api-stream-diagnose
Skill6 starsChanged 3 months agoMITView on GitHub
Debug and verify streamed parsers, framing, terminal state and continuation requests. Use when a streamed response or parser fixture misbehaves. RU: стриминг, SSE, потоковый ответ.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/agent-hook-verify/references/claude.mdCLAUDE.md
- agent-command-runSkill
- agent-context-auditSkill
- agent-hook-verifySkill
- agent-integration-auditSkill
- agent-model-findSkill
- agent-project-syncSkill
- agent-skill-findSkill
- agent-skill-syncSkill
- agent-terms-defineSkill
- agent-workspace-migrateSkill
- api-contract-defineSkill
- api-docs-syncSkill
- api-yandex-oauth-runSkill
- code-async-reviewSkill
- code-cli-buildSkill
- code-config-auditSkill
- code-durable-reviewSkill
- code-performance-fixSkill
- code-state-verifySkill
- deploy-artifact-publishSkill
- deploy-rollout-runSkill
- design-brand-buildSkill
- docs-claims-verifySkill
- docs-diagram-buildSkill
- docs-prose-fixSkill
- git-branch-cleanSkill
- git-merge-syncSkill
- git-path-runSkill
- git-repo-runSkill
- git-worktree-guardSkill
- infra-container-setupSkill
- infra-network-diagnoseSkill
- infra-project-migrateSkill
- infra-runbook-buildSkill
- kanban-board-auditSkill
- kanban-card-buildSkill
- kanban-card-planSkill
- kanban-card-reviewSkill
- kanban-card-runSkill
- kanban-card-verifySkill
- kanban-epic-coordinateSkill
- kanban-queue-coordinateSkill
- kanban-roadmap-planSkill
- kanban-schedule-runSkill
- monitor-telemetry-setupSkill
- personal-action-planSkill
- quality-artifact-verifySkill
- quality-change-reviewSkill
- quality-change-verifySkill
- research-prior-art-findSkill
- research-source-auditSkill
- research-source-findSkill
- research-spike-runSkill
- security-access-diagnoseSkill
- security-api-hardenSkill
- security-boundary-hardenSkill
- security-boundary-reviewSkill
- security-filesystem-hardenSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
When a protocol emits partial structured calls or other sparse deltas, validate fragments according to that protocol and assemble them by …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Stream protocol contracts
Use when a streamed response, parser fixture, event-level usage guard or continuation request behaves unexpectedly. Inspect the actual parser, framing, yielded types, state ownership, terminal marker and client loop before changing a fixture or production logic. Do not infer an event shape from a nearby model or assume each transport chunk is a complete event.
Build the smallest valid synthetic stream with real parser and dispatch seams. Cover fragmented frames, multiline events, state-establishing messages, terminal state and documented limits as applicable. First prove the parser reaches the intended state; then separately prove request count and continuation behavior, including identity, policy and privacy flags on each request. A fixture cannot make an intentionally disabled branch reachable.
Validate an event-level budget only after the protocol has assembled the relevant event; one network read or data line is not necessarily one event. Bound frame and buffering growth while parsing, retain the original byte stream when the contract requires passthrough, and establish a protocol-valid positive control through the installed consumer before treating an absent guard rejection as a product defect.
For security and durable delivery, distinguish local send completion from receiver consumption and acknowledgment. Test replay and finalization only through authorized isolated components; test-only controls must be capability-gated and unavailable to ordinary production requests. Keep an active timeout or transport failure distinct from a later cleanup failure. Report synthetic, integration and live-provider evidence separately.
When a protocol emits partial structured calls or other sparse deltas, validate fragments according to that protocol and assemble them by the documented identity and ordering before judging the final object. Interleaved text, usage, completion and terminal markers may have distinct timing; test the real parser and consumer with representative fragments without requiring each delta to be a complete object. Do not invent provider-specific fields or terminators.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

