CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

recurring-jobs

The legacy manage-jobs compatibility surface, job files under jobs/, and cron scheduler internals. Use when maintaining manage-jobs integrations or debugging the scheduler.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

86%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.

A dense, well-structured reference skill that assumes competence and delivers only non-obvious domain facts, with concrete tools, paths, and safeguards for the risky legacy-job operations. The only notable gap is the absence of a concrete create/frontmatter example that would make the most common task copy-paste ready.

DimensionReasoningScore

Conciseness

Every section carries only repo-specific facts Claude cannot know (scheduler tick cadence and per-platform firing behavior, the mcpTools allowlist rule, the job-fields-dropped audit event) with zero padding or explanation of known concepts. This matches 'lean and efficient; every token earns its place.'

5 / 5

Actionability

Concrete, executable guidance throughout: a tool-action table for manage-jobs, exact file paths with function names under Key Files, the stable URL '/agent#jobs', and the exact audit query (list-audit-events with action: "job-fields-dropped"). It misses anchor 5 because no example of a create invocation or a job file's frontmatter shape is shown, leaving the most common operations without a concrete template.

4 / 5

Workflow Clarity

'How It Works' gives a clear 5-step runtime sequence, and the risky write operations carry explicit checkpoints: create 'fails if the name exists', 'patch fields in place; rebuilding a file... drops the rest', and dropped fields are caught by the job-fields-dropped audit event. Not anchor 5 because there is no validate-before-proceeding loop for job-file edits, only after-the-fact detection.

4 / 5

Progressive Disclosure

A single well-organized file with clean section headers and tables; nothing inlined that belongs in a separate file. It defers the shared product model to a sibling skill up front ('Read automations for the product model...') and closes with one-level-deep, clearly signaled related-skill references, matching the clear-overview anchor.

5 / 5

Total

18

/

20

Passed

Description

70%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 well-scoped, appropriately concise description with an explicit 'Use when' clause and a clearly delimited legacy niche. Its main gaps are a thin list of concrete capabilities and missing natural trigger synonyms ('recurring', 'scheduled', 'cron job').

Suggestions

Name 1-2 concrete capabilities in the 'what' clause (e.g., 'create, list, and update recurring job files under jobs/ and their cron schedules') so specificity reaches the comprehensive anchor.

Add missing natural trigger phrases such as 'recurring', 'scheduled jobs', or 'a job did not fire/run' to broaden when-clause coverage and reduce ambiguity with the sibling automations skill.

DimensionReasoningScore

Specificity

Names the domain precisely ('manage-jobs compatibility surface, job files under jobs/, and cron scheduler internals') and gives two action contexts ('maintaining manage-jobs integrations', 'debugging the scheduler'), but never enumerates the concrete operations the skill supports (create/list/update jobs, cron parsing). This matches 'names domain and 1-2 concrete actions, but not comprehensive' rather than anchor 4, which expects a list of specific actions.

3 / 5

Completeness

Both parts are present: the 'what' ('The legacy manage-jobs compatibility surface, job files under jobs/, and cron scheduler internals') and an explicit 'when' ('Use when maintaining manage-jobs integrations or debugging the scheduler'). Not anchor 5 because the trigger clause covers only two scenarios and omits common triggers such as a scheduled job not firing or questions about the jobs/ directory.

4 / 5

Trigger Term Quality

Good keyword coverage with natural terms users would say: 'manage-jobs', 'job files', 'cron scheduler', 'debugging the scheduler'. It falls short of anchor 5 because common synonyms like 'recurring' and 'scheduled jobs' are absent, leaving a few natural phrasings uncovered.

4 / 5

Distinctiveness Conflict Risk

'legacy manage-jobs', 'cron scheduler internals' carve a clearly distinct niche with low conflict risk. It stays at anchor 4 rather than 5 because the sibling 'automations' skill owns the primary scheduled-product model, so generic 'scheduled'/'recurring' queries could land on either skill.

4 / 5

Total

15

/

20

Passed

Validation

87%

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

Validation — 14 / 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

Total

14

/

16

Passed

Repository

BuilderIO/agent-native

Path

.agents/skills/recurring-jobs/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.