he-compound-refresh

Analyze and validate compound Harness Engineering run state, blockers, validation status, and Linear context. Use when lifecycle runs drift, gates fail, blockers appear, or compound work needs refresh.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

The content is well-structured, concise, and has a clear sequenced workflow with explicit fail-fast validation. It loses points on actionability (vague about which live-state checks to run) and progressive disclosure (referenced bundle files are missing, so the offload-to-references promise is broken).

Suggestions

Replace "the smallest safe live-state checks" with a concrete, enumerated set of commands or checks to run (e.g., specific git/CI/Linear lookups) so the procedure is copy-paste actionable.

Either create the referenced files (references/session-evidence-contract.md and the two asset icons) or remove/relabel the broken links so the progressive-disclosure pointers actually resolve.

Move the inline Validation checklist into the Procedure as numbered checkpoints (e.g., a validate step after classification) to tighten the feedback loop within the workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned (Philosophy, When to use, Procedure, Validation, Constraints, Anti-patterns) with no padding explaining concepts Claude already knows (PR, CI, validation); every section is purposeful, matching the lean-and-efficient anchor.	3 / 3
Actionability	Concrete specifics exist (the 13-item maintenance taxonomy, mode normalization, target inventory list) but key execution details are abstract — "Re-run or inspect the smallest safe live-state checks" never names which checks or commands, leaving the guidance incomplete per the some-concrete-but-incomplete anchor.	2 / 3
Workflow Clarity	The Procedure is a clearly sequenced 1-8 flow with an explicit validation checkpoint ("Fail fast: stop at first failed gate and do not proceed") and a parallel Validation checklist, plus Failure Modes for error recovery, matching the clear-sequence-with-explicit-validation anchor.	3 / 3
Progressive Disclosure	The body is well-organized and signals a one-level reference to session-evidence-contract.md, but that referenced file and the cited asset icons (./assets/icon-small.png, ./assets/icon-large.png) do not exist in any bundle directory, so the signaled navigation does not resolve.	2 / 3
	Total	10 / 12 Passed

Description

85%

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

The description is strong: it states concrete capabilities and an explicit Use-when trigger with a clear, distinctive niche. Its main weakness is trigger-term naturalness, leaning on internal jargon and omitting the plain-language variations (continue/resume/re-check) it later relies on in the body.

Suggestions

Add the natural trigger verbs users actually say ("continue, resume, re-check") to the description's Use-when clause alongside the existing drift/blockers/refresh terms.

Soften jargon in the trigger clause (e.g., "CI gates fail" -> "CI checks fail") so it reads as something a user would naturally say.

Dimension	Reasoning	Score
Specificity	"Analyze and validate compound Harness Engineering run state, blockers, validation status, and Linear context" lists multiple concrete actions (analyze, validate, blockers, validation status, Linear context), matching the multiple-specific-actions anchor.	3 / 3
Completeness	It explicitly answers what ("Analyze and validate compound Harness Engineering run state, blockers, validation status, and Linear context") and when ("Use when lifecycle runs drift, gates fail, blockers appear, or compound work needs refresh"), satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	"Use when lifecycle runs drift, gates fail, blockers appear, or compound work needs refresh" has relevant keywords (drift, blockers, refresh) but is burdened with internal jargon ("compound Harness Engineering", "gates") and omits the simpler natural variations (continue, resume, re-check) that appear only in the body.	2 / 3
Distinctiveness Conflict Risk	The "compound Harness Engineering" run-state niche plus "Linear context" gives a clear, distinctive scope with triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 missing, 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: jscraik/Agent-Skills
Commit: 5a6027f

Reviewed: 5 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.