CtrlK
BlogDocsLog inGet started
Tessl Logo

real-time-sync

How to keep the UI in sync with agent changes via SSE plus polling fallback. Use when wiring query invalidation for new data models, debugging UI not updating, or understanding jitter prevention.

59

Quality

70%

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 ./.agents/skills/real-time-sync/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with complete, executable code and well-organized sections, but it is over-long for a single file with redundant explanations and lacks explicit verification checkpoints in its workflow. It would benefit from splitting detail into reference files and tightening repeated passages.

Suggestions

Move the detailed "Action Routes and Live Sync" and "Granular server-side merge" sections into a reference file (e.g. references/action-sync.md) and link to them from a leaner overview, improving progressive disclosure.

Remove redundant restatements: delete How It Works step 5 (it repeats the Rule) and de-duplicate the sync mechanism explanation between "How It Works" and "Action Routes and Live Sync".

Add an explicit verification checkpoint to the wiring workflow, e.g. after folding a counter into a query key, confirm the query refetches on a write by checking React Query devtools or the network tab.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes framework competence (it does not explain basic SSE/React Query concepts), but it repeats material: step 5 of "How It Works" restates the Rule, and the "Action Routes and Live Sync" section re-explains the sync mechanism. This matches "Mostly efficient but includes some unnecessary explanation or could be tightened" rather than the every-token-earns-its-place bar of 3.

2 / 3

Actionability

It provides multiple complete, copy-paste-ready TypeScript examples with real imports (useDbSync, useChangeVersion with useQuery, subscribeSyncEvents, useReconciledState, tab-id setup) plus a concrete sources table and tuning values. This matches "Fully executable code/commands; specific examples; copy-paste ready".

3 / 3

Workflow Clarity

Sequences are present (How It Works 1-5, Jitter Prevention 1-3, a numbered best-path under Action Routes) and a Troubleshooting table acts as a debug aid, but there is no explicit validation/verification checkpoint in the wiring workflow and explanatory prose is interleaved with the steps. This fits "Steps listed but validation gaps; sequence present but checkpoints missing or implicit"; it avoids 1 because the ordering is clear and the 3-anchor would require explicit validation feedback loops.

2 / 3

Progressive Disclosure

There are no bundle files (no references/, scripts/, or assets/) and the ~230-line body is a single monolithic file, though it is organized into clear sections and points to related skills (one level deep) via "Related Skills" and inline "See real-time-collab" mentions. This matches "Some structure but... content that should be separate is inline" rather than 3, since nothing is split into reference files and the under-50-lines exception does not apply.

2 / 3

Total

9

/

12

Passed

Description

75%

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 answers both what and when with a clear, distinctive niche, but its action list is a single framed goal rather than multiple concrete actions and its trigger terms lean on internal jargon. Strong on completeness and distinctiveness, weaker on specificity and natural trigger coverage.

Suggestions

Lead with third-person concrete actions instead of a single goal, e.g. "Keeps the UI in sync with agent changes by streaming writes over SSE with polling fallback, folding per-source change counters into React Query keys, and preventing edit jitter."

Add natural user-facing trigger terms alongside the jargon, such as "real-time updates", "live UI refresh", or "auto-refresh after agent writes".

Broaden the Use-when list with a simpler variation like "Use when the UI is not updating after an agent writes to the database."

DimensionReasoningScore

Specificity

Names the domain and concrete mechanisms ("SSE plus polling fallback", "query invalidation", "jitter prevention") but frames a single goal ("keep the UI in sync") rather than listing multiple concrete actions, matching the score-2 anchor "Names domain and some actions, but not comprehensive". It falls short of 3 because there is no enumerated set of specific actions comparable to "Extract text..., fill forms, merge documents".

2 / 3

Completeness

It explicitly answers both what ("How to keep the UI in sync with agent changes via SSE plus polling fallback") and when ("Use when wiring query invalidation... debugging UI not updating..."), with an explicit trigger clause. This matches the score-3 anchor "Clearly answers both what AND when with explicit triggers".

3 / 3

Trigger Term Quality

The "Use when" clause supplies three triggers ("wiring query invalidation", "debugging UI not updating", "jitter prevention"), with "UI not updating" being natural, but the set leans on framework jargon and omits common variations a user might say ("real-time", "live updates", "auto-refresh"). This fits "Some relevant keywords but missing common variations" rather than the broad natural-term coverage of 3.

2 / 3

Distinctiveness Conflict Risk

The niche is highly specific (agent-change UI sync via SSE + polling fallback, query invalidation, jitter prevention) with triggers unlikely to fire for unrelated skills. This matches "Clear niche with distinct triggers; unlikely to conflict"; it is well above the score-2 overlap anchor.

3 / 3

Total

10

/

12

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.

Validation13 / 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

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
BuilderIO/agent-native
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.