CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

omp-hooks

Use when writing, debugging, or configuring an omp hook or extension — blocking or rewriting tool calls, redacting tool output, reshaping LLM context, registering tools/commands, or wiring modules through config.yml. Covers ExtensionAPI (current) vs HookAPI (legacy), the event catalog, discovery and load order, and disable controls. Not for Claude Code hooks (~/.claude/settings.json) or the shared harness safety guard (~/.agents/harness/hooks/).

Quality

97%

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

93%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 dense, expert-level reference that assumes competence and delivers only non-obvious specifics: exact return-shape semantics, load-order rules, and failure modes that genuinely bite. The single weakness is the missing verification/debugging loop for confirming an extension loaded or a handler fired.

DimensionReasoningScore

Conciseness

Every section carries non-obvious specifics (e.g., "a raw setInterval... becomes an uncaughtException, and the postmortem handler tears down the whole session"; "handlers do not see each other's revisions"). No padding and no explanation of concepts Claude already knows — every token earns its place.

5 / 5

Actionability

Copy-paste-ready TypeScript factory example with real handler logic, a concrete config.yml block, named APIs and flags (ctx.setInterval, --no-extensions, disabledExtensions, -e/--extension), and exact return shapes for each contract. Fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

A clear logical progression (disambiguate which hook system → choose ExtensionAPI → learn the three contracts → placement/load order → pitfalls) but no explicit verification checkpoints, e.g. confirming a module actually loaded or a handler fired — a notable gap given "debugging" is a stated use case. Above the level-3 anchor (sequence is coherent, not gapped), below 5 (no feedback loops or validation steps).

4 / 5

Progressive Disclosure

Core contracts and pitfalls stay inline while bulk detail is split into two real, well-signaled reference files (references/event-catalog.md, references/configuration.md), each described by what it contains. One level deep, easy navigation, content appropriately placed.

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: explicit use-when triggers, five concrete capabilities, current-vs-legacy API disambiguation, and explicit not-for exclusions that prevent mis-triggering on the two adjacent hook systems. Nothing vague, padded, or over-claimed.

DimensionReasoningScore

Specificity

Lists five concrete actions — "blocking or rewriting tool calls, redacting tool output, reshaping LLM context, registering tools/commands, or wiring modules through config.yml" — plus coverage areas ("the event catalog, discovery and load order, and disable controls"). Comprehensive coverage with no vague language, matching the top anchor rather than the minor-gaps anchor at 4.

5 / 5

Completeness

An explicit "Use when writing, debugging, or configuring an omp hook or extension" clause answers "when" with concrete trigger phrases, and the action list plus "Covers ExtensionAPI (current) vs HookAPI (legacy)..." fully answers "what". Both halves are explicit, so it exceeds the level-4 anchor.

5 / 5

Trigger Term Quality

Natural trigger verbs ("writing, debugging, or configuring") plus the domain nouns users would actually say ("omp hook or extension", "ExtensionAPI", "HookAPI", "config.yml"). Synonyms (hook/extension) and a file path are both present, satisfying the comprehensive-coverage anchor.

5 / 5

Distinctiveness Conflict Risk

Explicit exclusions — "Not for Claude Code hooks (~/.claude/settings.json) or the shared harness safety guard (~/.agents/harness/hooks/)" — carve out the adjacent hook systems that would otherwise mis-trigger. Clear niche with distinct triggers and minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

phatblat/dotfiles

Path

.agents/skills/omp-hooks/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.