new-source

Investigate and implement support for a new waste-collection provider in hacs_waste_collection_schedule. Use when a contributor wants a council, municipality, or provider added, including shared-platform and ICS options.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

The body is an efficient, well-sequenced workflow that delegates to specialized agents and bakes verification into nearly every stage, with no wasted tokens or concept over-explanation. Its only notable gap is that failure recovery is summarized as 'resolve test failures' rather than spelled out as an explicit validate-fix-retry loop.

Suggestions

Replace the single 'resolve test failures before submission' step with an explicit feedback loop, e.g. 'On failure: read the agent's error report, apply the fix, re-run lint/tests, and only proceed when green'.

Optionally link to a one-level-deep reference (e.g. AGENTS.md) for the canonical lint/test command list so the exact commands are copy-paste-ready rather than implied.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: each step is a single directive line with zero padding, no explanations of what a waste-collection source or ICS feed is, and every token earns its place, matching the top anchor for token efficiency.	5 / 5
Actionability	Guidance is concrete and directive — it names exact agents ('source-investigator', 'source-implementer'), real artifacts ('SOURCE_CODEOWNERS', 'AGENTS.md'), and a precise PR-title pattern — but it stays at the instruction level with no executable code/commands, which the rubric notes is acceptable for an instruction-only skill yet leaves minor gaps versus copy-paste-ready examples.	4 / 5
Workflow Clarity	The Gather → Investigate → Implement → Prepare submission sequence is clearly ordered with verification built in ('lint every changed Python file', 'run structural tests', 'live-test real TEST_CASES', 'resolve test failures before submission'), giving strong checkpoints; it falls just short of the top anchor because the failure-handling feedback loop is a single 'resolve' directive without an explicit validate-fix-retry cycle.	4 / 5
Progressive Disclosure	For a sub-50-line single-purpose skill with no external references needed, the content is well organized into four clearly labeled sections and assumes no bundle files exist (none are present in references/scripts/assets), so per the simple-skill exception it scores the top anchor on clear, well-organized structure.	5 / 5
	Total	18 / 20 Passed

Description

82%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 states what the skill does and when to use it with concrete, domain-specific trigger terms and minimal conflict risk. Its main weakness is specificity: the actions are named at a high level rather than enumerated, so the capabilities read slightly generic despite the strong trigger framing.

Suggestions

Tighten the 'what' clause by naming the concrete deliverables, e.g. 'Investigate provider APIs/ICS feeds, implement a collection source or shared-config change, add documentation, and prepare a PR'.

Add a few more natural synonyms a contributor might say ('collection schedule', 'bin pickup', 'calendar feed') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('support for a new waste-collection provider') and two concrete actions ('Investigate' and 'implement'), but the actions remain high-level verbs without enumerating the specific sub-tasks (investigation, source implementation, documentation, PR submission) it actually performs, so coverage is incomplete per the anchor.	3 / 5
Completeness	It explicitly answers both 'what' ('Investigate and implement support for a new waste-collection provider in hacs_waste_collection_schedule') and 'when' ('Use when a contributor wants a council, municipality, or provider added, including shared-platform and ICS options') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It surfaces several natural user phrases ('council', 'municipality', 'provider added', 'shared-platform', 'ICS'), which map well to how a contributor would phrase the request; a few common synonyms (e.g., 'collection schedule', 'bin pickup') are missing, leaving it just short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The hacs_waste_collection_schedule-specific niche plus provider/council/municipality/ICS triggers form a clearly bounded scope unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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: mampfes/hacs_waste_collection_schedule
Path: .agents/skills/new-source/SKILL.md
Commit: 82a9f36

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.