CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

validate-report-file

Validate that worker-generated reports have all required sections and proper formatting. Use in quality gates, for report completeness checking, or when debugging missing report sections.

Quality

79%

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/validate-report-file/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 delivers a clear, well-sequenced validation workflow with concrete rules and worked examples that make it easy to execute correctly. Its weaknesses are redundancy (repeated output JSON, padded step blocks) and a broken self-referential pointer to a nonexistent schema.json, which hurt token efficiency and navigation.

Suggestions

Remove the duplicate output JSON in Example 1 (it is identical to Step 5's) and drop the 'Expected Input'/'Tools Used' filler blocks to tighten conciseness.

Fix or delete the 'Supporting Files' section: 'schema.json' does not exist in the bundle, and '(see Supporting Files section)' is self-referential.

Move the three full Examples (~140 lines) into a references/examples.md file and keep a one-line pointer in SKILL.md to improve progressive disclosure and token efficiency.

DimensionReasoningScore

Conciseness

Step instructions are lean, but the Step 5 output JSON is repeated verbatim in Example 1, "Expected Input"/"Tools Used" blocks pad the steps, and the self-referential "Supporting Files" line adds no value. Fits anchor 3 (mostly efficient but could be tightened); not 2 because the examples carry real signal rather than being padding.

3 / 5

Actionability

Enumerated required sections, exact format rules (H1 title, H2 sections, status emoji), a copy-paste-ready output JSON, and three worked input-to-output examples make this mostly executable. Not 5 because of minor gaps: Example 1 passes header validation despite lacking the required "Version identifier", and "Detailed Findings: Varies by report type" is underspecified.

4 / 5

Workflow Clarity

Five clearly sequenced steps (read, check sections, validate format, check consistency, return result), an explicit error-handling table, and a closing validation checklist give explicit checkpoints for a read-only task. Not 4 because no validation gaps remain — the skill is itself a validation gate and every failure mode has a defined response.

5 / 5

Progressive Disclosure

Section structure is clear, but the body references "`schema.json`: Report structure schema (see Supporting Files section)" — a self-referential pointer to a file that does not exist in the bundle — and the ~140-line Examples block is inlined where a one-level-deep reference file would fit. Fits anchor 3 (some structure, references not clearly signaled); not 4 because a broken reference is more than a minor organization gap.

3 / 5

Total

15

/

20

Passed

Description

78%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 cleanly answers both what the skill does and when to use it, with natural trigger phrases and third-person-style phrasing. Its main weakness is modest specificity — only two validation actions are named while the body covers several more.

DimensionReasoningScore

Specificity

Names the domain (worker-generated report validation) and two concrete actions ("have all required sections and proper formatting"), but coverage is not comprehensive — status-consistency checking and structured error output from the body are omitted. Not 4 because it lists fewer distinct specific actions than the anchor-4 example.

3 / 5

Completeness

Explicitly answers both questions: the "what" ("Validate that worker-generated reports have all required sections and proper formatting") and the "when" with three concrete trigger phrases ("quality gates", "report completeness checking", "debugging missing report sections"), matching the anchor-5 pattern. Not 4 because the when-clause is fully explicit rather than merely adequate.

5 / 5

Trigger Term Quality

"Use in quality gates, for report completeness checking, or when debugging missing report sections" gives good natural trigger coverage, but common variations like "validate a report", "check report structure", or "incomplete report" are missing. Not 3 because three distinct, naturally-spoken trigger phrases are present rather than just some relevant keywords.

4 / 5

Distinctiveness Conflict Risk

"Worker-generated reports" and "quality gates" carve a clear niche with distinct triggers, but "reports" and "formatting" are generic words with minor overlap risk against other report-writing or summary skills. Not 5 because a user asking about reports generically could plausibly trigger related skills too.

4 / 5

Total

16

/

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/validate-report-file/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.