CtrlK
BlogDocsLog inGet started
Tessl Logo

allowed-dirs-skill

A skill with development directories that require --allow-dirs.

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 ./crates/skill-validator-rs/tests/golden-corpus/fixtures/testdata/allowed-dirs-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%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 well-organized, token-efficient skeleton that points to real bundle files, but it delegates virtually all substance to a reference guide that contains no actual instructions. Claude invoking this skill would learn the directory layout but not what to do.

Suggestions

Replace the delegation-only Usage section with 2-3 concrete, executable steps (e.g. exact commands to run, what validate.sh should be run against, and what success looks like).

Flesh out references/guide.md with actual setup steps, or inline the steps in SKILL.md and drop the stub reference.

Add a validation checkpoint describing what to do when scripts/validate.sh fails (fix -> re-run loop), which would also lift workflow clarity.

DimensionReasoningScore

Conciseness

The body is lean (under 30 lines), assumes Claude's competence, and contains no concept explanations Claude already knows. The only trimmable material is the slight repetition between the intro ('development artifacts that require --allow-dirs') and the Notes section ('Neither is part of the standard skill structure'), which keeps it just below the 'every token earns its place' anchor 5.

4 / 5

Actionability

Concrete guidance is minimal: 'Follow the instructions in the [reference guide](references/guide.md)' is pure delegation with no stated steps, and 'Run scripts/validate.sh to check your work' is a command with no arguments, expected inputs, or expected output. This matches anchor 2 ('high-level hints but missing the specific steps to execute'); it is above anchor 1 only because a real script path is named.

2 / 5

Workflow Clarity

A rough two-step sequence is implied (read the guide, then run validate.sh), but the steps are poorly defined, the guide contains no actual steps to follow, and there is no indication of what validation checks or what to do on failure. This matches anchor 2 ('rough sequence present but many gaps; validation absent').

2 / 5

Progressive Disclosure

Structure is good: short overview, clear '## Usage' section, and a clearly signaled one-level-deep reference (references/guide.md, verified to exist) plus a named script (scripts/validate.sh, verified to exist). It falls short of anchor 5 because the referenced guide is itself a contentless stub ('Follow these steps to set up the skill') and the Notes section duplicates inline material that adds little navigational value.

4 / 5

Total

12

/

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 fails at its core job: it describes the skill's packaging (non-standard directories needing a CLI flag) rather than its capability, and provides no usage triggers. A user or Claude reading it could not decide when to invoke this skill.

Suggestions

State concrete actions the skill performs (the 'what'), e.g. 'Sets up development directories (evals/, testing/) alongside a standard skill structure...'.

Add an explicit 'Use when...' clause naming natural trigger phrases users would say, such as 'Use when creating a skill scaffold with custom dev directories or when --allow-dirs warnings appear'.

Differentiate from generic directory skills by naming the specific directories and tool context (e.g. skill scaffolding, evaluation fixtures) so it cannot collide with unrelated file-management skills.

DimensionReasoningScore

Specificity

The description 'A skill with development directories that require --allow-dirs' names a domain (development directories, a CLI flag) but states no actions whatsoever — it describes what the skill is, not what it does. It sits above the pure-abstraction anchor ('Helps with documents') only because '--allow-dirs' is a concrete token, but far below anchor 3 which requires 1-2 concrete actions.

2 / 5

Completeness

It offers only a vague 'what' (a skill with development directories) and no 'when' guidance at all — no 'Use when...' clause or equivalent, matching anchor 2 ('Has a vague what and no when'). It cannot reach 3 because the 'what' is not clear, and cannot reach 4 because the 'when' is entirely absent.

2 / 5

Trigger Term Quality

The only candidate keywords are 'development directories' and '--allow-dirs', the latter being technical jargon a user would not naturally say. No natural phrases a user would utter when needing this skill are present, matching the 'one or two generic keywords; missing the natural phrases users say' anchor.

2 / 5

Distinctiveness Conflict Risk

'A skill with development directories' is very broad and would overlap with any directory- or tooling-related skill; nothing in the description carves out a distinct niche or trigger set. It is marginally more specific than the entirely-generic anchor 1, so anchor 2 is the best fit.

2 / 5

Total

8

/

20

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

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
pantheon-org/tekhne
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.