CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pp-learn-disabled-example

Printing Press CLI for Learn Disabled Example. Golden fixture exercising the learn.disabled generation-time opt-out.

Quality

59%

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 ./testdata/golden/expected/generate-learn-disabled-api/learn-disabled-example/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 an highly actionable CLI operating manual with exemplary verification and error-recovery workflows. Its weaknesses are redundancy (duplicated read-only guidance, fixture meta-commentary) and a monolithic single-file structure that inlines material better split into reference files. Overall a strong, executable skill document with moderate token-efficiency and organization improvements available.

Suggestions

State the read-only restriction once and drop the golden-fixture meta paragraph from the body, keeping only operator-relevant install/usage contract.

Move the Paths-and-state env-var matrix, MCP HTTP/TLS configuration, and Output Delivery sink semantics into reference files linked from a short overview section.

DimensionReasoningScore

Conciseness

The body is dense with CLI-specific contract detail, but the read-only restriction is stated twice ("Do not activate this CLI for requests that require creating..." and "Read-only — do not use this CLI for create, update, delete..."), the golden-fixture paragraph is meta-commentary irrelevant to operating the CLI, and edge-case notes like the Go fallback and fleet-precedence paragraph could be trimmed. This fits 'Mostly efficient but includes some unnecessary explanation or could be tightened'; it is not a 4 because these are more than minor instances, and not a 2 because it never explains concepts Claude already knows.

3 / 5

Actionability

Every section provides copy-paste-ready commands: the npx install line, `learn-disabled-example-pp-cli --version` verification, `which "<capability>"` with documented exit codes, auth token piping, profile subcommands, and the `--deliver` sink table. Guidance is fully executable with the exit-code and envelope contracts needed to consume output correctly; no gaps remain.

5 / 5

Workflow Clarity

Sequences are explicit with validation checkpoints and error-recovery loops: install → verify version → ensure PATH with "Do not proceed with skill commands until verification succeeds", a numbered argument-parsing decision tree, Direct Use steps 1–4 with "If ambiguous, drill into subcommand help", plus `doctor`, `--dry-run`, and exit-code-7 retry guidance. This matches 'Clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

The ~210-line body is well-sectioned but entirely inline with zero reference files — reference-type material such as the Paths and state env-var matrix, MCP HTTP/TLS configuration, and delivery-sink semantics clearly belongs in separate files. This fits 'Some structure but could be better organized... content that should be separate is inline'; it is not a 2 because section structure is strong, and not a 4 because there are no references at all and the single file carries substantial reference material.

3 / 5

Total

16

/

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 precisely identifies the artifact but is written as internal fixture metadata rather than a user-facing capability description. It states no concrete actions, contains no natural trigger terms, and omits any 'when to use' guidance. Only its specificity of niche saves it from scoring lower.

Suggestions

Add an explicit 'Use when...' clause stating when to invoke this skill (e.g., 'Use when working with the Learn Disabled Example CLI or verifying learn-disabled output').

Replace jargon like 'Golden fixture exercising the learn.disabled generation-time opt-out' with the concrete capabilities the CLI offers, such as listing games, inspecting, and exporting read-only data.

Include natural keywords a user would actually say — the CLI name, 'learn disabled', 'printing press', 'opt-out check' — so the skill triggers on real queries.

DimensionReasoningScore

Specificity

The description names the domain ("Printing Press CLI for Learn Disabled Example") but lists no concrete user-facing actions — "Golden fixture exercising the learn.disabled generation-time opt-out" describes the artifact's test role, not capabilities. This matches the anchor 'Names the domain but actions are minimal or generic'; it is not a 3 because no 1-2 concrete actions (e.g., list games, sync, export) are stated, and not a 1 because it is not pure abstract language.

2 / 5

Completeness

The 'what' is vague (identifies a CLI exists for an example project but says nothing about what it does) and the 'when' is entirely missing — no 'Use when...' clause or equivalent trigger guidance, which also caps this dimension at 3. It is not a 1 because the artifact is precisely identified rather than extremely vague.

2 / 5

Trigger Term Quality

Every phrase — "Printing Press CLI", "Golden fixture", "learn.disabled generation-time opt-out" — is project-internal technical jargon a user would never naturally say when needing this skill. This matches 'No natural keywords; only technical jargon'; it is not a 2 because even one or two generic natural keywords are absent.

1 / 5

Distinctiveness Conflict Risk

The highly specific "Learn Disabled Example" / "learn.disabled" niche makes confusion with unrelated skills unlikely, matching 'Mostly distinct; minor overlap risk'. It is not a 5 because "Printing Press CLI" is a family name that overlaps with other printing-press CLI skills and the trigger phrasing is not distinct natural language.

4 / 5

Total

9

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

mvanhorn/cli-printing-press

Path

testdata/golden/expected/generate-learn-disabled-api/learn-disabled-example/SKILL.md

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.