CtrlK
BlogDocsLog inGet started
Tessl Logo

implement-spec

实现一份 specification 中描述的代码变更。

59

Quality

68%

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 ./skills/in-progress/implement-spec/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 a lean, well-sequenced orchestration workflow that respects token budget and includes a code-review feedback loop before completion. Its main weaknesses are minor: missing concrete subagent prompt/pointer examples and no explicit checkpoint for merge conflicts or build verification.

Suggestions

Add a short example of the context-pointer format or a skeleton implementer-subagent prompt to make step 4 fully executable.

Insert a validation checkpoint after each merger step (e.g., verify the PR branch builds or tests pass before spawning more implementers) to strengthen the feedback loop.

Briefly specify how merge conflicts should be handled when the merger subagent integrates an implementer's work.

DimensionReasoningScore

Conciseness

The ~30-line body is lean with no padding: it conveys only skill-specific semantics ('tickets 不是步骤清单,而是一个 task graph', 'frontier tickets', 'context pointers') and assumes Claude's competence rather than explaining concepts it already knows.

5 / 5

Actionability

Steps give mostly executable process guidance ('创建一个 branch 和一个 draft PR', subagents work '在自己的 worktree 和 branch 上', run '/code-review'), but minor gaps remain — no example subagent prompts, context-pointer format, or merge commands.

4 / 5

Workflow Clarity

The 9 steps are clearly sequenced and include a validate-then-fix feedback loop (run '/code-review', fix all issues before marking ready), but checkpoints for merge conflicts or build/test verification between merges are absent, matching the 'most checkpoints present; minor validation gaps' anchor.

4 / 5

Progressive Disclosure

This is a short (<50 line) instruction-only skill with no bundle files and no need for external references; the single well-organized '## Steps' section with a short conceptual preamble satisfies the simple-skill exception for a top score.

5 / 5

Total

18

/

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 is concise and states a clear single capability in third person, but it is minimal: it lacks any 'when to use' trigger clause, natural synonym coverage, and a listing of the concrete actions the skill actually performs. It sits squarely at the midpoint of the rubric across all dimensions.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user provides a specification or asks to implement a spec and its tickets.'

Enumerate the concrete actions (parse the ticket task graph, run parallel implementer subagents in worktrees, merge into a single PR) to raise specificity.

Include natural synonyms users would say — 'spec', 'tickets', 'implement', 'pull request' — to improve trigger term coverage and distinctiveness.

DimensionReasoningScore

Specificity

"实现一份 specification 中描述的代码变更" names the domain (implementing changes from a specification) and one concrete action, but does not enumerate the several specific actions the skill performs (branch creation, subagent orchestration, PR workflow), matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

The description clearly answers 'what' (implement code changes from a specification) but contains no 'when' or 'Use when...' trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords like 'specification' and '代码变更' (code changes) are present, but natural user variations such as 'spec', 'implement tickets', or 'PR' are missing, matching the 'some relevant keywords but missing common variations or synonyms' anchor.

3 / 5

Distinctiveness Conflict Risk

Being scoped to spec-driven implementation gives it some distinctiveness, but it could still overlap with general coding, implementation, or PR-creation skills since no distinguishing trigger phrases are given.

3 / 5

Total

12

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
vinvcn/mattpocock-skills-zh-CN
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.