CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

79

Quality

100%

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

100%

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

A well-engineered SOP: lean, action-dense, with an explicitly sequenced workflow and real validation checkpoints, plus exemplary progressive disclosure that signals exactly when to read each reference. The only minor gap is a referenced templates/anchor.template.py that is not present in the bundle.

DimensionReasoningScore

Conciseness

A lean procedural SOP that assumes Claude's competence — it never explains basic asyncio/event-loop concepts and every line is procedure, command, or actionable caution that earns its place.

3 / 3

Actionability

Provides copy-paste-ready commands (scan_changed_blocking_io.py, make detect-blocking-io, make test-blocking-io), concrete routing dispositions, and a stable match key (path, function, symbol) — fully executable guidance.

3 / 3

Workflow Clarity

Steps 0–6 are clearly sequenced with explicit validation checkpoints — Step 2 requires the finding to disappear, Step 5 mandates RED then GREEN teeth — plus feedback loops ('go back before touching any test') and the RULE discriminator.

3 / 3

Progressive Disclosure

The body is an overview pointing one level deep to references with conditional read guidance ('Read…before writing any anchor', 'Only read…when generalizing'), and both referenced files exist in the bundle.

3 / 3

Total

12

/

12

Passed

Description

100%

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 strong, specific description that states concrete capabilities and gives explicit, natural 'Use when' triggers for a well-scoped niche. It is dense but every clause carries capability or trigger information rather than fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Runs a deterministic scan (changed-lines or full-repo)', 'routes each candidate', 'drafts/extends an anchor', 'proves it fails when the blocking IO regresses' — matching the score-3 anchor for specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('Ensure…protected…Runs…routes…drafts…proves') and when ('Use when changing backend Python…when running a blocking-IO triage round…when a reviewer/CI asks'), with explicit triggers rather than implied ones.

3 / 3

Trigger Term Quality

The 'Use when' clause uses natural trigger terms a contributor would actually say — 'changing backend Python', 'blocking-IO triage round', 'reviewer/CI asks for blocking-IO coverage' — with good coverage of the niche's common phrasings.

3 / 3

Distinctiveness Conflict Risk

A clear, narrow niche (DeerFlow asyncio blocking-IO guard) with distinct triggers unlikely to fire for unrelated skills; voice is third-person/imperative as in the good examples.

3 / 3

Total

12

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
bytedance/deer-flow
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.