CtrlK
BlogDocsLog inGet started
Tessl Logo

cs-epic

大需求或系统级能力的路线发现、拆解与长程推进。单个功能走 cs-feat,bug 走 cs-issue。

50

Quality

55%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/codestable/skills/cs-epic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 skill body is a well-structured, validation-heavy instruction document with clear sequencing and appropriately signaled, real one-level references, but it leans verbose and mixes concrete commands with long conditional policy prose that limits conciseness and copy-paste actionability.

Suggestions

Convert the long policy-combination rules (item_progression/milestone_commit/remote_publish legality) into a compact table to cut tokens and improve scanability.

Add a short worked example of one full epic lifecycle (proposed -> gate -> active -> milestone -> accepted) with the concrete cursor field values at each step to raise actionability.

Tighten or move repeated qualifier clauses (e.g. repeated '不新增 owner gate / 不替代 review / 不推断授权') into a single consolidated invariants section.

DimensionReasoningScore

Conciseness

The body is dense but largely free of padding and does not explain concepts Claude already knows; however several paragraphs (e.g. the 拆解 confirmation and policy-combination sentences) run very long with repeated qualifiers that could be tightened into tables or shorter rules.

3 / 5

Actionability

Guidance is concrete in places (e.g. "shasum -a 256 <epic-file>", explicit file templates, named frontmatter fields) but much of it is conditional prose and policy enumeration rather than copy-paste-ready commands or worked examples, leaving key execution details implicit.

3 / 5

Workflow Clarity

The hard-gate section sequences a clear multi-step lifecycle (proposed -> active -> executing -> acceptance) with explicit validation checkpoints (review rounds, blocking/important handling, milestone commits) and error-recovery feedback loops; minor gaps remain in some implicit transitions.

4 / 5

Progressive Disclosure

Structure is well organized into clearly headed sections with three one-level-deep, conditionally-loaded references (shared-language.md, wayfinding.md, parallel-execution.md) that are all real files in ./references/ and signaled only-when-needed; the main body still inlines substantial policy detail that could be further split.

4 / 5

Total

14

/

20

Passed

Description

50%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 states a clear domain and disambiguates against sibling skills, but it lacks an explicit "Use when..." trigger clause and relies on generic rather than comprehensive natural trigger terms, capping completeness.

Suggestions

Add an explicit 'Use when ...' clause naming concrete trigger phrases an owner would say (e.g. large requirement, epic, initiative, roadmap, multi-session big need).

Expand trigger coverage with synonyms/variants like 'epic', '路线规划', 'initiative', 'RFC' alongside '大需求'.

Sharpen the "what" with a few concrete actions (e.g. 起草 proposed Epic、拆解子项契约、逐项推进与集成验收) to lift specificity from 4 toward 5.

DimensionReasoningScore

Specificity

Quotes "路线发现、拆解与长程推进" name a concrete domain (large-requirement roadmap discovery, decomposition, long-range progression) and several distinct actions (discover, decompose, push forward), though the actions are high-level rather than enumerated concrete operations, leaving minor coverage gaps.

4 / 5

Completeness

The "what" is stated (route discovery, decomposition, long-range progression) but there is no "Use when..." clause or explicit trigger guidance, only an implicit routing contrast to cs-feat/cs-issue, so the "when" is weakly implied at best and the missing-trigger cap of 3 applies; the near-absence of explicit when pushes it below the midpoint.

2 / 5

Trigger Term Quality

The phrase "大需求" (large requirement) is a relevant but generic trigger; the "单个功能走 cs-feat,bug 走 cs-issue" routing adds one disambiguating term, yet common natural variations an owner would say (e.g. "epic", "路线", "initiative", "RFC") are largely absent.

3 / 5

Distinctiveness Conflict Risk

The explicit routing "单个功能走 cs-feat,bug 走 cs-issue" carves out a distinct niche (epic-scale vs single feature vs bug) that minimizes overlap with sibling skills, with only minor residual overlap risk on mid-sized requirements.

4 / 5

Total

13

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
codestable/CodeStable
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.