CtrlK
BlogDocsLog inGet started
Tessl Logo

work-in-repo

Learn how to work in the current folder (repository)

38

Quality

36%

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

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 commendably concise and well-structured for a simple environment-setup skill, with concrete executable commands for most steps. Its main weakness is incomplete actionability and the absence of any verification checkpoints in the setup workflow.

Suggestions

Replace the vague step 4 with concrete commands, e.g. `uv run ruff check .` and `uv run pytest`, instead of 'Follow linter rules and contribution.md recommendations'.

Add a validation checkpoint after setup, such as confirming `uv sync` completed and `gh auth status` succeeds before proceeding.

Fix the broken references — link CONTRIBUTING.md correctly and verify the file name — so the inline pointer is actionable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, with no padding or explanation of concepts Claude already knows; every line (intro context plus four short steps) earns its place, matching the 'Lean and efficient' anchor.

3 / 3

Actionability

Steps 1–3 give concrete executable commands (`uv sync`, `brew install gh`, `uv run`), but step 4 ('Follow linter rules and contribution.md recommendations') is vague and no actual lint/test/build commands are given, so it is concrete yet incomplete like the level-2 anchor rather than copy-paste ready at level 3.

2 / 3

Workflow Clarity

The four steps are clearly sequenced, but there are no validation checkpoints (e.g., confirm `uv sync` succeeded or that `gh` is now available), matching the 'steps listed but validation gaps' anchor rather than the level-3 anchor with explicit verify steps.

2 / 3

Progressive Disclosure

This is a simple under-50-line skill with two well-organized sections and no need for external bundle files, so per the rubric's simple-skills note it qualifies for the top anchor on structure alone.

3 / 3

Total

10

/

12

Passed

Description

0%

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 overly vague, names no concrete capabilities, lacks any natural trigger terms, and provides no 'when to use' guidance, making it indistinguishable from many other skills. It reads like the 'Helps with documents' class of weak descriptions.

Suggestions

Name the concrete actions the skill performs (e.g., 'Set up the uv environment, install the GitHub CLI, and run Python commands') instead of the abstract 'work in the current folder'.

Add an explicit trigger clause such as 'Use when the user asks to build or run code in this pymc-marketing repository' to satisfy the 'when' half of completeness.

Tie the description to this specific repository and tooling (uv, gh) so it is distinct from generic repo-work skills.

DimensionReasoningScore

Specificity

The phrase "Learn how to work in the current folder (repository)" names no concrete actions, only an abstract goal, matching the vague 'Helps with documents' anchor rather than the level-2 anchor that names a domain and some actions.

1 / 3

Completeness

It gives only a very weak 'what' (learn to work in a folder) and entirely omits any 'when'/Use-when trigger guidance, so both halves are weak as in the level-1 anchor; it cannot reach 2 because the 'when' is not even implied.

1 / 3

Trigger Term Quality

"work in the current folder (repository)" contains no natural keywords a user would say when they need this skill; it is overly generic like the 'Handles document object model manipulation' anchor.

1 / 3

Distinctiveness Conflict Risk

The description is so generic it would overlap with almost any other skill, matching the 'would conflict with many skills' anchor; there is no niche trigger to lift it to level 2.

1 / 3

Total

4

/

12

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.