CtrlK
BlogDocsLog inGet started
Tessl Logo

loop-me

在这个工作区中,就我想构建的工作流规格访谈我。

49

Quality

53%

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/loop-me/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-structured with operational vocabulary and a clear definition-of-done, but the grilling workflow's sequencing and validation checkpoints remain implicit rather than explicit, leaving actionability and workflow clarity at the mid level.

Suggestions

Make the grilling procedure explicitly stepwise: e.g., 1) interview the user's world (populate NOTES.md) if thin, 2) grill one question at a time with a recommended answer, 3) create/edit/delete specs, 4) push checkpoints right, 5) stop only when an implementer needs no questions.

Add an explicit validation/feedback loop for the spec (e.g., re-read the spec as an implementer would and list any remaining questions; if none, it is done) to lift workflow clarity.

Surface the concrete spec artifacts and where they live (workflows/*.md, NOTES.md) earlier as a quick-start overview so the actionable path is immediately visible.

DimensionReasoningScore

Conciseness

The ~25-line body is lean and well-organized, defines only a focused vocabulary and lens, and assumes Claude's competence without padding or explaining concepts Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

It gives concrete discipline (one question at a time, each with a recommended answer), operational vocabulary definitions, and a clear definition-of-done, but the grilling procedure is partly descriptive rather than fully prescriptive, matching 'some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

The grill -> create/edit/delete specs -> push right -> done sequence is present with a termination checkpoint ('Definition of done'), but the sequencing between interviewing the user's world and writing specs and the validation checkpoints are largely implicit, matching 'steps listed but validation gaps; checkpoints missing or implicit'.

2 / 3

Progressive Disclosure

With no bundle files present and the skill well under 50 lines, the body is cleanly split into well-organized sections (loop lens, vocabulary, definition of done, workspace) satisfying the simple-skill allowance for a 3 with good organization alone.

3 / 3

Total

10

/

12

Passed

Description

35%

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 conveys a clear niche (interviewing the user to produce workflow specs) but is first-person and entirely lacks explicit trigger guidance or natural user-utterable keywords, capping completeness and trigger quality.

Suggestions

Rewrite in third person and add a 'Use when...' clause with natural trigger terms (e.g., 'Use when the user wants to design or specify a workflow, build a spec, or be interviewed about a recurring process').

Add concrete capability verbs (e.g., 'interviews the user, proposes workflow specs, creates/edits/deletes spec files') to lift specificity from a single abstract action to multiple concrete ones.

Include user-utterable keywords like 'workflow', 'spec', 'loop', and 'grilling' so the skill is discoverable when the user asks in those terms.

DimensionReasoningScore

Specificity

The phrase "就我想构建的工作流规格访谈我" names a domain (workflow specs) and one action (interview me), but offers only a single abstract action rather than a list of concrete capabilities, matching the 'names domain and some actions, but not comprehensive' anchor.

2 / 3

Completeness

It states what the skill does (interview the user about workflow specs) but provides no 'when to use it' guidance, and the rubric caps completeness at 2 when a 'Use when...' clause is missing; it is not 1 because the 'what' is present.

2 / 3

Trigger Term Quality

No natural trigger keywords a user would utter appear (no 'design workflow', 'spec', 'grilling', or 'Use when' phrasing); the first-person 'interview me' is a conversational instruction, not trigger language, matching the 'no natural keywords' anchor.

1 / 3

Distinctiveness Conflict Risk

The workflow-spec-design niche is reasonably specific and unlikely to trigger for unrelated skills, but the absence of distinguishing trigger terms leaves it somewhat generic and able to overlap with other planning skills, matching the 'somewhat specific but could still overlap' anchor.

2 / 3

Total

7

/

12

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
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.