blocking-io-guard

Ensure async-path backend code that could block the asyncio event loop is protected by a teeth-verified runtime anchor in tests/blocking_io/. Use when changing backend Python under app/, packages/harness/deerflow/, or scripts/, when running a blocking-IO triage round over the whole repo, or when a reviewer/CI asks for blocking-IO coverage. Runs a deterministic scan (changed-lines or full-repo), routes each candidate, drafts/extends an anchor, and proves it fails when the blocking IO regresses.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

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.

A well-structured SOP router with copy-paste commands, explicit red/green teeth validation, and clean one-level-deep references to real bundle files. The only weakness is mild verbosity from a repeated cross-file caveat and a tangential batching-policy paragraph.

Suggestions

State the same-file async-reachability caveat once (e.g. in Step 1's routing) and reference it from Step 0 instead of repeating the full explanation in both places.

Consider moving the 'Batching policy (PR sizing)' paragraph into a short reference note or sop-skeleton.md so the core Step 0 scope instructions stay focused on running the scan.

Dimension	Reasoning	Score
Conciseness	Mostly lean and task-oriented with copy-paste commands, but the cross-file caveat is restated across Step 0 and Step 1, and the 'Batching policy (PR sizing)' paragraph is tangential to the core routing SOP — minor trimming opportunities.	4 / 5
Actionability	Fully executable guidance throughout — concrete commands ('uv run --project backend python scripts/scan_changed_blocking_io.py --base origin/main', 'make detect-blocking-io', 'cd backend && make test-blocking-io'), exact file paths, and a decision router with dispositions; for an instruction/routing skill this is copy-paste ready.	5 / 5
Workflow Clarity	Steps 0–6 are clearly sequenced with explicit validation checkpoints — Step 2 re-scan confirming the candidate vanishes (match by stable key, not line), and Step 5's mandatory RED-then-GREEN teeth check — plus an explicit error-recovery feedback loop ('If it still shows ... go back before touching any test').	5 / 5
Progressive Disclosure	SKILL.md is a concise overview that signals one-level-deep references clearly ('Read references/good-anchor-rules.md before writing any anchor'; 'Only read references/sop-skeleton.md when generalizing'), and both referenced files exist in the bundle; detailed anchor rules and the generic skeleton are appropriately split out.	5 / 5
	Total	19 / 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.

A model description: third-person voice, concrete actions, an explicit 'Use when' clause with three natural triggers, and a distinct niche that minimizes conflict risk. No vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Runs a deterministic scan (changed-lines or full-repo), routes each candidate, drafts/extends an anchor, and proves it fails when the blocking IO regresses' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (ensure async-path code is protected by a teeth-verified runtime anchor; scans/routes/drafts/proves) and 'when' via a concrete 'Use when ...' clause with three trigger conditions.	5 / 5
Trigger Term Quality	Three explicit natural trigger scenarios — 'when changing backend Python under app/, packages/harness/deerflow/, or scripts/', 'when running a blocking-IO triage round over the whole repo', 'when a reviewer/CI asks for blocking-IO coverage' — cover the phrases a contributor would actually say, including path synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — asyncio event-loop blocking-IO protection with a teeth-verified runtime anchor — with triggers specific enough that no general-purpose skill would fire for the same situations.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: bytedance/deer-flow
Path: .agent/skills/blocking-io-guard/SKILL.md
Commit: 2a261d2

Reviewed: 4 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.