CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

work-in-repo

Learn how to work in the current folder (repository)

Quality

54%

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 body is admirably concise and partially actionable with real commands for environment setup, but the workflow stops short of the lint/test/PR guidance it gestures at and includes no validation steps. The "contribution.md" reference is vague and unlinked, leaving the final step unexecutable as written.

Suggestions

Make step 4 concrete: name the actual lint/test commands (e.g. `uv run pre-commit run --all-files`, `uv run pytest`) and link the real file ([CONTRIBUTING.md](CONTRIBUTING.md)).

Add a validation checkpoint after setup, e.g. "Verify with `uv run python -c 'import pymc_marketing'`" and what to do on failure.

Fix grammar/typos for clarity ("How to do when user ask a request?" → "What to do when the user makes a request") and clarify when gh is actually needed (e.g. only for PR/issue work).

DimensionReasoningScore

Conciseness

The body is lean and efficient — 17 lines with zero padding and no explanation of concepts Claude already knows; every token (env setup, gh install, uv run) earns its place.

5 / 5

Actionability

Steps 1-3 give executable commands (`uv sync`, `brew install gh`, `uv run`), but guidance is incomplete: "Follow linter rules and contribution.md recommendations" names no lint/test command and references an ambiguous filename, and the gh workflow (auth, branching, PRs) is never specified.

3 / 5

Workflow Clarity

A numbered sequence exists (sync → install gh → uv run → follow linter), but there are no validation checkpoints or error-recovery steps — e.g. nothing on what to do if `uv sync` fails or how to verify the environment.

3 / 5

Progressive Disclosure

As a sub-50-line skill with two clear sections (Introduction, workflow), structure is appropriate with no external files needed; the buried, unsignaled "contribution.md" reference (likely CONTRIBUTING.md, not linked) is a minor organization gap that keeps it below 5.

4 / 5

Total

15

/

20

Passed

Description

16%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 a vague placeholder: it names no concrete capabilities, includes no trigger guidance, and is indistinguishable from any generic development skill. It fails to tell Claude what the skill actually does or when to invoke it.

Suggestions

State concrete actions, e.g. "Sets up the pymc-marketing development environment with uv, installs gh, and runs linting/tests per pymc-labs contribution guidelines."

Add an explicit trigger clause, e.g. "Use when working in the pymc-marketing repository: setting up the environment, running Python commands, or preparing contributions."

Include natural trigger keywords users would say — repo setup, uv sync, contributing, pymc-marketing — to reduce conflict risk with other skills.

DimensionReasoningScore

Specificity

"Learn how to work in the current folder (repository)" names no concrete actions whatsoever — pure abstract language with no domain-specific verbs, matching the 'entirely vague; no concrete actions' anchor.

1 / 5

Completeness

It offers only a vague 'what' ("learn how to work") with no 'when'/"Use when..." clause at all — the anchor-2 pattern of vague what plus absent when; it cannot reach 3 because the 'what' itself is not clear.

2 / 5

Trigger Term Quality

"current folder (repository)" supplies only one or two generic keywords; the description lacks the natural phrases a user would actually say when needing this skill (e.g. repo setup, environment, contribute).

2 / 5

Distinctiveness Conflict Risk

The description is entirely generic and would conflict with virtually any software-development skill; nothing distinguishes it (no named tools, repo, or tasks).

1 / 5

Total

6

/

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

pymc-labs/pymc-marketing

Path

.claude/skills/work-in-repo/SKILL.md

Revision

ca98bc7

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill