CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

parse-package-json

Extract version, dependencies, and metadata from package.json files. Use when needing project version, dependency list, or package metadata for releases, audits, or reports.

60

Quality

75%

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/parse-package-json/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 well structured and actionable but over-engineered for a trivial read-and-extract task, spending most of its tokens restating what Claude already knows about package.json. Its one bundle reference is dangling, which undermines both navigation and trust in the Supporting Files section.

Suggestions

Cut the boilerplate ceremony — the per-step 'Expected Input' and 'Tools Used' blocks, the field-by-field annotations, and the full sample package.json dump — and reduce the skill to the field list, error messages, and one compact example; Claude already knows package.json's shape.

Fix the dangling reference: either actually provide schema.json in a references/ directory or remove the 'Supporting Files' section, since a referenced file that does not exist breaks navigation.

Replace the terminal 'Return error' instructions in Error Handling with a brief recovery path (e.g., re-check the path or report which required fields are missing), which would also raise workflow clarity.

DimensionReasoningScore

Conciseness

The body pads a trivial task Claude already knows how to perform: per-step 'Expected Input'/'Tools Used' ceremony, field-by-field annotations like 'main: Entry point file', and an 18-line sample package.json dump that merely restates the field list. This is noticeably verbose with several padded sections (anchor 2), beyond anchor 3's 'some unnecessary explanation'.

2 / 5

Actionability

Concrete field lists, verbatim error messages ('package.json not found at {path}'), and explicit input/output examples make the guidance mostly executable. Minor gaps — 'Parse the JSON content and validate structure' is direction rather than a checkable procedure — keep it below anchor 5.

4 / 5

Workflow Clarity

The four steps are clearly sequenced with validation rules in Step 2 and a dedicated Error Handling section; the task is read-only so the destructive-operation cap does not apply. It is not 5 because error paths are terminal ('Return error') with no recovery feedback loop.

4 / 5

Progressive Disclosure

Sections are well organized, but the single bundle reference — 'schema.json: JSON schema defining expected package.json structure' — points to a file that does not exist anywhere in the skill directory, breaking navigation. Combined with ~150 lines of inlined field/example content that could live in a reference file, this fits anchor 3 rather than anchor 4's 'references mostly clear'.

3 / 5

Total

13

/

20

Passed

Description

83%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.

A strong description with an explicit what-and-when structure, third-person voice, and domain-specific triggers. The only gaps are the generic term 'metadata' and missing common synonyms like 'npm' or 'node' that users might naturally say.

DimensionReasoningScore

Specificity

The description names the domain ('package.json files') and three concrete actions ('Extract version, dependencies, and metadata'), which exceeds anchor 3's 1-2 actions but falls short of anchor 5 because 'metadata' is generic rather than comprehensive field-level coverage.

4 / 5

Completeness

It explicitly answers both 'what' ('Extract version, dependencies, and metadata from package.json files') and 'when' ('Use when needing project version, dependency list, or package metadata for releases, audits, or reports') with concrete trigger phrases, matching the anchor 5 example pattern; it is not 4 because the when-clause is already explicit and specific.

5 / 5

Trigger Term Quality

Natural phrases like 'package.json', 'project version', 'dependency list', 'releases, audits' give good keyword coverage, but common synonyms such as 'npm', 'node project', or 'deps' are missing, matching anchor 4 rather than 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

'package.json files' carves out a clear niche with distinct triggers, but 'extract metadata... for reports' leaves minor overlap risk with general JSON-parsing or file-reading skills, fitting anchor 4 rather than 5's minimal conflict risk.

4 / 5

Total

17

/

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

maslennikov-ig/claude-code-orchestrator-kit

Path

.claude/skills/parse-package-json/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.