agent-hooks

Four lifecycle hooks every agent runs: on-session-start scans LESSONS-LEARNED.md, resumes checkpoints; on-pre-delegate verifies tracker issues, file partitions; on-post-delegate runs fast-review, CI checks; on-session-end executes session guard, writes logs. Use when starting a new session, running pre-flight checks before delegation, coordinating between agents, reviewing a completed handoff, or wrapping up a session. Trigger terms: multi-agent setup, delegate tasks, agent coordination, session management, run pre-flight checks, start a new session, coordinate between agents, wrap up session

Quality

92%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

92%

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

This is a well-crafted skill that efficiently communicates four lifecycle hooks with concrete, executable commands and clear sequencing. The ASCII flow diagram, numbered tables, and hard gate markers make the workflow easy to follow. The main weakness is that several referenced files (HOOKS-REFERENCE.md, logging-mandatory.md) and skills (fast-review, context-map, self-improvement) cannot be verified since no bundle files are provided, and skill references lack navigation links.

Suggestions

Provide HOOKS-REFERENCE.md in the bundle or inline the most critical extended checks to ensure the skill is self-sufficient

Add explicit links or load instructions for referenced skills (fast-review, context-map, self-improvement, observability-logging) rather than just naming them in bold

Dimension	Reasoning	Score
Conciseness	Every line serves a purpose. No explanations of what agents or lifecycle hooks are conceptually. Tables are tight, commands are specific, and the ASCII diagram efficiently conveys the flow. No wasted tokens.	3 / 3
Actionability	Each hook provides concrete, executable commands (rg, gh, jq, opencastle CLI, pnpm). The pre-delegate checklist has specific verification commands with expected outputs (e.g., '= empty', '= CLOSED'). Copy-paste ready.	3 / 3
Workflow Clarity	Four hooks are clearly sequenced with the ASCII diagram showing their relationship. Each hook has numbered steps in order. Hard gates are explicitly marked with ⛔. The pre-delegate section requires all 6 checks to pass before proceeding, and post-delegate includes a failure escalation path (3rd failure → AGENT-FAILURES.md).	3 / 3
Progressive Disclosure	References to HOOKS-REFERENCE.md and snippets/logging-mandatory.md are well-signaled and one level deep, which is good. However, since no bundle files are provided, we cannot verify these references exist. The skill also references other skills (fast-review, context-map, self-improvement, observability-logging) without clear navigation links, making discovery harder.	2 / 3
	Total	11 / 12 Passed

Description

92%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description that clearly articulates four specific lifecycle hooks with concrete actions, provides explicit 'Use when' guidance, and lists relevant trigger terms. Its main weakness is moderate overlap risk with other agent coordination or session management skills, though the specific four-hook lifecycle structure helps differentiate it. The description uses proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across four lifecycle hooks: scanning LESSONS-LEARNED.md, resuming checkpoints, verifying tracker issues, file partitions, running fast-review, CI checks, executing session guard, and writing logs.	3 / 3
Completeness	Clearly answers both 'what' (four lifecycle hooks with specific actions) and 'when' (explicit 'Use when...' clause covering starting sessions, pre-flight checks, delegation coordination, reviewing handoffs, and wrapping up sessions).	3 / 3
Trigger Term Quality	Includes a comprehensive set of natural trigger terms like 'multi-agent setup', 'delegate tasks', 'agent coordination', 'session management', 'run pre-flight checks', 'start a new session', 'coordinate between agents', and 'wrap up session' — these cover natural variations a user would say.	3 / 3
Distinctiveness Conflict Risk	The multi-agent lifecycle hook concept is fairly specific, but terms like 'session management' and 'delegate tasks' could overlap with general task management or session-handling skills. The four-hook structure helps distinguish it, but 'coordination between agents' is broad enough to potentially conflict with other agent-related skills.	2 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: monkilabs/opencastle
Commit: 7a69a05

Reviewed: about 1 month 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.