CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-rss-feed

Add or change a WorldMonitor news/RSS feed — catalog entry, RSS proxy allowlist mirrors, source tier, propaganda-risk review, and attribution. Use when adding a feed URL, a publisher, or a domain that the RSS proxy must fetch.

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 tightly written, project-specific runbook: it assumes Claude's competence, spends tokens only on facts unique to this codebase (mirror files, Edge limitations, SSRF rationale), and closes with executable verification plus a symptom-to-cause diagnostic. Structure and sequencing are clear with no validation gaps.

DimensionReasoningScore

Conciseness

Every line carries non-obvious, project-specific facts Claude could not infer ("api/_rss-allowed-domains.js (literal array; Edge cannot import JSON)", "Railway reads the mirror", "PR CI never runs either on purpose (contributor-controlled URLs would be an SSRF surface)") with zero padding or explanation of known concepts. This is the 'lean and efficient; every token earns its place' anchor; the score-4 anchor's 'minor instances of over-explanation' does not apply.

5 / 5

Actionability

Guidance is fully executable: exact file paths for all allowlist mirrors, copy-paste commands ("node scripts/run-data-tests.mjs tests/feed-catalog-drift.test.mts tests/edge-functions.test.mjs", "npm run sources:check", then "npm run sources:generate"), and a ready-to-run fetchFeed one-liner with only a URL placeholder. It matches the 'copy-paste ready code or commands' anchor rather than the score-4 anchor, which allows 'minor gaps'.

5 / 5

Workflow Clarity

The sequence — editorial checks, wire it, verify — is explicitly ordered, and verification is concrete (mirror-parity tests, "npm run test:related"), satisfying the batch-operation validation requirement. It even includes an error-recovery feedback loop: "A panel showing 'No news available' with HTTP 403 'Domain not allowed' ... means a missing allowlist entry", matching the score-5 anchor with explicit validation and recovery guidance.

5 / 5

Progressive Disclosure

The skill is under 50 lines with no bundle files and no need for external references, and it is organized into three well-ordered sections ("Editorial checks first", "Wire it", "Verify") plus a source-pointer header. Per the rubric's simple-skill guidance, this earns the top score on well-organized sections alone.

5 / 5

Total

20

/

20

Passed

Description

100%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.

An exemplary description: it states the full scope of the task in concrete terms and pairs it with an explicit, natural-language trigger clause covering the three realistic request phrasings. Project-specific naming makes confusion with other skills essentially impossible.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — "catalog entry, RSS proxy allowlist mirrors, source tier, propaganda-risk review, and attribution" — giving comprehensive, specific coverage of everything the skill touches rather than vague domain language. It matches the anchor 'Lists multiple specific concrete actions; comprehensive coverage' and clearly exceeds the score-4 anchor, which expects only 'minor gaps in coverage'.

5 / 5

Completeness

It explicitly answers both questions: the "what" via the em-dash action list and the "when" via an explicit "Use when..." clause with three concrete trigger phrases. This mirrors the score-5 anchor example's structure exactly; the score-4 anchor ('when' could be more explicit) does not apply since the triggers are fully explicit.

5 / 5

Trigger Term Quality

Trigger phrases "adding a feed URL, a publisher, or a domain that the RSS proxy must fetch" cover the natural ways a user would request this, with synonyms present ("news/RSS feed", "feed URL", "publisher", "domain"). No missing natural term is identifiable for this domain, so it fits the comprehensive-coverage anchor better than the score-4 anchor ('a few natural terms missing').

5 / 5

Distinctiveness Conflict Risk

The niche is tightly scoped by project-specific terms — "WorldMonitor news/RSS feed" and "RSS proxy allowlist" — that no other skill would plausibly share, giving minimal conflict risk. It clearly occupies the 'clear niche with distinct triggers' anchor rather than the score-4 anchor's 'minor overlap risk with closely related skills'.

5 / 5

Total

20

/

20

Passed

Validation

75%

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

Validation — 12 / 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

relative_links

Relative link issues: 2 suspicious

Warning

referenced_paths_exist

Referenced path issues: 4 missing, 3 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

koala73/worldmonitor

Path

.agents/skills/add-rss-feed/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.