he-strategy

Compress HE cognition artifacts into evidence-backed strategy. Use when intent, review, triage, ADR, core, or source-prompt comparison evidence needs durable direction.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

62%

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

The body is a well-structured, validation-driven workflow with a clear procedure and feedback loops, and it appropriately uses a trigger-conditioned reference index. Its weaknesses are jargon density and minor redundancy, actionability that defers executable detail to external contracts, and reference paths that largely do not resolve within the bundled file structure.

Suggestions

Tighten the overlap between 'Failure Mode', 'Handoff Rules', and 'Anti-Patterns' into a single section to remove redundancy and reduce jargon load.

Inline a minimal concrete output example (a small artifact skeleton with the required fields) so the skill is actionable without opening every referenced contract.

Reconcile reference paths with the actual bundle: either ship the referenced files under the paths used (e.g., ../../references/skills/he-strategy/...) or rewrite the routes to point at the bundled references/ files so navigation resolves.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence without explaining known concepts, but it carries heavy internal jargon ('stage_arc_boundary', 'left_arc/active_arc/right_arc', 'coding_lens') and some redundancy across 'Failure Mode', 'Handoff Rules', and 'Anti-Patterns', fitting 'mostly efficient but includes some unnecessary explanation or could be tightened'; not a 3 because of that overlap and jargon density.	2 / 3
Actionability	Concrete guidance is present (output paths like '.harness/decisions/', required fields 'schema_version: 1', 'subagent_policy', gates 'skill_gate.py', Vale), but much executable detail is deferred to external referenced contracts and the Examples section gives user prompts rather than output samples, matching 'some concrete guidance but incomplete'; not a 3 because it is not copy-paste ready and key detail lives in referenced files.	2 / 3
Workflow Clarity	A numbered 10-step Procedure is paired with a Validation section recording each gate as 'pass, fail, or blocked' and 'Rerun failed gates', providing a clear sequence with explicit validation steps and a feedback loop; not a 2 because checkpoints and error-recovery are explicit rather than implicit.	3 / 3
Progressive Disclosure	The References section is well-signaled with trigger-conditioned one-level-deep routing ('Read when selecting mode output -> ...'), but scored against the actual bundle most paths ('../../references/...') do not resolve: only references/contract.yaml and references/evals.yaml match, while the other ~10 point outside the provided bundle, fitting 'some structure but could be better organized'; not a 3 because navigation is weakened by non-resolving paths.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 cleanly answers both what and when with an explicit 'Use when' trigger, but it leans on internal HE jargon and a single primary action verb. Trigger terms mix a few natural keywords with domain-specific phrasing that limits plain-language discoverability.

Suggestions

Add a second concrete action verb or outcome (e.g., 'extract, compress, and route') so the description lists multiple specific actions rather than one verb applied to a mode list.

Soften jargon in the trigger clause by pairing 'HE cognition artifacts' and 'durable direction' with plain terms users actually say (e.g., 'architecture review', 'write an ADR', 'triage findings').

Disambiguate the generic 'review' and 'triage' triggers by qualifying them (e.g., 'strategy review', 'evidence triage') to reduce overlap with general review/triage skills.

Dimension	Reasoning	Score
Specificity	Quotes 'Compress HE cognition artifacts into evidence-backed strategy' name one concrete action plus an enumerated mode list ('intent, review, triage, ADR, core, or source-prompt comparison'), matching the 'names domain and some actions, but not comprehensive' anchor; it is not a 3 because only one primary verb ('Compress...into strategy') is given rather than multiple distinct concrete actions.	2 / 3
Completeness	The description answers what ('Compress HE cognition artifacts into evidence-backed strategy') and when via an explicit 'Use when intent, review, triage, ADR, core, or source-prompt comparison evidence needs durable direction' trigger, matching the 'clearly answers both what AND when with explicit triggers' anchor; it is not a 2 because the 'Use when...' clause is present and explicit.	3 / 3
Trigger Term Quality	Natural terms users might say ('review', 'triage', 'ADR', 'intent') appear in 'Use when intent, review, triage, ADR, core...', but they are wrapped in internal jargon ('HE cognition artifacts', 'durable direction', 'source-prompt comparison evidence') and lack common variations, fitting 'some relevant keywords but missing common variations'; not a 3 due to the jargon load and absent plain-language variants.	2 / 3
Distinctiveness Conflict Risk	The HE-specific framing and enumerated modes carve a niche, but bare trigger words 'review' and 'triage' could overlap with generic review/triage skills, matching 'somewhat specific but could still overlap with similar skills'; not a 3 because those generic terms retain conflict risk.	2 / 3
	Total	9 / 12 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 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.