CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

update-integrations

Sync the public integrations page (`public/integrations.html`) with the MCP servers this platform actually exposes. The page is 100% dynamic — it renders whatever `/api/v1/catalogs` returns — so there is nothing per-MCP to edit in the HTML itself. The two committed sources that drive it are `seedDefaultCatalogs()` in `src/mcpCatalogStore.ts` (which MCPs appear) and the `SAMPLE_PROMPTS` map in `src/website/webServer.ts` (the "Sample Prompts" section on each card). This skill diffs the catalog against `SAMPLE_PROMPTS`, adds prompts for any MCP that's missing them (so its card stops showing "Sample prompts coming soon."), and flags catalog/icon gaps. Use whenever the user wants to update, sync, or audit the integrations page after adding or changing an MCP server, or invokes `/update-integrations [slug]`. Chained as a soft follow-up from `add-mcp-server`.

Quality

93%

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

92%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 exemplary single-purpose skill body: fully executable steps with exact file/function anchors, a real validation gate, thoughtful guardrails (orphaned keys, redeploy note, no-catalog slugs), and well-organized sections needing no external references. The only trimmable fat is deliberate duplication between the 'key fact'/'procedure' sections and the 'Failure modes' recap, plus the description restated as the opening section.

Suggestions

Deduplicate 'Failure modes' against earlier sections: the dynamic-page rule, self-healing JSON, no-catalog-entry, and over-promising items each restate guidance already given in 'The key fact' and the procedure — one-line pointers or a merged list would cut ~10 lines.

Compress 'The key fact' section, since it restates the description verbatim in substance; the two-source table alone carries the needed context.

DimensionReasoningScore

Conciseness

The body is efficient and project-specific — it explains nothing Claude already knows — but it repeats itself: the dynamic-page rule, the self-healing `data/mcp-catalog.json` behavior, the no-catalog-entry guard, and the over-promising caution each appear both in the 'key fact'/procedure sections and again in 'Failure modes', and 'The key fact' section restates the description almost in full. This matches the score-4 anchor ('minor instances of over-explanation that could be trimmed') rather than the score-5 'every token earns its place'.

4 / 5

Actionability

Every step is executable against the repo: exact function (`seedDefaultCatalogs()`), an exact search anchor ('const SAMPLE_PROMPTS: Record<string, string[]> = {' with a ~line 2192 hint), a copy-paste verification command ('npx tsc --noEmit'), insertion/indentation instructions, and a concrete prompt-style spec with a worked example ('Who's out on leave next week?', not 'Query the absence API.'). For an instruction-only skill this fully covers the common cases, matching the score-5 anchor.

5 / 5

Workflow Clarity

The six steps (enumerate → read → diff → write → verify → report) are clearly sequenced with an explicit validation checkpoint (`npx tsc --noEmit`, with an explanation of what it catches and when `npm test` is instead needed) and error-handling guidance (stop on unknown slug; flag but don't delete orphaned keys). This matches the score-5 anchor's 'explicit validation steps; feedback loops for error recovery' rather than score-4's 'most checkpoints present'.

5 / 5

Progressive Disclosure

There are no bundle files, and none are needed: the ~90-line body is one tightly-coupled procedure that would not benefit from being split across references. Section structure (key fact / inputs / procedure / failure modes / relationships) makes navigation easy and all content is appropriately placed inline, which fits the spirit of the score-5 'appropriately split; easy navigation' anchor; the score-4 anchor's 'minor organization gaps' has no concrete instance here.

5 / 5

Total

19

/

20

Passed

Description

92%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 highly specific, third-person description that names exact files and functions, states the complete action set, and includes an explicit and concrete 'Use whenever' trigger clause with the slash-command invocation. Its only weakness is that a few natural user phrasings (e.g., 'sample prompts', 'MCP card') are not covered as trigger terms, and it front-loads implementation detail that is fully repeated in the body.

Suggestions

Add the natural phrases users would actually say — 'sample prompts', 'MCP cards show "coming soon"' — to the trigger clause so it fires on those phrasings, not just 'update/sync/audit the integrations page'.

Trim the implementation context (the 100%-dynamic explanation and the two-source file map) from the description, since the body's 'The key fact' section restates all of it; keep the description to what/when.

DimensionReasoningScore

Specificity

The description enumerates the skill's full action set concretely — 'diffs the catalog against SAMPLE_PROMPTS, adds prompts for any MCP that's missing them (so its card stops showing "Sample prompts coming soon."), and flags catalog/icon gaps' — and grounds them in named files and functions (`seedDefaultCatalogs()`, `src/mcpCatalogStore.ts`, `SAMPLE_PROMPTS` in `src/website/webServer.ts`). Coverage of the skill's behavior is comprehensive with no minor gaps, matching the score-5 anchor rather than the score-4 anchor.

5 / 5

Completeness

Both 'what' and 'when' are answered explicitly: the what is the diff/add/flag procedure, and the when is a concrete 'Use whenever the user wants to update, sync, or audit the integrations page after adding or changing an MCP server, or invokes /update-integrations [slug]' clause, plus the chaining context from add-mcp-server. This matches the score-5 anchor with concrete trigger phrases; the score-4 anchor's 'when could be more explicit' does not apply.

5 / 5

Trigger Term Quality

Good natural-term coverage: 'update, sync, or audit the integrations page', 'after adding or changing an MCP server', and the explicit '/update-integrations [slug]' invocation. It falls short of the score-5 anchor because common phrasings users would naturally say — 'sample prompts', 'MCP card', 'integrations cards' — are absent, though it comfortably exceeds the score-3 anchor's 'missing common variations'.

4 / 5

Distinctiveness Conflict Risk

The description carves a clear niche (syncing one specific dynamic page driven by two named sources) and explicitly disambiguates the closest sibling — 'Chained as a soft follow-up from add-mcp-server' — so overlap risk with that skill is addressed head-on. It matches the score-5 'clear niche with distinct triggers; minimal conflict risk' anchor rather than the score-4 'minor overlap risk' anchor.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

boarlabsxyz/awesome-mcp

Path

.claude/skills/update-integrations/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.