feat-lifecycle

Feature 立项、讨论、完成的全生命周期管理。 Use when: 开个新功能、new feature、F0xx、立项、feature 完成、验收通过、讨论新功能需求。 Not for: 代码实现、review、merge（那些有专门的 skill）。 Output: Feature 聚合文件 + BACKLOG 索引 + 真相源同步。

Quality

88%

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

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 and workflow-clear with concrete commands, gated checkpoints, and explicit error-recovery loops. Its weaknesses are conciseness (lengthy narrative lesson anchors) and progressive disclosure (monolithic inline content with no bundle files to offload detail into).

Suggestions

Move the recurring '教训/事故来源' narrative blocks (F216, F252, F190, F114/F115/F116 stories) into a references/lessons.md file and keep only a one-line pointer in the body to recover token budget for conciseness.

Extract the large gate tables (Design Gate type matrix, User Journey gate, Eval Contract, architecture-cell) into a references/ design-gate-checklists.md and reference them one level deep, turning the body into an overview with well-signaled references.

Either add the referenced files (feature-doc-template.md, decision-matrix.md, shared-rules.md) to the skill's references/ bundle or reword the in-body pointers so they are clearly one-level-deep local references rather than external paths.

Dimension	Reasoning	Score
Conciseness	The body is dense and terse with no concept-explanation padding, but it runs ~470 lines and carries extensive narrative lesson/事故 anchors (F216/F252/F190 stories) that exceed strict token necessity; matching the 'mostly efficient but could be tightened' anchor rather than the lean 3.	2 / 3
Actionability	Provides exact executable commands (grep -E 'F[0-9]+', pnpm check:features, gh pr list), concrete commit-message formats, file paths, and copy-paste-ready table schemas (CloseGateReport, User Journey verification), matching the 'fully executable; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Sequenced phases (Kickoff Steps 0-6, Design Gate, Completion Steps 0-6) with explicit validation checkpoints (🔴 markers, BLOCKED conditions, feature-truth gate, cross-cat verification) and feedback loops for error recovery, matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the body is a monolithic ~470-line wall of text with content (lesson narratives, multiple gate tables) that should be split into reference files; its file references point outside the skill bundle, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

100%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 is concise, specific, and complete: it states concrete actions and output artifacts, provides natural bilingual trigger terms, answers both what and when, and explicitly fences off adjacent skills. It is a strong, low-conflict description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the lifecycle (立项/讨论/完成 management) plus concrete output artifacts ('Feature 聚合文件 + BACKLOG 索引 + 真相源同步'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (lifecycle management + output) and when ('Use when: ...'), and adds a 'Not for' boundary, matching the 'clearly answers both what AND when with explicit triggers' anchor.	3 / 3
Trigger Term Quality	Natural bilingual phrases users would actually say ('开个新功能', 'new feature', '立项', 'feature 完成', '验收通过') plus project tokens (F0xx) give good coverage, matching the 'good coverage of natural terms' anchor.	3 / 3
Distinctiveness Conflict Risk	Clear feature-lifecycle niche with distinct triggers and an explicit 'Not for: 代码实现、review、merge（那些有专门的 skill）' boundary that prevents overlap with adjacent skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 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, 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: zts212653/clowder-ai
Path: cat-cafe-skills/feat-lifecycle/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.