CtrlK
BlogDocsLog inGet started
Tessl Logo

work-in-repo

Learn how to work in the current folder (repository)

45

Quality

46%

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 ./.claude/skills/work-in-repo/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 content is a concise, mostly actionable setup workflow with concrete commands, but it lacks validation checkpoints and a couple of steps remain vague. Section organization is decent for a simple skill but headers could be cleaner.

Suggestions

Add a verification step after `uv sync` (e.g. run `uv run python -c 'import pymc_marketing'` or check the venv) to close the workflow validation gap.

Clarify the vague step 4: name the specific linter command (e.g. `uv run ruff check .`) and the path to contribution.md.

Reword the 'How to do when user ask a request?' header to a clearer imperative such as '## When the user asks you to build something'.

DimensionReasoningScore

Conciseness

The body is lean: a one-line context statement plus four terse numbered steps with concrete commands, assuming Claude's competence and avoiding padding. It is not 5 because the introductory sentence and the awkward 'How to do when user ask a request?' header could be tightened.

4 / 5

Actionability

It gives concrete executable commands (`uv sync`, `brew install gh`, `uv run`) for the common cases, matching 'Mostly executable guidance with minor gaps'. It is not 5 because steps like 'Follow linter rules and contribution.md recommendations' are vague and contribution.md is not clearly located.

4 / 5

Workflow Clarity

A clear numbered sequence is present for the build request, but there are no validation checkpoints (e.g. verifying `uv sync` succeeded or that gh is authenticated), matching 'Steps listed but validation gaps'. It is not 4 because verification steps are entirely absent.

3 / 5

Progressive Disclosure

At under 50 lines with two organized sections and no need for external reference files, it is well-structured for a simple skill. It is not 5 because the section headers are unevenly phrased and a couple of inline references (contribution.md, the gh install URL) are not clearly signaled as separate resources.

4 / 5

Total

15

/

20

Passed

Description

25%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 generic and under-specified: it names a vague domain with no concrete actions and no trigger guidance, making it hard to distinguish from other skills or know when to invoke it. It needs explicit capabilities and a 'Use when...' clause.

Suggestions

Replace 'Learn how to work' with concrete actions, e.g. 'Set up the Python environment and run commands in the pymc-marketing repository'.

Add an explicit trigger clause: 'Use when the user asks to build, run, or modify code in this repository'.

Include natural trigger terms users would say ('uv sync', 'run tests', 'set up the repo') to improve distinctiveness.

DimensionReasoningScore

Specificity

The description names the domain ('work in the current folder (repository)') but uses the generic action 'Learn how to work' with no concrete capabilities listed, matching the anchor 'Names the domain but actions are minimal or generic'. It does not reach 3 because no concrete actions are enumerated, and it is above 1 because a domain is at least identified.

2 / 5

Completeness

It provides a vague 'what' ('Learn how to work in the current folder') and no 'when'/trigger guidance at all, matching 'Has a vague what and no when'. The missing 'Use when...' clause caps it well below 4, and it is not 1 because a domain is named.

2 / 5

Trigger Term Quality

The phrase 'work in the current folder (repository)' offers only generic keywords and lacks the natural phrases a user would actually say to trigger this skill, matching 'One or two generic keywords; missing the natural phrases users say'. It is not 3 because no relevant synonyms or natural trigger variations appear.

2 / 5

Distinctiveness Conflict Risk

'Learn how to work in the current folder (repository)' is very broad and would overlap with almost any repo-oriented skill, matching 'Very broad; high overlap risk with many similar skills'. It is not 1 only because it does narrow slightly to a repository context.

2 / 5

Total

8

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pymc-labs/pymc-marketing
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.