CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

renovate

Generate renovate.json covering all dependency file types used in a repo, emit a GitHub Actions workflow that validates renovate.json on every PR, or generate a pre-commit hook for local validation.

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 ./plugins/platform-skills/skills/renovate/SKILL.md

The canonical home for this skill is renovate in nitinjain999/platform-skills

SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

An exceptionally actionable, well-sequenced skill body whose wizard, detection commands, and complete config/workflow templates leave nothing abstract. Its weaknesses are structural: the cited references/renovate.md does not exist, the bulk of the templates should live in reference files rather than inlined, and there is some duplication and time-sensitive version pinning that adds token cost without value.

Suggestions

Create the missing references/renovate.md (or remove the three dangling "Reference:" lines), and move the full GitHub Actions workflow YAML plus the per-manager packageRules/hostRules catalog into reference files so SKILL.md stays an overview.

Delete the duplicated Terraform WARNING blockquote at lines 248-261 — it repeats the module rule already shown at lines 274-280 in a confusing nested-packageRules form.

Isolate time-sensitive pins ("rev: 43.150.0", action SHAs) into the reference file or a clearly labeled examples section so version drift doesn't age the main body.

DimensionReasoningScore

Conciseness

The body is instruction-dense with no concept explanations Claude already knows, but it can be tightened: the Terraform WARNING blockquote (lines 248-261) duplicates the module rule shown again at lines 274-280, the pinned versions ("rev: 43.150.0", action SHAs) are time-sensitive inline rather than isolated, and next-steps boilerplate repeats across the three modes. This fits anchor 3 (mostly efficient, some tightening needed) rather than 4, whose 'minor instances' understate the duplication and version drift.

3 / 5

Actionability

Everything is fully executable: exact grep/find detection commands, complete per-manager JSON packageRules blocks, a complete copy-paste-ready GitHub Actions workflow with exact npx and pre-commit commands, and explicit assembly instructions. Placeholders like "<org>" and "<host>" are deliberately parameterized with clear substitution rules, matching the anchor-5 copy-paste-ready standard.

5 / 5

Workflow Clarity

Modes and steps are clearly sequenced (wizard → mode parse → Step 1 detect → 1.5 internal-source scan → 2 emit → 2.5 registries → assembly → 3 write/diff) with real checkpoints: coverage table printed before emitting, "Write to renovate.json? [y/N]" confirmation, and adaptive re-asks. It falls short of 5 because there is no error-recovery loop — no guidance for zero-managers-detected or for validating the emitted JSON (validation is delegated to other modes via a "Next" pointer).

4 / 5

Progressive Disclosure

All three modes cite "Reference: references/renovate.md", but no references/ directory or file exists — a dangling reference. Meanwhile the ~150-line GitHub Actions workflow YAML and the full per-manager packageRules/hostRules catalog are inlined in SKILL.md, content that clearly belongs in separate files. This matches anchor 2 (content that belongs in separate files is inlined) more than anchor 3, since the signaling exists but the referenced file is missing entirely.

2 / 5

Total

14

/

20

Passed

Description

75%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, specific, third-person description that concretely enumerates all three of the skill's capabilities with good domain keywords. Its only real weakness is the absence of any "Use when..." trigger guidance, which both caps completeness and leaves some natural trigger terms unused.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions Renovate, renovate.json, dependency update automation, or wants pre-commit/CI validation of Renovate config."

Include natural trigger synonyms users would say — "Renovate bot", "dependency updates", ".pre-commit-config.yaml" — to raise trigger-term coverage.

Consider naming the repo scan explicitly ("scans a repo for dependency manifests") so the detection capability is discoverable from the description alone.

DimensionReasoningScore

Specificity

The description enumerates all three concrete capabilities — "Generate renovate.json covering all dependency file types", "emit a GitHub Actions workflow that validates renovate.json on every PR", "generate a pre-commit hook for local validation" — matching the comprehensive multiple-concrete-actions anchor. Voice is third person ("Generate", "emit"), so no person penalty applies.

5 / 5

Completeness

The "what" is clearly and fully stated (three modes), but there is no "Use when..." clause or any equivalent explicit trigger guidance, which per judging guidelines caps completeness at 3. It is not 4 because the "when" is entirely absent, not merely imprecise; it is not 2 because the "what" is concrete and comprehensive.

3 / 5

Trigger Term Quality

Good natural keywords are present ("renovate.json", "GitHub Actions workflow", "pre-commit hook", "dependency file types", "PR"), but common variations users might say are missing — "Renovate" the bot by name, "dependency updates", and file extensions like ".pre-commit-config.yaml". This matches anchor 4 (good coverage, a few natural terms missing) rather than anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

"renovate.json" plus "GitHub Actions workflow that validates renovate.json" and "pre-commit hook" defines a clear niche with distinct triggers and minimal conflict risk with other skills, matching anchor 5.

5 / 5

Total

17

/

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

skill_md_line_count

SKILL.md is long (813 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

13

/

16

Passed

Repository

nitinjain999/platform-skills

Path

plugins/platform-skills/skills/renovate/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.