only the iron rules and flow overview inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete and task-specific (exact tool calls, phase names, reply strings), but it carries real redundancy: the '整体流程概览' re-describes what each per-MSG section repeats, and '你不需要…' / '⛔ STOP' / '⛔ 禁止 @co-creator' instructions are restated multiple times, so it could be tightened rather than every token earning its place.	2 / 3
Actionability	Guidance is fully executable and copy-paste ready: exact tool calls (cat_cafe_update_bootcamp_state(threadId, phase='phase-2-env-check')), the exact legal phase-name list, verbatim reply strings in the skip matrix, and explicit rich-block parameters (kind: 'interactive', interactiveType: 'card-grid', id: 'bootcamp-next-project').	3 / 3
Workflow Clarity	The multi-step flow is clearly sequenced (MSG 1→2→3→4+, Phase 11) with an explicit validation checkpoint (env check branching into Path A/B), a feedback loop (retry the same tool on failure), and checklists (skip matrix, phase-name list, iron rules), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	The skill is a single monolithic ~230-line SKILL.md with no bundle files and no file splitting; it is well-sectioned internally but does not use one-level-deep references or split out bulky content (rich-block card config, per-phase details), so it sits at 'some structure but monolithic' rather than the well-signaled-reference anchor at 3.	2 / 3
	Total	10 / 12 Passed

Description

75%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.

The description clearly scopes a distinct niche with explicit use/exclusion triggers, but it is vague about concrete actions and leans on internal jargon (bootcampState, thread) rather than natural user phrasing.

Suggestions

Replace the abstract phrase '引导模式' with concrete actions, e.g. '引导新手 operator 走完训练营各阶段、检测环境、推进 phase、添加协作队友'.

Reword the 'Use when' clause around natural user terms ('新手训练营', '第一次协作开发') instead of internal mechanics like 'thread 有 bootcampState（系统自动注入）'.

Add 1–2 concrete capability verbs so the 'what' matches the specificity of the explicit 'when' guidance.

Dimension	Reasoning	Score
Specificity	The description names a clear domain ("operator 新手训练营引导模式") but the action "引导模式" is abstract and does not enumerate concrete actions like guiding phases, running env checks, or adding teammates, so it falls short of the multi-action anchor at 3 while being more specific than the vague 1 anchor.	2 / 3
Completeness	It states what it does ("operator 新手训练营引导模式") and explicitly answers when with both a "Use when:" clause and a "Not for:" exclusion, satisfying the 'clearly answers both what AND when with explicit triggers' anchor even though the 'what' is brief.	3 / 3
Trigger Term Quality	Natural terms are present ("训练营", "新手", "bootcamp") but they are mixed with internal jargon ("thread 有 bootcampState（系统自动注入）") that a user would not naturally say, matching the 'some relevant keywords but missing common variations' anchor rather than clean natural coverage at 3.	2 / 3
Distinctiveness Conflict Risk	The skill targets a narrow niche (bootcamp threads only) with an explicit exclusion ("Not for: 非训练营线程、老用户"), making it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/bootcamp-guide/SKILL.md
Commit: 80782c5

Reviewed: 11 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.